Forest Tree Species Distribution Mapping Using Landsat Satellite Imagery and Topographic Variables with the Maximum Entropy Method in Mongolia

NASA Astrophysics Data System (ADS)

Hao Chiang, Shou; Valdez, Miguel; Chen, Chi-Farn

2016-06-01

Forest is a very important ecosystem and natural resource for living things. Based on forest inventories, government is able to make decisions to converse, improve and manage forests in a sustainable way. Field work for forestry investigation is difficult and time consuming, because it needs intensive physical labor and the costs are high, especially surveying in remote mountainous regions. A reliable forest inventory can give us a more accurate and timely information to develop new and efficient approaches of forest management. The remote sensing technology has been recently used for forest investigation at a large scale. To produce an informative forest inventory, forest attributes, including tree species are unavoidably required to be considered. In this study the aim is to classify forest tree species in Erdenebulgan County, Huwsgul province in Mongolia, using Maximum Entropy method. The study area is covered by a dense forest which is almost 70% of total territorial extension of Erdenebulgan County and is located in a high mountain region in northern Mongolia. For this study, Landsat satellite imagery and a Digital Elevation Model (DEM) were acquired to perform tree species mapping. The forest tree species inventory map was collected from the Forest Division of the Mongolian Ministry of Nature and Environment as training data and also used as ground truth to perform the accuracy assessment of the tree species classification. Landsat images and DEM were processed for maximum entropy modeling, and this study applied the model with two experiments. The first one is to use Landsat surface reflectance for tree species classification; and the second experiment incorporates terrain variables in addition to the Landsat surface reflectance to perform the tree species classification. All experimental results were compared with the tree species inventory to assess the classification accuracy. Results show that the second one which uses Landsat surface reflectance coupled with terrain variables produced better result, with the higher overall accuracy and kappa coefficient than first experiment. The results indicate that the Maximum Entropy method is an applicable, and to classify tree species using satellite imagery data coupled with terrain information can improve the classification of tree species in the study area.

Description of a land classification system and its application to the management of Tennessee's state forests

Treesearch

Glendon W. Smalley; S. David Todd; K. Ward Tarkington

2006-01-01

The Tennessee Division of Forestry has adopted a land classification system developed by the senior author as the basic theme of information for the management of its 15 state forests (162,371 acres) with at least 1 in each of 8 physiographic provinces. This paper summarizes the application of the system to six forests on the Cumberland Plateau. Landtypes are the most...

Ecological classification and management characteristics of montane forest land in southwestern Washington.

Treesearch

D.G. Brockway; C. Topik

1984-01-01

Vegetation, soil, and site data werecollectedthroughout the forested portion of the Pacific silver fir and mountain hemlock zones of the Gifford Pinchot National Forest as part of the Forest Service program to develop anecoIogicallybasedplant association classification system for the Pacific Northwest Region. The major objective of sampling was to include a wide...

Multi-Cohort Stand Structural Classification: Ground- and LiDAR-based Approaches for Boreal Mixedwood and Black Spruce Forest Types of Northeastern Ontario

NASA Astrophysics Data System (ADS)

Kuttner, Benjamin George

Natural fire return intervals are relatively long in eastern Canadian boreal forests and often allow for the development of stands with multiple, successive cohorts of trees. Multi-cohort forest management (MCM) provides a strategy to maintain such multi-cohort stands that focuses on three broad phases of increasingly complex, post-fire stand development, termed "cohorts", and recommends different silvicultural approaches be applied to emulate different cohort types. Previous research on structural cohort typing has relied upon primarily subjective classification methods; in this thesis, I develop more comprehensive and objective methods for three common boreal mixedwood and black spruce forest types in northeastern Ontario. Additionally, I examine relationships between cohort types and stand age, productivity, and disturbance history and the utility of airborne LiDAR to retrieve ground-based classifications and to extend structural cohort typing from plot- to stand-levels. In both mixedwood and black spruce forest types, stand age and age-related deadwood features varied systematically with cohort classes in support of an age-based interpretation of increasing cohort complexity. However, correlations of stand age with cohort classes were surprisingly weak. Differences in site productivity had a significant effect on the accrual of increasingly complex multi-cohort stand structure in both forest types, especially in black spruce stands. The effects of past harvesting in predictive models of class membership were only significant when considered in isolation of age. As an age-emulation strategy, the three cohort model appeared to be poorly suited to black spruce forests where the accrual of structural complexity appeared to be more a function of site productivity than age. Airborne LiDAR data appear to be particularly useful in recovering plot-based cohort types and extending them to the stand-level. The main gradients of structural variability detected using LiDAR were similar between boreal mixedwood and black spruce forest types; the best LiDAR-based models of cohort type relied upon combinations of tree size, size heterogeneity, and tree density related variables. The methods described here to measure, classify, and predict cohort-related structural complexity assist in translating the conceptual three cohort model to a more precise, measurement-based management system. In addition, the approaches presented here to measure and classify stand structural complexity promise to significantly enhance the detail of structural information in operational forest inventories in support of a wide array of forest management and conservation applications.

Forestry 101.

ERIC Educational Resources Information Center

Markham, Mary T.

2000-01-01

Introduces a unit on forest management in which students manage the school forest. Involves students in tree identification, determining the size or volume and height of trees, and evaluation of the forest for management decisions. Integrates mathematics, writing, and social studies with plant classification, plant reproduction, and the use of…

Integrating Vegetation Classification, Mapping, and Strategic Inventory for Forest Management

Treesearch

C. K. Brewer; R. Bush; D. Berglund; J. A. Barber; S. R. Brown

2006-01-01

Many of the analyses needed to address multiple resource issues are focused on vegetation pattern and process relationships and most rely on the data models produced from vegetation classification, mapping, and/or inventory. The Northern Region Vegetation Mapping Project (R1-VMP) data models are based on these three integrally related, yet separate processes. This...

Indigenous systems of forest classification: understanding land use patterns and the role of NTFPs in shifting cultivators' subsistence economies.

PubMed

Delang, Claudio O

2006-04-01

This article discusses the system of classification of forest types used by the Pwo Karen in Thung Yai Naresuan Wildlife Sanctuary in western Thailand and the role of nontimber forest products (NTFPs), focusing on wild food plants, in Karen livelihoods. The article argues that the Pwo Karen have two methods of forest classification, closely related to their swidden farming practices. The first is used for forest land that has been, or can be, swiddened, and classifies forest types according to growth conditions. The second system is used for land that is not suitable for cultivation and looks at soil properties and slope. The article estimates the relative importance of each forest type in what concerns the collection of wild food plants. A total of 134 wild food plant species were recorded in December 2004. They account for some 80-90% of the amount of edible plants consumed by the Pwo Karen, and have a base value of Baht 11,505 per year, comparable to the cash incomes of many households. The article argues that the Pwo Karen reliance on NTFPs has influenced their land-use and forest management practices. However, by restricting the length of the fallow period, the Thai government has caused ecological changes that are challenging the ability of the Karen to remain subsistence oriented. By ignoring shifting cultivators' dependence on such products, the involvement of governments in forest management, especially through restrictions imposed on swidden farming practices, is likely to have a considerable impact on the livelihood strategies of these communities.

Forest classification at high latitudes as an aid to regeneration.

Treesearch

Mayo ed. Murray

1985-01-01

Early in 1979, the School of Agriculture and Land Resources Management of the University of Alaska-Fairbanks surveyed forest managers in a number of northern countries to identify topics of circumpolar interest in forest management. Responses most frequently centered on problems of forest regeneration. As a result, we initiated what was to be a series of international...

Assessing urban forest canopy cover using airborne or satellite imagery

Treesearch

Jeffrey T. Walton; David J. Nowak; Eric J. Greenfield

2008-01-01

With the availability of many sources of imagery and various digital classification techniques, assessing urban forest canopy cover is readily accessible to most urban forest managers. Understanding the capability and limitations of various types of imagery and classification methods is essential to interpreting canopy cover values. An overview of several remote...

A preliminary test of an ecological classification system for the Oconee National Forest using forest inventory and analysis data

Treesearch

W. Henry McNab; Ronald B. Stephens; Richard D. Rightmyer; Erika M. Mavity; Samuel G. Lambert

2012-01-01

An ecological classification system (ECS) has been developed for use in evaluating management, conservation and restoration options for forest and wildlife resources on the Oconee National Forest. Our study was the initial evaluation of the ECS to determine if the units at each level differed in potential productivity. We used loblolly pine (Pinus taeda...

Mapping Deforestation area in North Korea Using Phenology-based Multi-Index and Random Forest

NASA Astrophysics Data System (ADS)

Jin, Y.; Sung, S.; Lee, D. K.; Jeong, S.

2016-12-01

Forest ecosystem provides ecological benefits to both humans and wildlife. Growing global demand for food and fiber is accelerating the pressure on the forest ecosystem in whole world from agriculture and logging. In recently, North Korea lost almost 40 % of its forests to crop fields for food production and cut-down of forest for fuel woods between 1990 and 2015. It led to the increased damage caused by natural disasters and is known to be one of the most forest degraded areas in the world. The characteristic of forest landscape in North Korea is complex and heterogeneous, the major landscape types in the forest are hillside farm, unstocked forest, natural forest and plateau vegetation. Remote sensing can be used for the forest degradation mapping of a dynamic landscape at a broad scale of detail and spatial distribution. Confusion mostly occurred between hillside farmland and unstocked forest, but also between unstocked forest and forest. Most previous forest degradation that used focused on the classification of broad types such as deforests area and sand from the perspective of land cover classification. The objective of this study is using random forest for mapping degraded forest in North Korea by phenological based vegetation index derived from MODIS products, which has various environmental factors such as vegetation, soil and water at a regional scale for improving accuracy. The model created by random forest resulted in an overall accuracy was 91.44%. Class user's accuracy of hillside farmland and unstocked forest were 97.2% and 84%%, which indicate the degraded forest. Unstocked forest had relative low user accuracy due to misclassified hillside farmland and forest samples. Producer's accuracy of hillside farmland and unstocked forest were 85.2% and 93.3%, repectly. In this case hillside farmland had lower produce accuracy mainly due to confusion with field, unstocked forest and forest. Such a classification of degraded forest could supply essential information to decide the priority of forest management and restoration in degraded forest area.

Bunchgrass plant communities of the Blue and Ochoco Mountains: a guide for managers.

Treesearch

Charles Grier Johnson; David K. Swanson

2005-01-01

A classification of bunchgrass vegetation is presented for the Malheur, Ochoco, Umatilla, and part of the Wallowa-Whitman National Forests. It includes grassland vegetation as well as shrubland and forest land where the herbaceous layer is dominated by bunchgrasses. It is based on potential vegetation, with the plant association as the basic unit. Diagnostic keys and...

An accuracy assessment of forest disturbance mapping in the western Great Lakes

Treesearch

P.L. Zimmerman; I.W. Housman; C.H. Perry; R.A. Chastain; J.B. Webb; M.V. Finco

2013-01-01

The increasing availability of satellite imagery has spurred the production of thematic land cover maps based on satellite data. These maps are more valuable to the scientific community and land managers when the accuracy of their classifications has been assessed. Here, we assessed the accuracy of a map of forest disturbance in the watersheds of Lake Superior and Lake...

Predicting temperate forest stand types using only structural profiles from discrete return airborne lidar

NASA Astrophysics Data System (ADS)

Fedrigo, Melissa; Newnham, Glenn J.; Coops, Nicholas C.; Culvenor, Darius S.; Bolton, Douglas K.; Nitschke, Craig R.

2018-02-01

Light detection and ranging (lidar) data have been increasingly used for forest classification due to its ability to penetrate the forest canopy and provide detail about the structure of the lower strata. In this study we demonstrate forest classification approaches using airborne lidar data as inputs to random forest and linear unmixing classification algorithms. Our results demonstrated that both random forest and linear unmixing models identified a distribution of rainforest and eucalypt stands that was comparable to existing ecological vegetation class (EVC) maps based primarily on manual interpretation of high resolution aerial imagery. Rainforest stands were also identified in the region that have not previously been identified in the EVC maps. The transition between stand types was better characterised by the random forest modelling approach. In contrast, the linear unmixing model placed greater emphasis on field plots selected as endmembers which may not have captured the variability in stand structure within a single stand type. The random forest model had the highest overall accuracy (84%) and Cohen's kappa coefficient (0.62). However, the classification accuracy was only marginally better than linear unmixing. The random forest model was applied to a region in the Central Highlands of south-eastern Australia to produce maps of stand type probability, including areas of transition (the 'ecotone') between rainforest and eucalypt forest. The resulting map provided a detailed delineation of forest classes, which specifically recognised the coalescing of stand types at the landscape scale. This represents a key step towards mapping the structural and spatial complexity of these ecosystems, which is important for both their management and conservation.

Strata-based forest fuel classification for wild fire hazard assessment using terrestrial LiDAR

NASA Astrophysics Data System (ADS)

Chen, Yang; Zhu, Xuan; Yebra, Marta; Harris, Sarah; Tapper, Nigel

2016-10-01

Fuel structural characteristics affect fire behavior including fire intensity, spread rate, flame structure, and duration, therefore, quantifying forest fuel structure has significance in understanding fire behavior as well as providing information for fire management activities (e.g., planned burns, suppression, fuel hazard assessment, and fuel treatment). This paper presents a method of forest fuel strata classification with an integration between terrestrial light detection and ranging (LiDAR) data and geographic information system for automatically assessing forest fuel structural characteristics (e.g., fuel horizontal continuity and vertical arrangement). The accuracy of fuel description derived from terrestrial LiDAR scanning (TLS) data was assessed by field measured surface fuel depth and fuel percentage covers at distinct vertical layers. The comparison of TLS-derived depth and percentage cover at surface fuel layer with the field measurements produced root mean square error values of 1.1 cm and 5.4%, respectively. TLS-derived percentage cover explained 92% of the variation in percentage cover at all fuel layers of the entire dataset. The outcome indicated TLS-derived fuel characteristics are strongly consistent with field measured values. TLS can be used to efficiently and consistently classify forest vertical layers to provide more precise information for forest fuel hazard assessment and surface fuel load estimation in order to assist forest fuels management and fire-related operational activities. It can also be beneficial for mapping forest habitat, wildlife conservation, and ecosystem management.

Mapping forested wetlands in the Great Zhan River Basin through integrating optical, radar, and topographical data classification techniques.

PubMed

Na, X D; Zang, S Y; Wu, C S; Li, W L

2015-11-01

Knowledge of the spatial extent of forested wetlands is essential to many studies including wetland functioning assessment, greenhouse gas flux estimation, and wildlife suitable habitat identification. For discriminating forested wetlands from their adjacent land cover types, researchers have resorted to image analysis techniques applied to numerous remotely sensed data. While with some success, there is still no consensus on the optimal approaches for mapping forested wetlands. To address this problem, we examined two machine learning approaches, random forest (RF) and K-nearest neighbor (KNN) algorithms, and applied these two approaches to the framework of pixel-based and object-based classifications. The RF and KNN algorithms were constructed using predictors derived from Landsat 8 imagery, Radarsat-2 advanced synthetic aperture radar (SAR), and topographical indices. The results show that the objected-based classifications performed better than per-pixel classifications using the same algorithm (RF) in terms of overall accuracy and the difference of their kappa coefficients are statistically significant (p<0.01). There were noticeably omissions for forested and herbaceous wetlands based on the per-pixel classifications using the RF algorithm. As for the object-based image analysis, there were also statistically significant differences (p<0.01) of Kappa coefficient between results performed based on RF and KNN algorithms. The object-based classification using RF provided a more visually adequate distribution of interested land cover types, while the object classifications based on the KNN algorithm showed noticeably commissions for forested wetlands and omissions for agriculture land. This research proves that the object-based classification with RF using optical, radar, and topographical data improved the mapping accuracy of land covers and provided a feasible approach to discriminate the forested wetlands from the other land cover types in forestry area.

Application of China's National Forest Continuous Inventory database.

PubMed

Xie, Xiaokui; Wang, Qingli; Dai, Limin; Su, Dongkai; Wang, Xinchuang; Qi, Guang; Ye, Yujing

2011-12-01

The maintenance of a timely, reliable and accurate spatial database on current forest ecosystem conditions and changes is essential to characterize and assess forest resources and support sustainable forest management. Information for such a database can be obtained only through a continuous forest inventory. The National Forest Continuous Inventory (NFCI) is the first level of China's three-tiered inventory system. The NFCI is administered by the State Forestry Administration; data are acquired by five inventory institutions around the country. Several important components of the database include land type, forest classification and ageclass/ age-group. The NFCI database in China is constructed based on 5-year inventory periods, resulting in some of the data not being timely when reports are issued. To address this problem, a forest growth simulation model has been developed to update the database for years between the periodic inventories. In order to aid in forest plan design and management, a three-dimensional virtual reality system of forest landscapes for selected units in the database (compartment or sub-compartment) has also been developed based on Virtual Reality Modeling Language. In addition, a transparent internet publishing system for a spatial database based on open source WebGIS (UMN Map Server) has been designed and utilized to enhance public understanding and encourage free participation of interested parties in the development, implementation, and planning of sustainable forest management.

A new climatic classification of afforestation in Three-North regions of China with multi-source remote sensing data

NASA Astrophysics Data System (ADS)

Zheng, Xiao; Zhu, Jiaojun

2017-01-01

Afforestation and reforestation activities achieve high attention at the policy agenda as measures for carbon sequestration in order to mitigate climate change. The Three-North Shelter Forest Program, the largest ecological afforestation program worldwide, was launched in 1978 and will last until 2050 in the Three-North regions (accounting for 42.4 % of China's territory). Shelter forests of the Three-North Shelter Forest Program have exhibited severe decline after planting in 1978 due to lack of detailed climatic classification. Besides, a comprehensive assessment of climate adaptation for the current shelter forests was lacking. In this study, the aridity index determined by precipitation and reference evapotranspiration was employed to classify climatic zones for the afforestation program. The precipitation and reference evapotranspiration with 1-km resolution were estimated based on data from the tropical rainfall measuring mission and moderate resolution imaging spectroradiometer, respectively. Then, the detailed climatic classification for the afforestation program was obtained based on the relationship between the different vegetation types and the aridity index. The shelter forests in 2008 were derived from Landsat TM in the Three-North regions. In addition, climatic zones and shelter forests were corrected by comparing with natural vegetation map and field surveys. By overlaying the shelter forests on the climatic zones, we found that 16.30 % coniferous forests, 8.21 % broadleaved forests, 2.03 % mixed conifer-broadleaved forests, and 10.86 % shrubs were not in strict accordance with the climate conditions. These results open new perspectives for potential use of remote sensing techniques for afforestation management.

Classification of riparian forest species and health condition using multi-temporal and hyperspatial imagery from unmanned aerial system.

PubMed

Michez, Adrien; Piégay, Hervé; Lisein, Jonathan; Claessens, Hugues; Lejeune, Philippe

2016-03-01

Riparian forests are critically endangered many anthropogenic pressures and natural hazards. The importance of riparian zones has been acknowledged by European Directives, involving multi-scale monitoring. The use of this very-high-resolution and hyperspatial imagery in a multi-temporal approach is an emerging topic. The trend is reinforced by the recent and rapid growth of the use of the unmanned aerial system (UAS), which has prompted the development of innovative methodology. Our study proposes a methodological framework to explore how a set of multi-temporal images acquired during a vegetative period can differentiate some of the deciduous riparian forest species and their health conditions. More specifically, the developed approach intends to identify, through a process of variable selection, which variables derived from UAS imagery and which scale of image analysis are the most relevant to our objectives.The methodological framework is applied to two study sites to describe the riparian forest through two fundamental characteristics: the species composition and the health condition. These characteristics were selected not only because of their use as proxies for the riparian zone ecological integrity but also because of their use for river management.The comparison of various scales of image analysis identified the smallest object-based image analysis (OBIA) objects (ca. 1 m(2)) as the most relevant scale. Variables derived from spectral information (bands ratios) were identified as the most appropriate, followed by variables related to the vertical structure of the forest. Classification results show good overall accuracies for the species composition of the riparian forest (five classes, 79.5 and 84.1% for site 1 and site 2). The classification scenario regarding the health condition of the black alders of the site 1 performed the best (90.6%).The quality of the classification models developed with a UAS-based, cost-effective, and semi-automatic approach competes successfully with those developed using more expensive imagery, such as multi-spectral and hyperspectral airborne imagery. The high overall accuracy results obtained by the classification of the diseased alders open the door to applications dedicated to monitoring of the health conditions of riparian forest. Our methodological framework will allow UAS users to manage large imagery metric datasets derived from those dense time series.

Forest management in Northeast China: history, problems, and challenges.

PubMed

Yu, Dapao; Zhou, Li; Zhou, Wangming; Ding, Hong; Wang, Qingwei; Wang, Yue; Wu, Xiaoqing; Dai, Limin

2011-12-01

Studies of the history and current status of forest resources in Northeast China have become important in discussions of sustainable forest management in the region. Prior to 1998, excessive logging and neglected cultivation led to a series of problems that left exploitable forest reserves in the region almost exhausted. A substantial decrease in the area of natural forests was accompanied by severe disruption of stand structure and serious degradation of overall forest quality and function. In 1998, China shifted the primary focus of forest management in the country from wood production to ecological sustainability, adopting ecological restoration and protection as key foci of management. In the process, China launched the Natural Forest Conversion Program and implemented a new system of Classification-based Forest Management. Since then, timber harvesting levels in Northeast China have decreased, and forest area and stocking levels have slowly increased. At present, the large area of low quality secondary forest lands, along with high levels of timber production, present researchers and government agencies in China with major challenges in deciding on management models and strategies that will best protect, restore and manage so large an area of secondary forest lands. This paper synthesizes information from a number of sources on forest area, stand characteristics and stocking levels, and forest policy changes in Northeastern China. Following a brief historical overview of forest harvesting and ecological research in Northeast China, the paper discusses the current state of forest resources and related problems in forest management in the region, concluding with key challenges in need of attention in order to meet the demands for multi-purpose forest sustainability and management in the future.

Neighbourhood-Scale Urban Forest Ecosystem Classification

Treesearch

James W.N. Steenberg; Andrew A. Millward; Peter N. Duinker; David J. Nowak; Pamela J. Robinson

2015-01-01

Urban forests are now recognized as essential components of sustainable cities, but there remains uncertainty concerning how to stratify and classify urban landscapes into units of ecological significance at spatial scales appropriate for management. Ecosystem classification is an approach that entails quantifying the social and ecological processes that shape...

Use of topographic and climatological models in a geographical data base to improve Landsat MSS classification for Olympic National Park

NASA Technical Reports Server (NTRS)

Cibula, William G.; Nyquist, Maurice O.

1987-01-01

An unsupervised computer classification of vegetation/landcover of Olympic National Park and surrounding environs was initially carried out using four bands of Landsat MSS data. The primary objective of the project was to derive a level of landcover classifications useful for park management applications while maintaining an acceptably high level of classification accuracy. Initially, nine generalized vegetation/landcover classes were derived. Overall classification accuracy was 91.7 percent. In an attempt to refine the level of classification, a geographic information system (GIS) approach was employed. Topographic data and watershed boundaries (inferred precipitation/temperature) data were registered with the Landsat MSS data. The resultant boolean operations yielded 21 vegetation/landcover classes while maintaining the same level of classification accuracy. The final classification provided much better identification and location of the major forest types within the park at the same high level of accuracy, and these met the project objective. This classification could now become inputs into a GIS system to help provide answers to park management coupled with other ancillary data programs such as fire management.

Forested land cover classification on the Cumberland Plateau, Jackson County, Alabama: a comparison of Landsat ETM+ and SPOT5 images

Treesearch

Yong Wang; Shanta Parajuli; Callie Schweitzer; Glendon Smalley; Dawn Lemke; Wubishet Tadesse; Xiongwen Chen

2010-01-01

Forest cover classifications focus on the overall growth form (physiognomy) of the community, dominant vegetation, and species composition of the existing forest. Accurately classifying the forest cover type is important for forest inventory and silviculture. We compared classification accuracy based on Landsat Enhanced Thematic Mapper Plus (Landsat ETM+) and Satellite...

Forested plant associations of the Colville National Forest.

Treesearch

Clinton K. Williams; Brian F. Kelley; Bradley G. Smith; Terry R. Lillybridge

1995-01-01

A classification of forest vegetation is presented for the Colville National Forest in northeastern Washington State. It is based on potential vegetation with the plant association as the basic unit. The classification is based on a sample of approximately 229 intensive plots and 282 reconnaissance plots distributed across the forest from 1980 to 1983. The hierarchical...

Assessing three fuel classification systems and their maps using Forest Inventory and Analysis (FIA) surface fuel measurements

Treesearch

Robert E. Keane; Jason M. Herynk; Chris Toney; Shawn P. Urbanski; Duncan C. Lutes; Roger D. Ottmar

2015-01-01

Fuel classifications are integral tools in fire management and planning because they are used as inputs to fire behavior and effects simulation models. Fuel Loading Models (FLMs) and Fuel Characteristic Classification System (FCCSs) fuelbeds are the most popular classifications used throughout wildland fire science and management, but they have yet to be thoroughly...

Forest disturbances, deforestation and timber harvest patterns in the Conterminous United States

NASA Astrophysics Data System (ADS)

Boschetti, L.; Huo, L. Z.

2016-12-01

Current estimates of carbon-equivalent emissions report the contribution of deforestation as 12% of total anthropogenic carbon emissions (van der Werf et al., 2009), but accurate monitoring of forest carbon balance should discriminate between land use change related to forest natural disturbances, forest management and deforestation. The total change in forest cover (Gross Forest Cover Loss, GFCL) needs to be characterized based on the cause (natural/human) and on the outcome of the change (regeneration to forest/transition to non-forest)(Kurtz et al, 2010). We developed a multitemporal, object-oriented methodology to classify GFCL as either (a) deforestation, (b) fire and insect disturbances (c) forest management practices. The Landsat-derived University of Maryland Global Forest Change product (Hansen, 2013) is used to identify all the areas forest cover loss: those areas are subsequently converted to objects, and used to extract temporal profiles of spectral reflectances and spectral indices from the Landsat WELD dataset. Finally, the temporal profiles and descriptive parameters of shapes, textures, and spatial relationships of the objects are used in a rule-based classifier to identify the type of disturbance. To pathfind a global disturbance type classification, the methods are demonstrated by wall-to-wall classification of the forest cover loss in the conterminous United States for the 2002-2011 period. The results show that deforestation accounts for a small percentage (approximately 2%) of the GFCL in the CONUS, and are in agreement with the known patterns of logging activity, fire and insect damage. The time series of timber harvest clearcut is also in agreement with the national timber extraction statistics, showing reduced harvesting following the 2008 economic crisis. The results also highlight the different management practices on private and public lands: 36% of the US forests are publicly owned (federal, state and local institutions) but account only for 12% of the clearcuts, whereas private lands (64% of the total) account for 88% of the clearcut area. Conversely, stand replacing fire and insect disturbances affect primarily public lands (85% versus 15% on private lands).

The Efficiency of Random Forest Method for Shoreline Extraction from LANDSAT-8 and GOKTURK-2 Imageries

NASA Astrophysics Data System (ADS)

Bayram, B.; Erdem, F.; Akpinar, B.; Ince, A. K.; Bozkurt, S.; Catal Reis, H.; Seker, D. Z.

2017-11-01

Coastal monitoring plays a vital role in environmental planning and hazard management related issues. Since shorelines are fundamental data for environment management, disaster management, coastal erosion studies, modelling of sediment transport and coastal morphodynamics, various techniques have been developed to extract shorelines. Random Forest is one of these techniques which is used in this study for shoreline extraction.. This algorithm is a machine learning method based on decision trees. Decision trees analyse classes of training data creates rules for classification. In this study, Terkos region has been chosen for the proposed method within the scope of "TUBITAK Project (Project No: 115Y718) titled "Integration of Unmanned Aerial Vehicles for Sustainable Coastal Zone Monitoring Model - Three-Dimensional Automatic Coastline Extraction and Analysis: Istanbul-Terkos Example". Random Forest algorithm has been implemented to extract the shoreline of the Black Sea where near the lake from LANDSAT-8 and GOKTURK-2 satellite imageries taken in 2015. The MATLAB environment was used for classification. To obtain land and water-body classes, the Random Forest method has been applied to NIR bands of LANDSAT-8 (5th band) and GOKTURK-2 (4th band) imageries. Each image has been digitized manually and shorelines obtained for accuracy assessment. According to accuracy assessment results, Random Forest method is efficient for both medium and high resolution images for shoreline extraction studies.

Mapping Mangrove Density from Rapideye Data in Central America

NASA Astrophysics Data System (ADS)

Son, Nguyen-Thanh; Chen, Chi-Farn; Chen, Cheng-Ru

2017-06-01

Mangrove forests provide a wide range of socioeconomic and ecological services for coastal communities. Extensive aquaculture development of mangrove waters in many developing countries has constantly ignored services of mangrove ecosystems, leading to unintended environmental consequences. Monitoring the current status and distribution of mangrove forests is deemed important for evaluating forest management strategies. This study aims to delineate the density distribution of mangrove forests in the Gulf of Fonseca, Central America with Rapideye data using the support vector machines (SVM). The data collected in 2012 for density classification of mangrove forests were processed based on four different band combination schemes: scheme-1 (bands 1-3, 5 excluding the red-edge band 4), scheme-2 (bands 1-5), scheme-3 (bands 1-3, 5 incorporating with the normalized difference vegetation index, NDVI), and scheme-4 (bands 1-3, 5 incorporating with the normalized difference red-edge index, NDRI). We also hypothesized if the obvious contribution of Rapideye red-edge band could improve the classification results. Three main steps of data processing were employed: (1), data pre-processing, (2) image classification, and (3) accuracy assessment to evaluate the contribution of red-edge band in terms of the accuracy of classification results across these four schemes. The classification maps compared with the ground reference data indicated the slightly higher accuracy level observed for schemes 2 and 4. The overall accuracies and Kappa coefficients were 97% and 0.95 for scheme-2 and 96.9% and 0.95 for scheme-4, respectively.

A GIS-based multicriteria evaluation for aiding risk management Pinus pinaster Ait. forests: a case study in Corsican Island, western Mediterranean Region.

PubMed

Pasqualini, Vanina; Oberti, Pascal; Vigetta, Stéphanie; Riffard, Olivier; Panaïotis, Christophe; Cannac, Magali; Ferrat, Lila

2011-07-01

Forest management can benefit from decision support tools, including GIS-based multicriteria decision-aiding approach. In the Mediterranean region, Pinus pinaster forests play a very important role in biodiversity conservation and offer many socioeconomic benefits. However, the conservation of this species is affected by the increase in forest fires and the expansion of Matsucoccus feytaudi. This paper proposes a methodology based on commonly available data for assessing the values and risks of P. pinaster forests and to generating maps to aid in decisions pertaining to fire and phytosanitary risk management. The criteria for assessing the values (land cover type, legislative tools for biodiversity conservation, environmental tourist sites and access routes, and timber yield) and the risks (fire and phytosanitation) of P. pinaster forests were obtained directly or by considering specific indicators, and they were subsequently aggregated by means of GIS-based multicriteria analysis. This approach was tested on the island of Corsica (France), and maps to aid in decisions pertaining to fire risk and phytosanitary risk (M. feytaudi) were obtained for P. pinaster forest management. Study results are used by the technical offices of the local administration-Corsican Agricultural and Rural Development Agency (ODARC)-for planning the conservation of P. pinaster forests with regard to fire prevention and safety and phytosanitary risks. The decision maker took part in the evaluation criteria study (weight, normalization, and classification of the values). Most suitable locations are given to target the public intervention. The methodology presented in this paper could be applied to other species and in other Mediterranean regions.

A GIS-Based Multicriteria Evaluation for Aiding Risk Management Pinus pinaster Ait. Forests: A Case Study in Corsican Island, Western Mediterranean Region

NASA Astrophysics Data System (ADS)

Pasqualini, Vanina; Oberti, Pascal; Vigetta, Stéphanie; Riffard, Olivier; Panaïotis, Christophe; Cannac, Magali; Ferrat, Lila

2011-07-01

Forest management can benefit from decision support tools, including GIS-based multicriteria decision-aiding approach. In the Mediterranean region, Pinus pinaster forests play a very important role in biodiversity conservation and offer many socioeconomic benefits. However, the conservation of this species is affected by the increase in forest fires and the expansion of Matsucoccus feytaudi. This paper proposes a methodology based on commonly available data for assessing the values and risks of P. pinaster forests and to generating maps to aid in decisions pertaining to fire and phytosanitary risk management. The criteria for assessing the values (land cover type, legislative tools for biodiversity conservation, environmental tourist sites and access routes, and timber yield) and the risks (fire and phytosanitation) of P. pinaster forests were obtained directly or by considering specific indicators, and they were subsequently aggregated by means of GIS-based multicriteria analysis. This approach was tested on the island of Corsica (France), and maps to aid in decisions pertaining to fire risk and phytosanitary risk ( M. feytaudi) were obtained for P. pinaster forest management. Study results are used by the technical offices of the local administration— Corsican Agricultural and Rural Development Agency (ODARC)—for planning the conservation of P. pinaster forests with regard to fire prevention and safety and phytosanitary risks. The decision maker took part in the evaluation criteria study (weight, normalization, and classification of the values). Most suitable locations are given to target the public intervention. The methodology presented in this paper could be applied to other species and in other Mediterranean regions.

Nationwide classification of forest types of India using remote sensing and GIS.

PubMed

Reddy, C Sudhakar; Jha, C S; Diwakar, P G; Dadhwal, V K

2015-12-01

India, a mega-diverse country, possesses a wide range of climate and vegetation types along with a varied topography. The present study has classified forest types of India based on multi-season IRS Resourcesat-2 Advanced Wide Field Sensor (AWiFS) data. The study has characterized 29 land use/land cover classes including 14 forest types and seven scrub types. Hybrid classification approach has been used for the classification of forest types. The classification of vegetation has been carried out based on the ecological rule bases followed by Champion and Seth's (1968) scheme of forest types in India. The present classification scheme has been compared with the available global and national level land cover products. The natural vegetation cover was estimated to be 29.36% of total geographical area of India. The predominant forest types of India are tropical dry deciduous and tropical moist deciduous. Of the total forest cover, tropical dry deciduous forests occupy an area of 2,17,713 km(2) (34.80%) followed by 2,07,649 km(2) (33.19%) under tropical moist deciduous forests, 48,295 km(2) (7.72%) under tropical semi-evergreen forests and 47,192 km(2) (7.54%) under tropical wet evergreen forests. The study has brought out a comprehensive vegetation cover and forest type maps based on inputs critical in defining the various categories of vegetation and forest types. This spatially explicit database will be highly useful for the studies related to changes in various forest types, carbon stocks, climate-vegetation modeling and biogeochemical cycles.

Forest site classification for cultural plant harvest by tribal weavers can inform management

Treesearch

S. Hummel; F.K. Lake

2015-01-01

Do qualitative classifications of ecological conditions for harvesting culturally important forest plants correspond to quantitative differences among sites? To address this question, we blended scientific methods (SEK) and traditional ecological knowledge (TEK) to identify conditions on sites considered good, marginal, or poor for harvesting the leaves of a plant (...

Proceedings, 15th central hardwood forest conference

Treesearch

David S. Buckley; Wayne K. Clatterbuck; [Editors

2007-01-01

Proceedings of the 15th central hardwood forest conference held February 27–March 1, 2006, in Knoxville, TN. Includes 86 papers and 30 posters pertaining to forest health and protection, ecology and forest dynamics, natural and artificial regeneration, forest products, wildlife, site classification, management and forest resources, mensuration and models, soil and...

Integrating management strategies for the mountain pine beetle with multiple-resource management of lodgepole pine forests

Treesearch

Mark D. McGregor; Dennis M. Cole

1985-01-01

Provides guidelines for integrating practices for managing mountain pine beetle populations with silvicultural practices for enhancing multiple resource values of lodgepole pine forests. Summarizes published and unpublished technical information and recent research on the ecology of pest and host and presents visual and classification criteria for recognizing...

Identification of understory invasive exotic plants with remote sensing in urban forests

NASA Astrophysics Data System (ADS)

Shouse, Michael; Liang, Liang; Fei, Songlin

2013-04-01

Invasive exotic plants (IEP) pose a significant threat to many ecosystems. To effectively manage IEP, it is important to efficiently detect their presences and determine their distribution patterns. Remote sensing has been a useful tool to map IEP but its application is limited in urban forests, which are often the sources and sinks for IEP. In this study, we examined the feasibility and tradeoffs of species level IEP mapping using multiple remote sensing techniques in a highly complex urban forest setting. Bush honeysuckle (Lonicera maackii), a pervasive IEP in eastern North America, was used as our modeling species. Both medium spatial resolution (MSR) and high spatial resolution (HSR) imagery were employed in bush honeysuckle mapping. The importance of spatial scale was also examined using an up-scaling simulation from the HSR object based classification. Analysis using both MSR and HSR imagery provided viable results for IEP distribution mapping in urban forests. Overall mapping accuracy ranged from 89.8% to 94.9% for HSR techniques and from 74.6% to 79.7% for MSR techniques. As anticipated, classification accuracy reduces as pixel size increases. HSR based techniques produced the most desirable results, therefore is preferred for precise management of IEP in heterogeneous environment. However, the use of MSR techniques should not be ruled out given their wide availability and moderate accuracy.

Analysis of Multipsectral Time Series for supporting Forest Management Plans

NASA Astrophysics Data System (ADS)

Simoniello, T.; Carone, M. T.; Costantini, G.; Frattegiani, M.; Lanfredi, M.; Macchiato, M.

2010-05-01

Adequate forest management requires specific plans based on updated and detailed mapping. Multispectral satellite time series have been largely applied to forest monitoring and studies at different scales tanks to their capability of providing synoptic information on some basic parameters descriptive of vegetation distribution and status. As a low expensive tool for supporting forest management plans in operative context, we tested the use of Landsat-TM/ETM time series (1987-2006) in the high Agri Valley (Southern Italy) for planning field surveys as well as for the integration of existing cartography. As preliminary activity to make all scenes radiometrically consistent the no-change regression normalization was applied to the time series; then all the data concerning available forest maps, municipal boundaries, water basins, rivers, and roads were overlapped in a GIS environment. From the 2006 image we elaborated the NDVI map and analyzed the distribution for each land cover class. To separate the physiological variability and identify the anomalous areas, a threshold on the distributions was applied. To label the non homogenous areas, a multitemporal analysis was performed by separating heterogeneity due to cover changes from that linked to basilar unit mapping and classification labelling aggregations. Then a map of priority areas was produced to support the field survey plan. To analyze the territorial evolution, the historical land cover maps were elaborated by adopting a hybrid classification approach based on a preliminary segmentation, the identification of training areas, and a subsequent maximum likelihood categorization. Such an analysis was fundamental for the general assessment of the territorial dynamics and in particular for the evaluation of the efficacy of past intervention activities.

Comparing Pixel and Object-Based Approaches to Map an Understorey Invasive Shrub in Tropical Mixed Forests

PubMed Central

Niphadkar, Madhura; Nagendra, Harini; Tarantino, Cristina; Adamo, Maria; Blonda, Palma

2017-01-01

The establishment of invasive alien species in varied habitats across the world is now recognized as a genuine threat to the preservation of biodiversity. Specifically, plant invasions in understory tropical forests are detrimental to the persistence of healthy ecosystems. Monitoring such invasions using Very High Resolution (VHR) satellite remote sensing has been shown to be valuable in designing management interventions for conservation of native habitats. Object-based classification methods are very helpful in identifying invasive plants in various habitats, by their inherent nature of imitating the ability of the human brain in pattern recognition. However, these methods have not been tested adequately in dense tropical mixed forests where invasion occurs in the understorey. This study compares a pixel-based and object-based classification method for mapping the understorey invasive shrub Lantana camara (Lantana) in a tropical mixed forest habitat in the Western Ghats biodiversity hotspot in India. Overall, a hierarchical approach of mapping top canopy at first, and then further processing for the understorey shrub, using measures such as texture and vegetation indices proved effective in separating out Lantana from other cover types. In the first method, we implement a simple parametric supervised classification for mapping cover types, and then process within these types for Lantana delineation. In the second method, we use an object-based segmentation algorithm to map cover types, and then perform further processing for separating Lantana. The improved ability of the object-based approach to delineate structurally distinct objects with characteristic spectral and spatial characteristics of their own, as well as with reference to their surroundings, allows for much flexibility in identifying invasive understorey shrubs among the complex vegetation of the tropical forest than that provided by the parametric classifier. Conservation practices in tropical mixed forests can benefit greatly by adopting methods which use high resolution remotely sensed data and advanced techniques to monitor the patterns and effective functioning of native ecosystems by periodically mapping disturbances such as invasion. PMID:28620400

Quantitative classification of a historic northern Wisconsin (U.S.A.) landscape: mapping forests at regional scales

Treesearch

Lisa A. Schulte; David J. Mladenoff; Erik V. Nordheim

2002-01-01

We developed a quantitative and replicable classification system to improve understanding of historical composition and structure within northern Wisconsin's forests. The classification system was based on statistical cluster analysis and two forest metrics, relative dominance (% basal area) and relative importance (mean of relative dominance and relative density...

Proceedings from the conference on the ecology and management of high-elevation forests in the central and southern Appalachian Mountains

Treesearch

James S. Rentch; Thomas M. Schuler

2010-01-01

The proceedings includes 18 peer-reviewed papers and 41 abstracts pertaining to acid deposition and nutrient cycling, ecological classification, forest dynamics, avifauna, wildlife and fisheries, forests pests, climate change, old-growth forest structure, regeneration, and restoration.

Toward an integrated classification of ecosystems: Defining opportunities for managing fish and forest health

Treesearch

Bruce E. Rieman; Danny C. Lee; Russell F. Thurow; Paul F. Hessburg; James R. Sedell

2000-01-01

Many of the aquatic and terrestrial ecosystems of the Pacific Northwest United States have been simplified and degraded in part through past land-management activities. Recent listings of fishes under the Endangered Species Act and major new initiatives for the restoration of forest health have precipitated contentious debate among managers and conservation interests...

Forest habitat types of central Idaho

Treesearch

Robert Steele; Robert D. Pfister; Russell A. Ryker; Jay A. Kittams

1981-01-01

A land-classification system based upon potential natural vegetation is presented for the forests of central Idaho. It is based on reconnaissance sampling of about 800 stands. A hierarchical taxonomic classification of forest sites was developed using the habitat type concept. A total of eight climax series, 64 habitat types, and 55 additional phases of habitat types...

Automated lidar-derived canopy height estimates for the Upper Mississippi River System

USGS Publications Warehouse

Hlavacek, Enrika

2015-01-01

Land cover/land use (LCU) classifications serve as important decision support products for researchers and land managers. The LCU classifications produced by the U.S. Geological Survey’s Upper Midwest Environmental Sciences Center (UMESC) include canopy height estimates that are assigned through manual aerial photography interpretation techniques. In an effort to improve upon these techniques, this project investigated the use of high-density lidar data for the Upper Mississippi River System to determine canopy height. An ArcGIS tool was developed to automatically derive height modifier information based on the extent of land cover features for forest classes. The measurement of canopy height included a calculation of the average height from lidar point cloud data as well as the inclusion of a local maximum filter to identify individual tree canopies. Results were compared to original manually interpreted height modifiers and to field survey data from U.S. Forest Service Forest Inventory and Analysis plots. This project demonstrated the effectiveness of utilizing lidar data to more efficiently assign height modifier attributes to LCU classifications produced by the UMESC.

Discriminant forest classification method and system

DOEpatents

Chen, Barry Y.; Hanley, William G.; Lemmond, Tracy D.; Hiller, Lawrence J.; Knapp, David A.; Mugge, Marshall J.

2012-11-06

A hybrid machine learning methodology and system for classification that combines classical random forest (RF) methodology with discriminant analysis (DA) techniques to provide enhanced classification capability. A DA technique which uses feature measurements of an object to predict its class membership, such as linear discriminant analysis (LDA) or Andersen-Bahadur linear discriminant technique (AB), is used to split the data at each node in each of its classification trees to train and grow the trees and the forest. When training is finished, a set of n DA-based decision trees of a discriminant forest is produced for use in predicting the classification of new samples of unknown class.

Integration of visual quality considerations in development of Israeli vegetation management policy.

PubMed

Misgav, A; Amir, S

2001-06-01

This article deals with the visual quality of Mediterranean vegetation groups in northern Israel, the public's preference of these groups as a visual resource, and the policy options for their management. The study is based on a sample of 44 Mediterranean vegetation groups and three population groups of local residents, who were interviewed using a questionnaire and photographs of the vegetation groups. The results of the research showed that plant classification methods based on flora composition, habitat, and external appearance were found to be suitable for visual plant classification and for the evaluation of visual preference of vegetation groups by the interviewed public. The vegetation groups of planted pine forests and olive groves, characterizing a cultured vegetation landscape, were preferred over typical Mediterranean landscapes such as scrub and grassed scrub. The researchers noted a marked difference between the two products of vegetation management policy, one that proposes the conservation and restoration of the variety of native Mediterranean vegetation landscape, and a second that advanced the development of the cultured landscape of planted olive groves and pines forests, which were highly preferred by the public. The authors suggested the development of an integrated vegetation management policy that would combine both needs and thus reduce the gap between the policy proposed by planners and the local population's visual preference.

The North American Forest Database: going beyond national-level forest resource assessment statistics.

PubMed

Smith, W Brad; Cuenca Lara, Rubí Angélica; Delgado Caballero, Carina Edith; Godínez Valdivia, Carlos Isaías; Kapron, Joseph S; Leyva Reyes, Juan Carlos; Meneses Tovar, Carmen Lourdes; Miles, Patrick D; Oswalt, Sonja N; Ramírez Salgado, Mayra; Song, Xilong Alex; Stinson, Graham; Villela Gaytán, Sergio Armando

2018-05-21

Forests cannot be managed sustainably without reliable data to inform decisions. National Forest Inventories (NFI) tend to report national statistics, with sub-national stratification based on domestic ecological classification systems. It is becoming increasingly important to be able to report statistics on ecosystems that span international borders, as global change and globalization expand stakeholders' spheres of concern. The state of a transnational ecosystem can only be properly assessed by examining the entire ecosystem. In global forest resource assessments, it may be useful to break national statistics down by ecosystem, especially for large countries. The Inventory and Monitoring Working Group (IMWG) of the North American Forest Commission (NAFC) has begun developing a harmonized North American Forest Database (NAFD) for managing forest inventory data, enabling consistent, continental-scale forest assessment supporting ecosystem-level reporting and relational queries. The first iteration of the database contains data describing 1.9 billion ha, including 677.5 million ha of forest. Data harmonization is made challenging by the existence of definitions and methodologies tailored to suit national circumstances, emerging from each country's professional forestry development. This paper reports the methods used to synchronize three national forest inventories, starting with a small suite of variables and attributes.

Coupling a distributed hydrological model with detailed forest structural information for large-scale global change impact assessment

NASA Astrophysics Data System (ADS)

Eisner, Stephanie; Huang, Shaochun; Majasalmi, Titta; Bright, Ryan; Astrup, Rasmus; Beldring, Stein

2017-04-01

Forests are recognized for their decisive effect on landscape water balance with structural forest characteristics as stand density or species composition determining energy partitioning and dominant flow paths. However, spatial and temporal variability in forest structure is often poorly represented in hydrological modeling frameworks, in particular in regional to large scale hydrological modeling and impact analysis. As a common practice, prescribed land cover classes (including different generic forest types) are linked to parameter values derived from literature, or parameters are determined by calibration. While national forest inventory (NFI) data provide comprehensive, detailed information on hydrologically relevant forest characteristics, their potential to inform hydrological simulation over larger spatial domains is rarely exploited. In this study we present a modeling framework that couples the distributed hydrological model HBV with forest structural information derived from the Norwegian NFI and multi-source remote sensing data. The modeling framework, set up for the entire of continental Norway at 1 km spatial resolution, is explicitly designed to study the combined and isolated impacts of climate change, forest management and land use change on hydrological fluxes. We use a forest classification system based on forest structure rather than biomes which allows to implicitly account for impacts of forest management on forest structural attributes. In the hydrological model, different forest classes are represented by three parameters: leaf area index (LAI), mean tree height and surface albedo. Seasonal cycles of LAI and surface albedo are dynamically simulated to make the framework applicable under climate change conditions. Based on a hindcast for the pilot regions Nord-Trøndelag and Sør-Trøndelag, we show how forest management has affected regional hydrological fluxes during the second half of the 20th century as contrasted to climate variability.

Forest habitat types of eastern Idaho-western Wyoming

Treesearch

Robert Steele; Stephen V. Cooper; David M. Ondov; David W. Roberts; Robert D. Pfister

1983-01-01

A land-classification system based upon potential natural vegetation is presented for the forests of central Idaho. It is based on reconnaissance sampling of about 980 stands. A hierarchical taxonomic classification of forest sites was developed using the habitat type concept. A total of six climax series, 58 habitat types, and 24 additional phases of habitat types are...

Coniferous forest habitat types of central and southern Utah

Treesearch

Andrew P. Youngblood; Ronald L. Mauk

1985-01-01

A land-classification system based upon potential natural vegetation is presented for the coniferous forests of central and southern Utah. It is based on reconnaissance sampling of about 720 stands. A hierarchical taxonomic classification of forest sites was developed using the habitat type concept. Seven climax series, 37 habitat types, and six additional phases of...

Forest habitat types of Montana

Treesearch

Robert D. Pfister; Bernard L. Kovalchik; Stephen F. Arno; Richard C. Presby

1977-01-01

A land-classification system based upon potential natural vegetation is presented for the forests of Montana. It is based on an intensive 4-year study and reconnaissance sampling of about 1,500 stands. A hierarchical classification of forest sites was developed using the habitat type concept. A total of 9 climax series, 64 habitat types, and 37 additional phases of...

Evaluating the performance and mapping of three fuel classification systems using Forest Inventory and Analysis surface fuel measurements

Treesearch

Robert E. Keane; Jason M. Herynk; Chris Toney; Shawn P. Urbanski; Duncan C. Lutes; Roger D. Ottmar

2013-01-01

Fuel Loading Models (FLMs) and Fuel Characteristic Classification System (FCCSs) fuelbeds are used throughout wildland fire science and management to simplify fuel inputs into fire behavior and effects models, but they have yet to be thoroughly evaluated with field data. In this study, we used a large dataset of Forest Inventory and Analysis (FIA) surface fuel...

[Eco-value level classification and ecosystem management strategy of broad-leaved Korean pine forest in Changbai Mountain].

PubMed

Zheng, Jingming; Jiang, Fengqi; Zeng, Dehui

2003-06-01

To realize the sustainable management of forest ecosystems, we should explicitly clarify the types and differences of the ecosystem services provided by different ecosystems under different conditions, with rethinking about the value of forest ecosystems; then solid management strategies and measurements will be enacted and applied to achieve the objects. The broad-leaved Korean pine forest (BLKPF) in Changbai Mountain is a unique and important forest type in China, owing to its many important ecosystem services such as preventing soil erosion, regulating climates, nutrient cycling, providing wood and non-timber forest products, etc. This paper is a preliminary study on the management strategy of BLKPF on the basis of analyzing the characters of the ecosystems and the relative importance of services they provided in this region. Based on the latest research of ecosystem services of BLKPF in Changbai Mountain, an idea of eco-value level (EVL) was introduced, and accordingly, management strategies were summarized by adopting the advanced theories in ecosystem management science and by analyzing field survey data. EVL means the relative amount of the value of ecosystem services provided by certain ecosystem, which can indicate the difference between services in given objects. The EVL classification of BLKPF implies the relative amount of the eco-value of different ecosystems including virgin forest, secondary forest, forest with human disturbance, and man-made forest in the clear-cutting sites. Analytical Hierarchical Processing method was used to formulate the equation for EVL index. Eight factors, namely, slope, soil depth, stability of soil maternal material, coverage of above-ground canopy, species diversity, regeneration rate of the stand, life span of dominant tree species, and intensity of human disturbance were chosen to build the formula. These factors belonged to three aspects affecting ecosystem services including the physical environment, community, and disturbance regime, and their selection and scaling were based on the previous studies on the BLKPF. The equation of EVL index (EI) was expressed as: EI = 0.542A1 + 0.171A2 + 0.072A3 + 0.067B1 + 0.043B2 + 0.014B3 + 0.010B4 + 0.081C1. According to the range of EI, ecosystems were classified into three types: low EVL type with EI from 1.000 to 1.874, medium EVL type with EI 1.874-2.749, and high EVL type with EI 2.749-3.623. Typical plots were surveyed and scaled with EI, and the predominant characters of each EVL type were summarized. Most forests of high EVL type were those in sites at high risk of soil erosion and hard to recover after disrupted. Forests of medium EVL type were those with worse community structure and composition, and were disturbed by human activities in relative steep sites. Forest of low EVL type were those in plane site with serious disruption or some young man-made stands. Based on the analyses of the characters of these three types, different management strategies were put forward. For high EVL type forest, strictly protection is most important to maintain the forest in natural succession and its eco-services. For medium EVL type forest, the key points of management are restoring their health and vigor by regulating their composition and structure in a seminatural way. For low EVL type forest, some area could be used to extensive exploration for economic benefits, and the rests should be reconstructed towards the original stand in composition and structure, based on the 'shadow ecosystem' in a close-to-nature way to promote the capacity of providing more eco-services.

Vegetation classification, mapping, and monitoring at Voyageurs National Park, Minnesota: An application of the U.S. National Vegetation Classification

USGS Publications Warehouse

Faber-Langendoen, D.; Aaseng, N.; Hop, K.; Lew-Smith, M.; Drake, J.

2007-01-01

Question: How can the U.S. National Vegetation Classification (USNVC) serve as an effective tool for classifying and mapping vegetation, and inform assessments and monitoring? Location: Voyageurs National Park, northern Minnesota, U.S.A and environs. The park contains 54 243 ha of terrestrial habitat in the sub-boreal region of North America. Methods: We classified and mapped the natural vegetation using the USNVC, with 'alliance' and 'association' as base units. We compiled 259 classification plots and 1251 accuracy assessment test plots. Both plot and type ordinations were used to analyse vegetation and environmental patterns. Color infrared aerial photography (1:15840 scale) was used for mapping. Polygons were manually drawn, then transferred into digital form. Classification and mapping products are stored in publicly available databases. Past fire and logging events were used to assess distribution of forest types. Results and Discussion: Ordination and cluster analyses confirmed 49 associations and 42 alliances, with three associations ranked as globally vulnerable to extirpation. Ordination provided a useful summary of vegetation and ecological gradients. Overall map accuracy was 82.4%. Pinus banksiana - Picea mariana forests were less frequent in areas unburned since the 1930s. Conclusion: The USNVC provides a consistent ecological tool for summarizing and mapping vegetation. The products provide a baseline for assessing forests and wetlands, including fire management. The standardized classification and map units provide local to continental perspectives on park resources through linkages to state, provincial, and national classifications in the U.S. and Canada, and to NatureServe's Ecological Systems classification. ?? IAVS; Opulus Press.

Temporal carbon dynamics of forests in Washington, US: implications for ecological theory and carbon management

Treesearch

Crystal L. Raymond; Donald McKenzie

2014-01-01

We quantified carbon (C) dynamics of forests in Washington, US using theoretical models of C dynamics as a function of forest age. We fit empirical models to chronosequences of forest inventory data at two scales: a coarse-scale ecosystem classification (ecosections) and forest types (potential vegetation) within ecosections. We hypothesized that analysis at the finer...

Remote sensing applications in agriculture and forestry. Applications of aerial photography and ERTS data to agricultural, forest and water resources management

NASA Technical Reports Server (NTRS)

1973-01-01

Remote sensing techniques are being used in Minnesota to study: (1) forest disease detection and control; (2) water quality indicators; (3) forest vegetation classification and management; (4) detection of saline soils in the Red River Valley; (5) corn defoliation; and (6) alfalfa crop productivity. Results of progress, and plans for future work in these areas, are discussed.

Spatial and thematic assessment of object-based forest stand delineation using an OFA-matrix

NASA Astrophysics Data System (ADS)

Hernando, A.; Tiede, D.; Albrecht, F.; Lang, S.

2012-10-01

The delineation and classification of forest stands is a crucial aspect of forest management. Object-based image analysis (OBIA) can be used to produce detailed maps of forest stands from either orthophotos or very high resolution satellite imagery. However, measures are then required for evaluating and quantifying both the spatial and thematic accuracy of the OBIA output. In this paper we present an approach for delineating forest stands and a new Object Fate Analysis (OFA) matrix for accuracy assessment. A two-level object-based orthophoto analysis was first carried out to delineate stands on the Dehesa Boyal public land in central Spain (Avila Province). Two structural features were first created for use in class modelling, enabling good differentiation between stands: a relational tree cover cluster feature, and an arithmetic ratio shadow/tree feature. We then extended the OFA comparison approach with an OFA-matrix to enable concurrent validation of thematic and spatial accuracies. Its diagonal shows the proportion of spatial and thematic coincidence between a reference data and the corresponding classification. New parameters for Spatial Thematic Loyalty (STL), Spatial Thematic Loyalty Overall (STLOVERALL) and Maximal Interfering Object (MIO) are introduced to summarise the OFA-matrix accuracy assessment. A stands map generated by OBIA (classification data) was compared with a map of the same area produced from photo interpretation and field data (reference data). In our example the OFA-matrix results indicate good spatial and thematic accuracies (>65%) for all stand classes except for the shrub stands (31.8%), and a good STLOVERALL (69.8%). The OFA-matrix has therefore been shown to be a valid tool for OBIA accuracy assessment.

Object-based forest classification to facilitate landscape-scale conservation in the Mississippi Alluvial Valley

USGS Publications Warehouse

Mitchell, Michael; Wilson, R. Randy; Twedt, Daniel J.; Mini, Anne E.; James, J. Dale

2016-01-01

The Mississippi Alluvial Valley is a floodplain along the southern extent of the Mississippi River extending from southern Missouri to the Gulf of Mexico. This area once encompassed nearly 10 million ha of floodplain forests, most of which has been converted to agriculture over the past two centuries. Conservation programs in this region revolve around protection of existing forest and reforestation of converted lands. Therefore, an accurate and up to date classification of forest cover is essential for conservation planning, including efforts that prioritize areas for conservation activities. We used object-based image analysis with Random Forest classification to quickly and accurately classify forest cover. We used Landsat band, band ratio, and band index statistics to identify and define similar objects as our training sets instead of selecting individual training points. This provided a single rule-set that was used to classify each of the 11 Landsat 5 Thematic Mapper scenes that encompassed the Mississippi Alluvial Valley. We classified 3,307,910±85,344 ha (32% of this region) as forest. Our overall classification accuracy was 96.9% with Kappa statistic of 0.96. Because this method of forest classification is rapid and accurate, assessment of forest cover can be regularly updated and progress toward forest habitat goals identified in conservation plans can be periodically evaluated.

Neighbourhood-scale urban forest ecosystem classification.

PubMed

Steenberg, James W N; Millward, Andrew A; Duinker, Peter N; Nowak, David J; Robinson, Pamela J

2015-11-01

Urban forests are now recognized as essential components of sustainable cities, but there remains uncertainty concerning how to stratify and classify urban landscapes into units of ecological significance at spatial scales appropriate for management. Ecosystem classification is an approach that entails quantifying the social and ecological processes that shape ecosystem conditions into logical and relatively homogeneous management units, making the potential for ecosystem-based decision support available to urban planners. The purpose of this study is to develop and propose a framework for urban forest ecosystem classification (UFEC). The multifactor framework integrates 12 ecosystem components that characterize the biophysical landscape, built environment, and human population. This framework is then applied at the neighbourhood scale in Toronto, Canada, using hierarchical cluster analysis. The analysis used 27 spatially-explicit variables to quantify the ecosystem components in Toronto. Twelve ecosystem classes were identified in this UFEC application. Across the ecosystem classes, tree canopy cover was positively related to economic wealth, especially income. However, education levels and homeownership were occasionally inconsistent with the expected positive relationship with canopy cover. Open green space and stocking had variable relationships with economic wealth and were more closely related to population density, building intensity, and land use. The UFEC can provide ecosystem-based information for greening initiatives, tree planting, and the maintenance of the existing canopy. Moreover, its use has the potential to inform the prioritization of limited municipal resources according to ecological conditions and to concerns of social equity in the access to nature and distribution of ecosystem service supply. Copyright © 2015 Elsevier Ltd. All rights reserved.

Basic forest cover mapping using digitized remote sensor data and automated data processing techniques

NASA Technical Reports Server (NTRS)

Coggeshall, M. E.; Hoffer, R. M.

1973-01-01

Remote sensing equipment and automatic data processing techniques were employed as aids in the institution of improved forest resource management methods. On the basis of automatically calculated statistics derived from manually selected training samples, the feature selection processor of LARSYS selected, upon consideration of various groups of the four available spectral regions, a series of channel combinations whose automatic classification performances (for six cover types, including both deciduous and coniferous forest) were tested, analyzed, and further compared with automatic classification results obtained from digitized color infrared photography.

Classification of very high resolution satellite remote sensing data in a pilot phase of the forest cover classification of the Democratic Republic of Congo, Forêts d'Afrique Central Evaluées par Télédetection (FACET) product

NASA Astrophysics Data System (ADS)

Singa Monga Lowengo, C.

2012-12-01

The Observatoire Satellital des Forêts d'Afrique Centrale (OSFAC) based in Kinshasa, serves as the focal point of the GOFC-GOLD network for Central Africa. OSFAC's long term objective is building regional capacity to use remotely sensed data to map forest cover and forest cover change across Central Africa. OSFAC archives and disseminates satellite data, offers training in geospatial data applications in coordination with the University of Kinshasa, and provides technical support to CARPE partners. Forêts d'Afrique Centrale Évaluées par Télédétection (FACET) is an OSFAC initiative that implements the UMD/SDSU methodology at the national level and quantitatively evaluates the spatiotemporal dynamics of forest cover in Central Africa. The multi-temporal series of FACET data is a useful contribution to many projects, such as biodiversity monitoring, climate modeling, conservation, natural resource management, land use planning, agriculture and REDD+. I am working as Remote Sensing and GIS Officer in various projects of OSFAC. My activities include forest cover and lands dynamics monitoring in Congo Basin. I am familiar with the use of digital mapping software, GIS and RS (Arc GIS, ENVI and PCI Geomatica etc.), classification and spatial Analysis of satellite images, 3D modeling, etc. I started as an intern at OSFAC, Assistant Trainer (Professional Training) and Consultant than permanent employee since October 2009. To assist in the OSFAC activities regarding the monitoring of forest cover and the CARPE program in the context of natural resources management, I participated in the development of the FACET Atlas (Republic of Congo). I received data from Matt Hansen (map.img), WRI and Brazzaville (shapefiles). With all these data I draw maps of the ROC Atlas and statistics of forest cover and forest loss. We organize field work on land to collect data to validate the FACET product. Therefore, to assess forest cover in the region of Kwamouth and Kahuzi-Maiko Biega landscape with very high resolution data and field work for validating FACET product (Remotelly Sensing Product).;

A comparison of rule-based and machine learning approaches for classifying patient portal messages.

PubMed

Cronin, Robert M; Fabbri, Daniel; Denny, Joshua C; Rosenbloom, S Trent; Jackson, Gretchen Purcell

2017-09-01

Secure messaging through patient portals is an increasingly popular way that consumers interact with healthcare providers. The increasing burden of secure messaging can affect clinic staffing and workflows. Manual management of portal messages is costly and time consuming. Automated classification of portal messages could potentially expedite message triage and delivery of care. We developed automated patient portal message classifiers with rule-based and machine learning techniques using bag of words and natural language processing (NLP) approaches. To evaluate classifier performance, we used a gold standard of 3253 portal messages manually categorized using a taxonomy of communication types (i.e., main categories of informational, medical, logistical, social, and other communications, and subcategories including prescriptions, appointments, problems, tests, follow-up, contact information, and acknowledgement). We evaluated our classifiers' accuracies in identifying individual communication types within portal messages with area under the receiver-operator curve (AUC). Portal messages often contain more than one type of communication. To predict all communication types within single messages, we used the Jaccard Index. We extracted the variables of importance for the random forest classifiers. The best performing approaches to classification for the major communication types were: logistic regression for medical communications (AUC: 0.899); basic (rule-based) for informational communications (AUC: 0.842); and random forests for social communications and logistical communications (AUCs: 0.875 and 0.925, respectively). The best performing classification approach of classifiers for individual communication subtypes was random forests for Logistical-Contact Information (AUC: 0.963). The Jaccard Indices by approach were: basic classifier, Jaccard Index: 0.674; Naïve Bayes, Jaccard Index: 0.799; random forests, Jaccard Index: 0.859; and logistic regression, Jaccard Index: 0.861. For medical communications, the most predictive variables were NLP concepts (e.g., Temporal_Concept, which maps to 'morning', 'evening' and Idea_or_Concept which maps to 'appointment' and 'refill'). For logistical communications, the most predictive variables contained similar numbers of NLP variables and words (e.g., Telephone mapping to 'phone', 'insurance'). For social and informational communications, the most predictive variables were words (e.g., social: 'thanks', 'much', informational: 'question', 'mean'). This study applies automated classification methods to the content of patient portal messages and evaluates the application of NLP techniques on consumer communications in patient portal messages. We demonstrated that random forest and logistic regression approaches accurately classified the content of portal messages, although the best approach to classification varied by communication type. Words were the most predictive variables for classification of most communication types, although NLP variables were most predictive for medical communication types. As adoption of patient portals increases, automated techniques could assist in understanding and managing growing volumes of messages. Further work is needed to improve classification performance to potentially support message triage and answering. Copyright © 2017 Elsevier B.V. All rights reserved.

Estimating forest characteristics using NAIP imagery and ArcObjects

Treesearch

John S Hogland; Nathaniel M. Anderson; Woodam Chung; Lucas Wells

2014-01-01

Detailed, accurate, efficient, and inexpensive methods of estimating basal area, trees, and aboveground biomass per acre across broad extents are needed to effectively manage forests. In this study we present such a methodology using readily available National Agriculture Imagery Program imagery, Forest Inventory Analysis samples, a two stage classification and...

[Object-oriented segmentation and classification of forest gap based on QuickBird remote sensing image.

PubMed

Mao, Xue Gang; Du, Zi Han; Liu, Jia Qian; Chen, Shu Xin; Hou, Ji Yu

2018-01-01

Traditional field investigation and artificial interpretation could not satisfy the need of forest gaps extraction at regional scale. High spatial resolution remote sensing image provides the possibility for regional forest gaps extraction. In this study, we used object-oriented classification method to segment and classify forest gaps based on QuickBird high resolution optical remote sensing image in Jiangle National Forestry Farm of Fujian Province. In the process of object-oriented classification, 10 scales (10-100, with a step length of 10) were adopted to segment QuickBird remote sensing image; and the intersection area of reference object (RA or ) and intersection area of segmented object (RA os ) were adopted to evaluate the segmentation result at each scale. For segmentation result at each scale, 16 spectral characteristics and support vector machine classifier (SVM) were further used to classify forest gaps, non-forest gaps and others. The results showed that the optimal segmentation scale was 40 when RA or was equal to RA os . The accuracy difference between the maximum and minimum at different segmentation scales was 22%. At optimal scale, the overall classification accuracy was 88% (Kappa=0.82) based on SVM classifier. Combining high resolution remote sensing image data with object-oriented classification method could replace the traditional field investigation and artificial interpretation method to identify and classify forest gaps at regional scale.

Multiple-factor classification of a human-modified forest landscape in the Hsuehshan Mountain Range, Taiwan.

PubMed

Berg, Kevan J; Icyeh, Lahuy; Lin, Yih-Ren; Janz, Arnold; Newmaster, Steven G

2016-12-01

Human actions drive landscape heterogeneity, yet most ecosystem classifications omit the role of human influence. This study explores land use history to inform a classification of forestland of the Tayal Mrqwang indigenous people of Taiwan. Our objectives were to determine the extent to which human action drives landscape heterogeneity. We used interviews, field sampling, and multivariate analysis to relate vegetation patterns to environmental gradients and human modification across 76 sites. We identified eleven forest classes. In total, around 70 % of plots were at lower elevations and had a history of shifting cultivation, terrace farming, and settlement that resulted in alder, laurel, oak, pine, and bamboo stands. Higher elevation mixed conifer forests were least disturbed. Arboriculture and selective harvesting were drivers of other conspicuous forest patterns. The findings show that past land uses play a key role in shaping forests, which is important to consider when setting targets to guide forest management.

Using indigenous knowledge to link hyper-temporal land cover mapping with land use in the Venezuelan Amazon: "The Forest Pulse".

PubMed

Olivero, Jesús; Ferri, Francisco; Acevedo, Pelayo; Lobo, Jorge M; Fa, John E; Farfán, Miguel Á; Romero, David; Real, Raimundo

2016-12-01

Remote sensing and traditional ecological knowledge (TEK) can be combined to advance conservation of remote tropical regions, e.g. Amazonia, where intensive in situ surveys are often not possible. Integrating TEK into monitoring and management of these areas allows for community participation, as well as for offering novel insights into sustainable resource use. In this study, we developed a 250 m resolution land-cover map of the Western Guyana Shield (Venezuela) based on remote sensing, and used TEK to validate its relevance for indigenous livelihoods and land uses. We first employed a hyper-temporal remotely sensed vegetation index to derive a land classification system. During a 1 300 km, eight day fluvial expedition in roadless areas in the Amazonas State (Venezuela), we visited six indigenous communities who provided geo-referenced data on hunting, fishing and farming activities. We overlaid these TEK data onto the land classification map, to link land classes with indigenous use. We characterized land classes using patterns of greenness temporal change and topo-hydrological information, and proposed 12 land-cover types, grouped into five main landscapes: 1) water bodies; 2) open lands/forest edges; 3) evergreen forests; 4) submontane semideciduous forests, and 5) cloud forests. Each land cover class was identified with a pulsating profile describing temporal changes in greenness, hence we labelled our map as "The Forest Pulse". These greenness profiles showed a slightly increasing trend, for the period 2000 to 2009, in the land classes representing grassland and scrubland, and a slightly decreasing trend in the classes representing forests. This finding is consistent with a gain in carbon in grassland as a consequence of climate warming, and also with some loss of vegetation in the forests. Thus, our classification shows potential to assess future effects of climate change on landscape. Several classes were significantly connected with agriculture, fishing, overall hunting, and more specifically the hunting of primates, Mazama americana, Dasyprocta fuliginosa, and Tayassu pecari. Our results showed that TEK-based approaches can serve as a basis for validating the livelihood relevance of landscapes in high-value conservation areas, which can form the basis for furthering the management of natural resources in these regions.

The US Forest Service Watershed Condition Classification: Status and Path Forward

NASA Astrophysics Data System (ADS)

Levinson, D. H.; Carlson, C. P.; Eberle, M. B.

2017-12-01

The US Forest Service Watershed Condition Classification (WCC) was developed as a tool to characterize the condition or health of watersheds on National Forests and Grasslands and assist the Agency in prioritizing actions to restore or maintain the condition of specified watersheds. After a number of years of exploring alternative approaches to assessing the health or condition of watersheds, the WCC and the associated Watershed Condition Framework were developed in response to concerns raised by the US Office of Management and Budget that the Forest Service was not able to demonstrate success in restoring watersheds on a national scale. The WCC was initially applied in 2011 to the roughly 15,000 HUC12 watersheds with an area of Forest Service management of 5% or greater. This initial watershed classification found that 52% (or 7,882) were Functioning Properly (Class 1), 45% (or 6,751) were Functioning at Risk (Class 2), and 3% (or 431) had Impaired Function (Class 3). The basic model used in the WCC was intended to provide a reconnaissance-level evaluation of watershed condition through the use of a systematic, flexible means of classifying and comparing watersheds based on a core set of national watershed condition indicators. The WCC consists of 12 indicators in four major process categories: (1) aquatic physical, (2) aquatic biological, (3) terrestrial physical, and (4) terrestrial biological. Each of the indicators is informed by one or more attributes. The attributes fall into three primary categories: numeric, descriptive, and map-derived, each of which is to be interpreted by an interdisciplinary team at the unit level. The descriptive and map-derived attributes are considered to be semi-quantitative or based on professional judgement of the team. The original description of the attributes anticipated that many of them would be improved as better data and information become available. With the advances in geographic information systems and remote sensing, the Forest Service is interested in working toward a more data-driven approach to the attributes and indicators in the WCC. The need for consistency, reproducibility, and landscape-scale comparability, suggests that it may be a good time to evaluate alternate approaches to assess and track watershed condition.

Mapping land cover and estimating forest structure using satellite imagery and coarse resolution lidar in the Virgin Islands

Treesearch

T.A. Kennaway; E.H. Helmer; M.A. Lefsky; T.A. Brandeis; K.R. Sherill

2008-01-01

Current information on land cover, forest type and forest structure for the Virgin Islands is critical to land managers and researchers for accurate forest inventory and ecological monitoring. In this study, we use cloud free image mosaics of panchromatic sharpened Landsat ETM+ images and decision tree classification software to map land cover and forest type for the...

Mapping land cover and estimating forest structure using satellite imagery and coarse resolution lidar in the Virgin Islands

Treesearch

Todd Kennaway; Eileen Helmer; Michael Lefsky; Thomas Brandeis; Kirk Sherrill

2009-01-01

Current information on land cover, forest type and forest structure for the Virgin Islands is critical to land managers and researachers for accurate forest inverntory and ecological monitoring. In this study, we use cloud free image mosaics of panchromatic sharpened Landsat ETM+ images and decision tree classification software to map land cover and forest type for the...

Land cover mapping of the upper Kuskokwim Resource Managment Area using LANDSAT and a digital data base approach

USGS Publications Warehouse

Markon, Carl J.

1988-01-01

Digital land cover and terrain data for the Upper Kuskokwim Resource Hanagement Area (UKRMA) were produced by the U.S. Geological Survey, Earth Resources Observation Systems Field Office, Anchorage, Alaska for the Bureau of Land Management. These and other environmental data, were incorporated into a digital data base to assist in the management and planning of the UKRMA. The digital data base includes land cover classifications, elevation, slope, and aspect data centering on the UKRMA boundaries. The data are stored on computer compatible tapes at a 50-m pixel size. Additional digital data in the data base include: (a) summer and winter Landsat multispectral scanner (MSS) data registered to a 50-m Universal Transverse Mercator grid; (b) elevation, slope, aspect, and solar illumination data; (c) soils and surficial geology; and (e) study area boundary. The classification of Landsat MSS data resulted in seven major classes and 24 subclasses. Major classes include: forest, shrubland, dwarf scrub, herbaceous, barren, water, and other. The final data base will be used by resource personnel for management and planning within the UKRMA.

Forest land management by satellite: LANDSAT-derived information as input to a forest inventory system. [North Carolina

NASA Technical Reports Server (NTRS)

Williams, D. L.; Haver, G. F. (Principal Investigator)

1976-01-01

The author has identified the following significant results. Analysis of LANDSAT temporal data, specifically the digitally merged winter and summer scenes, provided the best overall classification results. Comparison of temporal classification results with available ground truth reveal a 94% agreement in the delineation of hardwood categories, a 96% agreement for the combined pine category, and a greater than 50% agreement for each individual pine subcategory. For nearly 1000 acres, compared clearcut acreage estimated with LANDSAT digital data differed from company inventory records by only 3%. Through analysis of summer data, pine stands were successfully classified into subcategories based upon the extent of crown closure. Maximum spectral separability of hardwood and pine stands was obtained from the analysis of winter data.

Object based image analysis for the classification of the growth stages of Avocado crop, in Michoacán State, Mexico

NASA Astrophysics Data System (ADS)

Gao, Yan; Marpu, Prashanth; Morales Manila, Luis M.

2014-11-01

This paper assesses the suitability of 8-band Worldview-2 (WV2) satellite data and object-based random forest algorithm for the classification of avocado growth stages in Mexico. We tested both pixel-based with minimum distance (MD) and maximum likelihood (MLC) and object-based with Random Forest (RF) algorithm for this task. Training samples and verification data were selected by visual interpreting the WV2 images for seven thematic classes: fully grown, middle stage, and early stage of avocado crops, bare land, two types of natural forests, and water body. To examine the contribution of the four new spectral bands of WV2 sensor, all the tested classifications were carried out with and without the four new spectral bands. Classification accuracy assessment results show that object-based classification with RF algorithm obtained higher overall higher accuracy (93.06%) than pixel-based MD (69.37%) and MLC (64.03%) method. For both pixel-based and object-based methods, the classifications with the four new spectral bands (overall accuracy obtained higher accuracy than those without: overall accuracy of object-based RF classification with vs without: 93.06% vs 83.59%, pixel-based MD: 69.37% vs 67.2%, pixel-based MLC: 64.03% vs 36.05%, suggesting that the four new spectral bands in WV2 sensor contributed to the increase of the classification accuracy.

Statistical inference for remote sensing-based estimates of net deforestation

Treesearch

Ronald E. McRoberts; Brian F. Walters

2012-01-01

Statistical inference requires expression of an estimate in probabilistic terms, usually in the form of a confidence interval. An approach to constructing confidence intervals for remote sensing-based estimates of net deforestation is illustrated. The approach is based on post-classification methods using two independent forest/non-forest classifications because...

A framework for mapping tree species combining hyperspectral and LiDAR data: Role of selected classifiers and sensor across three spatial scales

NASA Astrophysics Data System (ADS)

Ghosh, Aniruddha; Fassnacht, Fabian Ewald; Joshi, P. K.; Koch, Barbara

2014-02-01

Knowledge of tree species distribution is important worldwide for sustainable forest management and resource evaluation. The accuracy and information content of species maps produced using remote sensing images vary with scale, sensor (optical, microwave, LiDAR), classification algorithm, verification design and natural conditions like tree age, forest structure and density. Imaging spectroscopy reduces the inaccuracies making use of the detailed spectral response. However, the scale effect still has a strong influence and cannot be neglected. This study aims to bridge the knowledge gap in understanding the scale effect in imaging spectroscopy when moving from 4 to 30 m pixel size for tree species mapping, keeping in mind that most current and future hyperspectral satellite based sensors work with spatial resolution around 30 m or more. Two airborne (HyMAP) and one spaceborne (Hyperion) imaging spectroscopy dataset with pixel sizes of 4, 8 and 30 m, respectively were available to examine the effect of scale over a central European forest. The forest under examination is a typical managed forest with relatively homogenous stands featuring mostly two canopy layers. Normalized digital surface model (nDSM) derived from LiDAR data was used additionally to examine the effect of height information in tree species mapping. Six different sets of predictor variables (reflectance value of all bands, selected components of a Minimum Noise Fraction (MNF), Vegetation Indices (VI) and each of these sets combined with LiDAR derived height) were explored at each scale. Supervised kernel based (Support Vector Machines) and ensemble based (Random Forest) machine learning algorithms were applied on the dataset to investigate the effect of the classifier. Iterative bootstrap-validation with 100 iterations was performed for classification model building and testing for all the trials. For scale, analysis of overall classification accuracy and kappa values indicated that 8 m spatial resolution (reaching kappa values of over 0.83) slightly outperformed the results obtained from 4 m for the study area and five tree species under examination. The 30 m resolution Hyperion image produced sound results (kappa values of over 0.70), which in some areas of the test site were comparable with the higher spatial resolution imagery when qualitatively assessing the map outputs. Considering input predictor sets, MNF bands performed best at 4 and 8 m resolution. Optical bands were found to be best for 30 m spatial resolution. Classification with MNF as input predictors produced better visual appearance of tree species patches when compared with reference maps. Based on the analysis, it was concluded that there is no significant effect of height information on tree species classification accuracies for the present framework and study area. Furthermore, in the examined cases there was no single best choice among the two classifiers across scales and predictors. It can be concluded that tree species mapping from imaging spectroscopy for forest sites comparable to the one under investigation is possible with reliable accuracies not only from airborne but also from spaceborne imaging spectroscopy datasets.

Object-oriented classification of forest structure from light detection and ranging data for stand mapping

Treesearch

Alicia A. Sullivan; Robert J. McGaughey; Hans-Erik Andersen; Peter Schiess

2009-01-01

Stand delineation is an important step in the process of establishing a forest inventory and provides the spatial framework for many forest management decisions. Many methods for extracting forest structure characteristics for stand delineation and other purposes have been researched in the past, primarily focusing on high-resolution imagery and satellite data. High-...

Remote sensing based detection of forested wetlands: An evaluation of LiDAR, aerial imagery, and their data fusion

NASA Astrophysics Data System (ADS)

Suiter, Ashley Elizabeth

Multi-spectral imagery provides a robust and low-cost dataset for assessing wetland extent and quality over broad regions and is frequently used for wetland inventories. However in forested wetlands, hydrology is obscured by tree canopy making it difficult to detect with multi-spectral imagery alone. Because of this, classification of forested wetlands often includes greater errors than that of other wetlands types. Elevation and terrain derivatives have been shown to be useful for modelling wetland hydrology. But, few studies have addressed the use of LiDAR intensity data detecting hydrology in forested wetlands. Due the tendency of LiDAR signal to be attenuated by water, this research proposed the fusion of LiDAR intensity data with LiDAR elevation, terrain data, and aerial imagery, for the detection of forested wetland hydrology. We examined the utility of LiDAR intensity data and determined whether the fusion of Lidar derived data with multispectral imagery increased the accuracy of forested wetland classification compared with a classification performed with only multi-spectral image. Four classifications were performed: Classification A -- All Imagery, Classification B -- All LiDAR, Classification C -- LiDAR without Intensity, and Classification D -- Fusion of All Data. These classifications were performed using random forest and each resulted in a 3-foot resolution thematic raster of forested upland and forested wetland locations in Vermilion County, Illinois. The accuracies of these classifications were compared using Kappa Coefficient of Agreement. Importance statistics produced within the random forest classifier were evaluated in order to understand the contribution of individual datasets. Classification D, which used the fusion of LiDAR and multi-spectral imagery as input variables, had moderate to strong agreement between reference data and classification results. It was found that Classification A performed using all the LiDAR data and its derivatives (intensity, elevation, slope, aspect, curvatures, and Topographic Wetness Index) was the most accurate classification with Kappa: 78.04%, indicating moderate to strong agreement. However, Classification C, performed with LiDAR derivative without intensity data had less agreement than would be expected by chance, indicating that LiDAR contributed significantly to the accuracy of Classification B.

Differences in forest area classification based on tree tally from variable- and fixed-radius plots

Treesearch

David Azuma; Vicente J. Monleon

2011-01-01

In forest inventory, it is not enough to formulate a definition; it is also necessary to define the "measurement procedure." In the classification of forestland by dominant cover type, the measurement design (the plot) can affect the outcome of the classification. We present results of a simulation study comparing classification of the dominant cover type...

Developing New Coastal Forest Restoration Products Based on Landsat, ASTER, and MODIS Data

NASA Technical Reports Server (NTRS)

Spruce, Joseph P.; Graham, William; Smoot, James

2009-01-01

This paper discusses an ongoing effort to develop new geospatial information products for aiding coastal forest restoration and conservation efforts in coastal Louisiana and Mississippi. This project employs Landsat, Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), and Moderate Resolution Imaging Spectroradiometer (MODIS) satellite data in conjunction with airborne elevation data to compute coastal forest cover type maps and change detection products. Improved forest mapping products are needed to aid coastal forest restoration and management efforts of State and Federal agencies in the Northern Gulf of Mexico (NGOM) region. In particular, such products may aid coastal forest land acquisition and conservation easement procurements. This region's forests are often disturbed and subjected to multiple biotic and abiotic threats, including subsidence, salt water intrusion, hurricanes, sea-level rise, insect-induced defoliation and mortality, altered hydrology, wildfire, and conversion to non-forest land use. In some cases, such forest disturbance has led to forest loss or loss of regeneration capacity. In response, a case study was conducted to assess and demonstrate the potential of satellite remote sensing products for improving forest type maps and for assessing forest change over the last 25 years. Change detection products are needed for assessing risks for specific priority coastal forest types, such as live oak and baldcypress-dominated forest. Preliminary results indicate Landsat time series data are capable of generating the needed forest type and change detection products. Useful classifications were obtained using 2 strategies: 1) general forest classification based on use of 3 seasons of Landsat data from the same year; and 2) classification of specific forest types of concern using a single date of Landsat data in which a given targeted type is spectrally distinct compared to adjacent forested cover. When available, ASTER data was useful as a complement to Landsat data. Elevation data helped to define areas in which targeted forest types occur, such as live oak forests on natural levees. MODIS Normalized Difference Vegetation Index time series data aided visual assessments of coastal forest damage and recovery from hurricanes. Landsat change detection products enabled change to be identified at the stand level and at 10- year intervals with the earliest date preceding available change detection products from the National Oceanic and Atmospheric Administration and from the U.S. Geological Survey. Additional work is being done in collaboration with State and Federal agency partners in a follow-on NASA ROSES project to refine and validate these new, promising products. The products from the ROSES project will be available for aiding NGOM coastal forest restoration and conservation.

Wildland Arson as Clandestine Resource Management: A Space-Time Permutation Analysis and Classification of Informal Fire Management Regimes in Georgia, USA

NASA Astrophysics Data System (ADS)

Coughlan, Michael R.

2016-05-01

Forest managers are increasingly recognizing the value of disturbance-based land management techniques such as prescribed burning. Unauthorized, "arson" fires are common in the southeastern United States where a legacy of agrarian cultural heritage persists amidst an increasingly forest-dominated landscape. This paper reexamines unauthorized fire-setting in the state of Georgia, USA from a historical ecology perspective that aims to contribute to historically informed, disturbance-based land management. A space-time permutation analysis is employed to discriminate systematic, management-oriented unauthorized fires from more arbitrary or socially deviant fire-setting behaviors. This paper argues that statistically significant space-time clusters of unauthorized fire occurrence represent informal management regimes linked to the legacy of traditional land management practices. Recent scholarship has pointed out that traditional management has actively promoted sustainable resource use and, in some cases, enhanced biodiversity often through the use of fire. Despite broad-scale displacement of traditional management during the 20th century, informal management practices may locally circumvent more formal and regionally dominant management regimes. Space-time permutation analysis identified 29 statistically significant fire regimes for the state of Georgia. The identified regimes are classified by region and land cover type and their implications for historically informed disturbance-based resource management are discussed.

Wildland Arson as Clandestine Resource Management: A Space-Time Permutation Analysis and Classification of Informal Fire Management Regimes in Georgia, USA.

PubMed

Coughlan, Michael R

2016-05-01

Forest managers are increasingly recognizing the value of disturbance-based land management techniques such as prescribed burning. Unauthorized, "arson" fires are common in the southeastern United States where a legacy of agrarian cultural heritage persists amidst an increasingly forest-dominated landscape. This paper reexamines unauthorized fire-setting in the state of Georgia, USA from a historical ecology perspective that aims to contribute to historically informed, disturbance-based land management. A space-time permutation analysis is employed to discriminate systematic, management-oriented unauthorized fires from more arbitrary or socially deviant fire-setting behaviors. This paper argues that statistically significant space-time clusters of unauthorized fire occurrence represent informal management regimes linked to the legacy of traditional land management practices. Recent scholarship has pointed out that traditional management has actively promoted sustainable resource use and, in some cases, enhanced biodiversity often through the use of fire. Despite broad-scale displacement of traditional management during the 20th century, informal management practices may locally circumvent more formal and regionally dominant management regimes. Space-time permutation analysis identified 29 statistically significant fire regimes for the state of Georgia. The identified regimes are classified by region and land cover type and their implications for historically informed disturbance-based resource management are discussed.

Exploiting machine learning algorithms for tree species classification in a semiarid woodland using RapidEye image

NASA Astrophysics Data System (ADS)

Adelabu, Samuel; Mutanga, Onisimo; Adam, Elhadi; Cho, Moses Azong

2013-01-01

Classification of different tree species in semiarid areas can be challenging as a result of the change in leaf structure and orientation due to soil moisture constraints. Tree species mapping is, however, a key parameter for forest management in semiarid environments. In this study, we examined the suitability of 5-band RapidEye satellite data for the classification of five tree species in mopane woodland of Botswana using machine leaning algorithms with limited training samples.We performed classification using random forest (RF) and support vector machines (SVM) based on EnMap box. The overall accuracies for classifying the five tree species was 88.75 and 85% for both SVM and RF, respectively. We also demonstrated that the new red-edge band in the RapidEye sensor has the potential for classifying tree species in semiarid environments when integrated with other standard bands. Similarly, we observed that where there are limited training samples, SVM is preferred over RF. Finally, we demonstrated that the two accuracy measures of quantity and allocation disagreement are simpler and more helpful for the vast majority of remote sensing classification process than the kappa coefficient. Overall, high species classification can be achieved using strategically located RapidEye bands integrated with advanced processing algorithms.

Forest above ground biomass estimation and forest/non-forest classification for Odisha, India, using L-band Synthetic Aperture Radar (SAR) data

NASA Astrophysics Data System (ADS)

Suresh, M.; Kiran Chand, T. R.; Fararoda, R.; Jha, C. S.; Dadhwal, V. K.

2014-11-01

Tropical forests contribute to approximately 40 % of the total carbon found in terrestrial biomass. In this context, forest/non-forest classification and estimation of forest above ground biomass over tropical regions are very important and relevant in understanding the contribution of tropical forests in global biogeochemical cycles, especially in terms of carbon pools and fluxes. Information on the spatio-temporal biomass distribution acts as a key input to Reducing Emissions from Deforestation and forest Degradation Plus (REDD+) action plans. This necessitates precise and reliable methods to estimate forest biomass and to reduce uncertainties in existing biomass quantification scenarios. The use of backscatter information from a host of allweather capable Synthetic Aperture Radar (SAR) systems during the recent past has demonstrated the potential of SAR data in forest above ground biomass estimation and forest / nonforest classification. In the present study, Advanced Land Observing Satellite (ALOS) / Phased Array L-band Synthetic Aperture Radar (PALSAR) data along with field inventory data have been used in forest above ground biomass estimation and forest / non-forest classification over Odisha state, India. The ALOSPALSAR 50 m spatial resolution orthorectified and radiometrically corrected HH/HV dual polarization data (digital numbers) for the year 2010 were converted to backscattering coefficient images (Schimada et al., 2009). The tree level measurements collected during field inventory (2009-'10) on Girth at Breast Height (GBH at 1.3 m above ground) and height of all individual trees at plot (plot size 0.1 ha) level were converted to biomass density using species specific allometric equations and wood densities. The field inventory based biomass estimations were empirically integrated with ALOS-PALSAR backscatter coefficients to derive spatial forest above ground biomass estimates for the study area. Further, The Support Vector Machines (SVM) based Radial Basis Function classification technique was employed to carry out binary (forest-non forest) classification using ALOSPALSAR HH and HV backscatter coefficient images and field inventory data. The textural Haralick's Grey Level Cooccurrence Matrix (GLCM) texture measures are determined on HV backscatter image for Odisha, for the year 2010. PALSAR HH, HV backscatter coefficient images, their difference (HHHV) and HV backscatter coefficient based eight textural parameters (Mean, Variance, Dissimilarity, Contrast, Angular second moment, Homogeneity, Correlation and Contrast) are used as input parameters for Support Vector Machines (SVM) tool. Ground based inputs for forest / non-forest were taken from field inventory data and high resolution Google maps. Results suggested significant relationship between HV backscatter coefficient and field based biomass (R2 = 0.508, p = 0.55) compared to HH with biomass values ranging from 5 to 365 t/ha. The spatial variability of biomass with reference to different forest types is in good agreement. The forest / nonforest classified map suggested a total forest cover of 50214 km2 with an overall accuracy of 92.54 %. The forest / non-forest information derived from the present study showed a good spatial agreement with the standard forest cover map of Forest Survey of India (FSI) and corresponding published area of 50575 km2. Results are discussed in the paper.

Fuel characterization in the southern Appalachian Mountains: an application of landscape ecosystem classification

Treesearch

Aaron D. Stottlemeyer; Victor B. Shelburne; Thomas A. Waldrop; Sandra Rideout-Hanzak; William C. Bridges

2009-01-01

Prescribed fire has been widely used in the south-eastern United States to meet forest management objectives, but has only recently been reintroduced to the southern Appalachian Mountains. Fuel information is not available to forest managers in this region and direct measurement is often impractical owing to steep, remote topography. The objective of the present study...

Characterization and classification of vegetation canopy structure and distribution within the Great Smoky Mountains National Park using LiDAR

Treesearch

Jitendra Kumar; Jon Weiner; William W. Hargrove; Steve Norman; Forrest M. Hoffman; Doug Newcomb

2016-01-01

Vegetation canopy structure is a critically important habitat characteristic for many threatened and endangered birds and other animal species, and it is key information needed by forest and wildlife managers for monitoring and managing forest resources, conservation planning and fostering biodiversity. Advances in Light Detection and Ranging (LiDAR) technologies have...

Forest community classification of the Porcupine River drainage, interior Alaska, and its application to forest management.

Treesearch

John Yarie

1983-01-01

The forest vegetation of 3,600,000 hectares in northeast interior Alaska was classified. A total of 365 plots located in a stratified random design were run through the ordination programs SIMORD and TWINSPAN. A total of 40 forest communities were described vegetatively and, to a limited extent, environmentally. The area covered by each community was similar, ranging...

Application of airborne hyperspectral remote sensing for the retrieval of forest inventory parameters

NASA Astrophysics Data System (ADS)

Dmitriev, Yegor V.; Kozoderov, Vladimir V.; Sokolov, Anton A.

2016-04-01

Collecting and updating forest inventory data play an important part in the forest management. The data can be obtained directly by using exact enough but low efficient ground based methods as well as from the remote sensing measurements. We present applications of airborne hyperspectral remote sensing for the retrieval of such important inventory parameters as the forest species and age composition. The hyperspectral images of the test region were obtained from the airplane equipped by the produced in Russia light-weight airborne video-spectrometer of visible and near infrared spectral range and high resolution photo-camera on the same gyro-stabilized platform. The quality of the thematic processing depends on many factors such as the atmospheric conditions, characteristics of measuring instruments, corrections and preprocessing methods, etc. An important role plays the construction of the classifier together with methods of the reduction of the feature space. The performance of different spectral classification methods is analyzed for the problem of hyperspectral remote sensing of soil and vegetation. For the reduction of the feature space we used the earlier proposed stable feature selection method. The results of the classification of hyperspectral airborne images by using the Multiclass Support Vector Machine method with Gaussian kernel and the parametric Bayesian classifier based on the Gaussian mixture model and their comparative analysis are demonstrated.

Classification and evaluation for forest sites on the Mid-Cumberland Plateau

Treesearch

Glendon W. Smalley

1982-01-01

Presents a comprehensive forest site classification system for the central portion of the Cumberland Plateau in northeast Alabama, and east-central Tennessee. The system is based on physiography, geology, soils, topography, and vegetation.

Forest tree species clssification based on airborne hyper-spectral imagery

NASA Astrophysics Data System (ADS)

Dian, Yuanyong; Li, Zengyuan; Pang, Yong

2013-10-01

Forest precision classification products were the basic data for surveying of forest resource, updating forest subplot information, logging and design of forest. However, due to the diversity of stand structure, complexity of the forest growth environment, it's difficult to discriminate forest tree species using multi-spectral image. The airborne hyperspectral images can achieve the high spatial and spectral resolution imagery of forest canopy, so it will good for tree species level classification. The aim of this paper was to test the effective of combining spatial and spectral features in airborne hyper-spectral image classification. The CASI hyper spectral image data were acquired from Liangshui natural reserves area. Firstly, we use the MNF (minimum noise fraction) transform method for to reduce the hyperspectral image dimensionality and highlighting variation. And secondly, we use the grey level co-occurrence matrix (GLCM) to extract the texture features of forest tree canopy from the hyper-spectral image, and thirdly we fused the texture and the spectral features of forest canopy to classify the trees species using support vector machine (SVM) with different kernel functions. The results showed that when using the SVM classifier, MNF and texture-based features combined with linear kernel function can achieve the best overall accuracy which was 85.92%. It was also confirm that combine the spatial and spectral information can improve the accuracy of tree species classification.

A novel approach to internal crown characterization for coniferous tree species classification

NASA Astrophysics Data System (ADS)

Harikumar, A.; Bovolo, F.; Bruzzone, L.

2016-10-01

The knowledge about individual trees in forest is highly beneficial in forest management. High density small foot- print multi-return airborne Light Detection and Ranging (LiDAR) data can provide a very accurate information about the structural properties of individual trees in forests. Every tree species has a unique set of crown structural characteristics that can be used for tree species classification. In this paper, we use both the internal and external crown structural information of a conifer tree crown, derived from a high density small foot-print multi-return LiDAR data acquisition for species classification. Considering the fact that branches are the major building blocks of a conifer tree crown, we obtain the internal crown structural information using a branch level analysis. The structure of each conifer branch is represented using clusters in the LiDAR point cloud. We propose the joint use of the k-means clustering and geometric shape fitting, on the LiDAR data projected onto a novel 3-dimensional space, to identify branch clusters. After mapping the identified clusters back to the original space, six internal geometric features are estimated using a branch-level analysis. The external crown characteristics are modeled by using six least correlated features based on cone fitting and convex hull. Species classification is performed using a sparse Support Vector Machines (sparse SVM) classifier.

Classification and evaluation for forest sites on the Eastern Highland Rim and Pennyroyal.

Treesearch

Glendon W. Smalley

1983-01-01

Presents a comprehensive forest site classification system for the Eastern Highland Rim and Pennyroyal in north Alabama, east-central Tennessee, and central Kentucky. The system is based on physiography, geology, soils, topography, and vegetation.

Human preference for ecological units: patterns of dispersed campsites within landtype associations on the Chippewa National Forest

Treesearch

Lisa Whitcomb; Dennis Parker; Bob Carr; Paul Gobster; Herb Schroeder

2002-01-01

Forest Service landscape architects sought a method for determining if people showed a preference for certain landscape-scale ecosystems and if ecological classification units could be used in visual resource management. A study was conducted on the Chippewa National Forest to test whether there was a systematic relationship between dispersed campsite locations and...

New Tree-Classification System Used by the Southern Forest Inventory and Analysis Unit

Treesearch

Dennis M. May; John S. Vissage; D. Vince Few

1990-01-01

Trees at USDA Forest Service, Southern Forest Inventory and Analysis, sample locations are classified as growing stock or cull based on their ability to produce sawlogs. The old and new classification systems are compared, and the impacts of the new system on the reporting of tree volumes are illustrated with inventory data from north Alabama.

Characteristics of Forests in Western Sayani Mountains, Siberia from SAR Data

NASA Technical Reports Server (NTRS)

Ranson, K. Jon; Sun, Guoqing; Kharuk, V. I.; Kovacs, Katalin

1998-01-01

This paper investigated the possibility of using spaceborne radar data to map forest types and logging in the mountainous Western Sayani area in Siberia. L and C band HH, HV, and VV polarized images from the Shuttle Imaging Radar-C instrument were used in the study. Techniques to reduce topographic effects in the radar images were investigated. These included radiometric correction using illumination angle inferred from a digital elevation model, and reducing apparent effects of topography through band ratios. Forest classification was performed after terrain correction utilizing typical supervised techniques and principal component analyses. An ancillary data set of local elevations was also used to improve the forest classification. Map accuracy for each technique was estimated for training sites based on Russian forestry maps, satellite imagery and field measurements. The results indicate that it is necessary to correct for topography when attempting to classify forests in mountainous terrain. Radiometric correction based on a DEM (Digital Elevation Model) improved classification results but required reducing the SAR (Synthetic Aperture Radar) resolution to match the DEM. Using ratios of SAR channels that include cross-polarization improved classification and

Classification and evaluation for forest sites on the Western Highland Rim and Pennyroyal

Treesearch

Glendon W. Smalley

1980-01-01

Presents a comprehensive forest site classification system for the Western Highland Rim and Western Pennyroyal-Limestone area in northwest Alabama, west-central Tennessee, and western Kentucky. The system is based on physiography, geology, soils, topography, and vegetation.

CW-SSIM kernel based random forest for image classification

NASA Astrophysics Data System (ADS)

Fan, Guangzhe; Wang, Zhou; Wang, Jiheng

2010-07-01

Complex wavelet structural similarity (CW-SSIM) index has been proposed as a powerful image similarity metric that is robust to translation, scaling and rotation of images, but how to employ it in image classification applications has not been deeply investigated. In this paper, we incorporate CW-SSIM as a kernel function into a random forest learning algorithm. This leads to a novel image classification approach that does not require a feature extraction or dimension reduction stage at the front end. We use hand-written digit recognition as an example to demonstrate our algorithm. We compare the performance of the proposed approach with random forest learning based on other kernels, including the widely adopted Gaussian and the inner product kernels. Empirical evidences show that the proposed method is superior in its classification power. We also compared our proposed approach with the direct random forest method without kernel and the popular kernel-learning method support vector machine. Our test results based on both simulated and realworld data suggest that the proposed approach works superior to traditional methods without the feature selection procedure.

Spatiotemporal Change Detection in Forest Cover Dynamics Along Landslide Susceptible Region of Karakoram Highway, Pakistan

NASA Astrophysics Data System (ADS)

Rashid, Barira; Iqbal, Javed

2018-04-01

Forest Cover dynamics and its understanding is essential for a country's social, environmental, and political engagements. This research provides a methodical approach for the assessment of forest cover along Karakoram Highway. It has great ecological and economic significance because it's a part of China-Pakistan Economic Corridor. Landsat 4, 5 TM, Landsat 7 ETM and Landsat 8 OLI imagery for the years 1990, 2000, 2010 and 2016 respectively were subjected to supervised classification in ArcMap 10.5 to identify forest change. The study area was categorized into five major land use land cover classes i.e., Forest, vegetation, urban, open land and snow cover. Results from post classification forest cover change maps illustrated notable decrease of almost 26 % forest cover over the time period of 26 years. The accuracy assessment revealed the kappa coefficients 083, 0.78, 0.77 and 0.85, respectively. Major reason for this change is an observed replacement of native forest cover with urban areas (12.5 %) and vegetation (18.6 %) However, there is no significant change in the reserved forests along the study area that contributes only 2.97 % of the total forest cover. The extensive forest degradation and risk prone topography of the region has increased the environmental risk of landslides. Hence, effective policies and forest management is needed to protect not only the environmental and aesthetic benefits of the forest cover but also to manage the disaster risks. Apart from the forest assessment, this research gives an insight of land cover dynamics, along with causes and consequences, thereby showing the forest degradation hotspots.

BCDForest: a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data.

PubMed

Guo, Yang; Liu, Shuhui; Li, Zhanhuai; Shang, Xuequn

2018-04-11

The classification of cancer subtypes is of great importance to cancer disease diagnosis and therapy. Many supervised learning approaches have been applied to cancer subtype classification in the past few years, especially of deep learning based approaches. Recently, the deep forest model has been proposed as an alternative of deep neural networks to learn hyper-representations by using cascade ensemble decision trees. It has been proved that the deep forest model has competitive or even better performance than deep neural networks in some extent. However, the standard deep forest model may face overfitting and ensemble diversity challenges when dealing with small sample size and high-dimensional biology data. In this paper, we propose a deep learning model, so-called BCDForest, to address cancer subtype classification on small-scale biology datasets, which can be viewed as a modification of the standard deep forest model. The BCDForest distinguishes from the standard deep forest model with the following two main contributions: First, a named multi-class-grained scanning method is proposed to train multiple binary classifiers to encourage diversity of ensemble. Meanwhile, the fitting quality of each classifier is considered in representation learning. Second, we propose a boosting strategy to emphasize more important features in cascade forests, thus to propagate the benefits of discriminative features among cascade layers to improve the classification performance. Systematic comparison experiments on both microarray and RNA-Seq gene expression datasets demonstrate that our method consistently outperforms the state-of-the-art methods in application of cancer subtype classification. The multi-class-grained scanning and boosting strategy in our model provide an effective solution to ease the overfitting challenge and improve the robustness of deep forest model working on small-scale data. Our model provides a useful approach to the classification of cancer subtypes by using deep learning on high-dimensional and small-scale biology data.

Spatio-Temporal Analysis of Forest Fire Risk and Danger Using LANDSAT Imagery.

PubMed

Saglam, Bülent; Bilgili, Ertugrul; Dincdurmaz, Bahar; Kadiogulari, Ali Ihsan; Kücük, Ömer

2008-06-20

Computing fire danger and fire risk on a spatio-temporal scale is of crucial importance in fire management planning, and in the simulation of fire growth and development across a landscape. However, due to the complex nature of forests, fire risk and danger potential maps are considered one of the most difficult thematic layers to build up. Remote sensing and digital terrain data have been introduced for efficient discrete classification of fire risk and fire danger potential. In this study, two time-series data of Landsat imagery were used for determining spatio-temporal change of fire risk and danger potential in Korudag forest planning unit in northwestern Turkey. The method comprised the following two steps: (1) creation of indices of the factors influencing fire risk and danger; (2) evaluation of spatio-temporal changes in fire risk and danger of given areas using remote sensing as a quick and inexpensive means and determining the pace of forest cover change. Fire risk and danger potential indices were based on species composition, stand crown closure, stand development stage, insolation, slope and, proximity of agricultural lands to forest and distance from settlement areas. Using the indices generated, fire risk and danger maps were produced for the years 1987 and 2000. Spatio-temporal analyses were then realized based on the maps produced. Results obtained from the study showed that the use of Landsat imagery provided a valuable characterization and mapping of vegetation structure and type with overall classification accuracy higher than 83%.

78 FR 69374 - Endangered and Threatened Species; Take of Anadromous Fish

Federal Register 2010, 2011, 2012, 2013, 2014

2013-11-19

...-managed forest lands in the state of Washington. The purpose of the research is to conduct surveys to... Snohomish River estuary. The purpose of the study is to measure restored habitat functionality in the wake... of Natural Resources, Snohomish County, and United States Forest Service stream classifications and...

Linear Subpixel Learning Algorithm for Land Cover Classification from WELD using High Performance Computing

NASA Technical Reports Server (NTRS)

Kumar, Uttam; Nemani, Ramakrishna R.; Ganguly, Sangram; Kalia, Subodh; Michaelis, Andrew

2017-01-01

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS-national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91 percent was achieved, which is a 6 percent improvement in unmixing based classification relative to per-pixel-based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

Linear Subpixel Learning Algorithm for Land Cover Classification from WELD using High Performance Computing

NASA Astrophysics Data System (ADS)

Ganguly, S.; Kumar, U.; Nemani, R. R.; Kalia, S.; Michaelis, A.

2017-12-01

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS - national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91% was achieved, which is a 6% improvement in unmixing based classification relative to per-pixel based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

Enhanced Deforestation Mapping in North Korea using Spatial-temporal Image Fusion Method and Phenology-based Index

NASA Astrophysics Data System (ADS)

Jin, Y.; Lee, D.

2017-12-01

North Korea (the Democratic People's Republic of Korea, DPRK) is known to have some of the most degraded forest in the world. The characteristics of forest landscape in North Korea is complex and heterogeneous, the major vegetation cover types in the forest are hillside farm, unstocked forest, natural forest, and plateau vegetation. Better classification of types in high spatial resolution of deforested areas could provide essential information for decisions about forest management priorities and restoration of deforested areas. For mapping heterogeneous vegetation covers, the phenology-based indices are helpful to overcome the reflectance value confusion that occurs when using one season images. Coarse spatial resolution images may be acquired with a high repetition rate and it is useful for analyzing phenology characteristics, but may not capture the spatial detail of the land cover mosaic of the region of interest. Previous spatial-temporal fusion methods were only capture the temporal change, or focused on both temporal change and spatial change but with low accuracy in heterogeneous landscapes and small patches. In this study, a new concept for spatial-temporal image fusion method focus on heterogeneous landscape was proposed to produce fine resolution images at both fine spatial and temporal resolution. We classified the three types of pixels between the base image and target image, the first type is only reflectance changed caused by phenology, this type of pixels supply the reflectance, shape and texture information; the second type is both reflectance and spectrum changed in some bands caused by phenology like rice paddy or farmland, this type of pixels only supply shape and texture information; the third type is reflectance and spectrum changed caused by land cover type change, this type of pixels don't provide any information because we can't know how land cover changed in target image; and each type of pixels were applied different prediction methods. Results show that both STARFM and FSDAF predicted in low accuracy in second type pixels and small patches. Classification results used spatial-temporal image fusion method proposed in this study showed overall classification accuracy of 89.38%, with corresponding kappa coefficients of 0.87.

FIELD TESTS OF GEOGRAPHICALLY-DEPENDENT VS. THRESHOLD-BASED WATERSHED CLASSIFICATION SCHEMES IN THE GREAT LAKES BASIN

EPA Science Inventory

We compared classification schemes based on watershed storage (wetland + lake area/watershed area) and forest fragmentation with a geographically-based classification scheme for two case studies involving 1) Lake Superior tributaries and 2) watersheds of riverine coastal wetlands...

THE WESTERN LAKE SUPERIOR COMPARATIVE WATERSHED FRAMEWORK: A FIELD TEST OF GEOGRAPHICALLY-DEPENDENT VS. THRESHOLD-BASED GEOGRAPHICALLY-INDEPENDENT CLASSIFICATION

EPA Science Inventory

Stratified random selection of watersheds allowed us to compare geographically-independent classification schemes based on watershed storage (wetland + lake area/watershed area) and forest fragmentation with a geographically-based classification scheme within the Northern Lakes a...

FIELD TESTS OF GEOGRAPHICALLY-DEPENDENT VS. THRESHOLD-BASED WATERSHED CLASSIFICATION SCHEMED IN THE GREAT LAKES BASIN

EPA Science Inventory

We compared classification schemes based on watershed storage (wetland + lake area/watershed area) and forest fragmentation with a geographically-based classification scheme for two case studies involving 1)Lake Superior tributaries and 2) watersheds of riverine coastal wetlands ...

Vegetation classification in southern pine mixed hardwood forests using airborne scanning laser point data.

DOE Office of Scientific and Technical Information (OSTI.GOV)

McGaughey, Robert J.; Reutebuch, Stephen E.

2012-10-15

Forests of the southeastern United States are dominated by a relatively small number of conifer species. However, many of these forests also have a hardwood component composed of a wide variety of species that are found in all canopy positions. The presence or absence of hardwood species and their position in the canopy often dictates management activities such as thinning or prescribed burning. In addition, the characteristics of the under- and mid-story layers, often dominated by hardwood species, are key factors when assessing suitable habitat for threatened and endangered species such as the Red Cockaded Woodpecker (Picoides borealis) (RCW), makingmore » information describing the hardwood component important to forest managers. General classification of cover types using LIDAR data has been reported (Song et al. 2002, Brennan and Webster 2006) but most efforts focusing on the identification of individual species or species groups rely on some type of imagery to provide more complete spectral information for the study area. Brandtberg (2007) found that use of intensity data significantly improved LIDAR detection and classification of three leaf-off deciduous eastern species: oaks (Quercus spp.), red maple (Acer rubrum L.), and yellow poplar (Liriodendron tulipifera L.). Our primary objective was to determine the proportion of hardwood species present in the canopy using only the LIDAR point data and derived products. However, the presence of several hardwood species that retain their foliage through the winter months complicated our analyses. We present two classification approaches. The first identifies areas containing hardwood and softwood (conifer) species (H/S) and the second identifies vegetation with foliage absent or present (FA/FP) at the time of the LIDAR data acquisition. The classification results were used to develop predictor variables for forest inventory models. The ability to incorporate the proportion of hardwood and softwood was important to the inventory as well as habitat assessments for the RCW.« less

THE ROLE OF WATERSHED CLASSIFICATION IN DIAGNOSING CAUSES OF BIOLOGICAL IMPAIRMENT

EPA Science Inventory

We compared classification schemes based on watershed storage (wetland + lake area/watershed area) and forest fragmention with a gewographically-based classification scheme for two case studies involving 1) Lake Superior tributaries and 2) watersheds of riverine coastal wetlands ...

Using laser altimetry-based segmentation to refine automated tree identification in managed forests of the Black Hills, South Dakota

Treesearch

Eric Rowell; Carl Selelstad; Lee Vierling; Lloyd Queen; Wayne Sheppard

2006-01-01

The success of a local maximum (LM) tree detection algorithm for detecting individual trees from lidar data depends on stand conditions that are often highly variable. A laser height variance and percent canopy cover (PCC) classification is used to segment the landscape by stand condition prior to stem detection. We test the performance of the LM algorithm using canopy...

Forest vegetation of the Black Hills National Forest of South Dakota and Wyoming: A habitat type classification

Treesearch

George R. Hoffman; Robert R. Alexander

1987-01-01

A vegetation classification based on concepts and methods developed by Daubenmire was used to identify 12 forest habitat types and one shrub habitat type in the Black Hills. Included were two habitat types in the Quercus macrocarpa series, seven in the Pinus ponderosa series, one in the Populus tremuloides series, two in the Picea glaucci series, and one in the...

Object-based methods for individual tree identification and tree species classification from high-spatial resolution imagery

NASA Astrophysics Data System (ADS)

Wang, Le

2003-10-01

Modern forest management poses an increasing need for detailed knowledge of forest information at different spatial scales. At the forest level, the information for tree species assemblage is desired whereas at or below the stand level, individual tree related information is preferred. Remote Sensing provides an effective tool to extract the above information at multiple spatial scales in the continuous time domain. To date, the increasing volume and readily availability of high-spatial-resolution data have lead to a much wider application of remotely sensed products. Nevertheless, to make effective use of the improving spatial resolution, conventional pixel-based classification methods are far from satisfactory. Correspondingly, developing object-based methods becomes a central challenge for researchers in the field of Remote Sensing. This thesis focuses on the development of methods for accurate individual tree identification and tree species classification. We develop a method in which individual tree crown boundaries and treetop locations are derived under a unified framework. We apply a two-stage approach with edge detection followed by marker-controlled watershed segmentation. Treetops are modeled from radiometry and geometry aspects. Specifically, treetops are assumed to be represented by local radiation maxima and to be located near the center of the tree-crown. As a result, a marker image was created from the derived treetop to guide a watershed segmentation to further differentiate overlapping trees and to produce a segmented image comprised of individual tree crowns. The image segmentation method developed achieves a promising result for a 256 x 256 CASI image. Then further effort is made to extend our methods to the multiscales which are constructed from a wavelet decomposition. A scale consistency and geometric consistency are designed to examine the gradients along the scale-space for the purpose of separating true crown boundary from unwanted textures occurring due to branches and twigs. As a result from the inverse wavelet transform, the tree crown boundary is enhanced while the unwanted textures are suppressed. Based on the enhanced image, an improvement is achieved when applying the two-stage methods to a high resolution aerial photograph. To improve tree species classification, we develop a new method to choose the optimal scale parameter with the aid of Bhattacharya Distance (BD), a well-known index of class separability in traditional pixel-based classification. The optimal scale parameter is then fed in the process of a region-growing-based segmentation as a break-off value. Our object classification achieves a better accuracy in separating tree species when compared to the conventional Maximum Likelihood Classification (MLC). In summary, we develop two object-based methods for identifying individual trees and classifying tree species from high-spatial resolution imagery. Both methods achieve promising results and will promote integration of Remote Sensing and GIS in forest applications.

Recent forest cover changes (2002-2015) in the Southern Carpathians: A case study of the Iezer Mountains, Romania.

PubMed

Mihai, Bogdan; Săvulescu, Ionuț; Rujoiu-Mare, Marina; Nistor, Constantin

2017-12-01

The paper explores the dynamics of the forest cover change in the Iezer Mountains, part of Southern Carpathians, in the context of the forest ownership recovery and deforestation processes, combined with the effects of biotic and abiotic disturbances. The aim of the study is to map and evaluate the typology and the spatial extension of changes in the montane forest cover between 700 and 2462m a.s.l., sampling all the representative Carpathian ecosystems, from the European beech zone up to the spruce-fir zone and the subalpine-alpine pastures. The methodology uses a change detection analysis of satellite imagery with Landsat ETM+/OLI and Sentinel-2 MSI data. The workflow started with a complete calibration of multispectral data from 2002, before the massive forest restitution to private owners, after the Law 247/2005 empowerment, and 2015, the intensification of deforestation process. For the data classification, a Maximum Likelihood supervised classification algorithm was utilized. The forest change map was developed after combining the classifications in a unitary formula using image difference. The principal outcome of the research identifies the type of forest cover change using a quantitative formula. This information can be integrated in the future decision-making strategies for forest stand management and sustainable development. Copyright © 2017 Elsevier B.V. All rights reserved.

A minimum spanning forest based classification method for dedicated breast CT images

DOE Office of Scientific and Technical Information (OSTI.GOV)

Pike, Robert; Sechopoulos, Ioannis; Fei, Baowei, E-mail: bfei@emory.edu

Purpose: To develop and test an automated algorithm to classify different types of tissue in dedicated breast CT images. Methods: Images of a single breast of five different patients were acquired with a dedicated breast CT clinical prototype. The breast CT images were processed by a multiscale bilateral filter to reduce noise while keeping edge information and were corrected to overcome cupping artifacts. As skin and glandular tissue have similar CT values on breast CT images, morphologic processing is used to identify the skin based on its position information. A support vector machine (SVM) is trained and the resulting modelmore » used to create a pixelwise classification map of fat and glandular tissue. By combining the results of the skin mask with the SVM results, the breast tissue is classified as skin, fat, and glandular tissue. This map is then used to identify markers for a minimum spanning forest that is grown to segment the image using spatial and intensity information. To evaluate the authors’ classification method, they use DICE overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on five patient images. Results: Comparison between the automatic and the manual segmentation shows that the minimum spanning forest based classification method was able to successfully classify dedicated breast CT image with average DICE ratios of 96.9%, 89.8%, and 89.5% for fat, glandular, and skin tissue, respectively. Conclusions: A 2D minimum spanning forest based classification method was proposed and evaluated for classifying the fat, skin, and glandular tissue in dedicated breast CT images. The classification method can be used for dense breast tissue quantification, radiation dose assessment, and other applications in breast imaging.« less

An assessment of commonly employed satellite-based remote sensors for mapping mangrove species in Mexico using an NDVI-based classification scheme.

PubMed

Valderrama-Landeros, L; Flores-de-Santiago, F; Kovacs, J M; Flores-Verdugo, F

2017-12-14

Optimizing the classification accuracy of a mangrove forest is of utmost importance for conservation practitioners. Mangrove forest mapping using satellite-based remote sensing techniques is by far the most common method of classification currently used given the logistical difficulties of field endeavors in these forested wetlands. However, there is now an abundance of options from which to choose in regards to satellite sensors, which has led to substantially different estimations of mangrove forest location and extent with particular concern for degraded systems. The objective of this study was to assess the accuracy of mangrove forest classification using different remotely sensed data sources (i.e., Landsat-8, SPOT-5, Sentinel-2, and WorldView-2) for a system located along the Pacific coast of Mexico. Specifically, we examined a stressed semiarid mangrove forest which offers a variety of conditions such as dead areas, degraded stands, healthy mangroves, and very dense mangrove island formations. The results indicated that Landsat-8 (30 m per pixel) had  the lowest overall accuracy at 64% and that WorldView-2 (1.6 m per pixel) had the highest at 93%. Moreover, the SPOT-5 and the Sentinel-2 classifications (10 m per pixel) were very similar having accuracies of 75 and 78%, respectively. In comparison to WorldView-2, the other sensors overestimated the extent of Laguncularia racemosa and underestimated the extent of Rhizophora mangle. When considering such type of sensors, the higher spatial resolution can be particularly important in mapping small mangrove islands that often occur in degraded mangrove systems.

Classification and evaluation for forest sites on the Southern Cumberland Plateau

Treesearch

Glendon W. Smalley

1979-01-01

This paper presents a comprehensive forest site classification system for the southern portion of the Cumberland Plateau in northern Alabama, northwest Georgia, and extreme south-central Tennessee. The system is based on physiography, geology, soils, topography, and vegetation. Twenty-one landtypes are described, and each landtype is evaluated in terms of productivity...

Forest statistics for Arkansas counties - 1988

Treesearch

F. Dee Hines; John S. Vissage

1988-01-01

The tables and figures in this report were derived from data obtained during a recent inventory of the five survey regions and 75 counties in the State of Arkansas (fig. I), Data on forest-nonforest classification using aerial photographs was accomplished for points representing approximately 230 acres. These photo classifications were adjusted based on ground...

Semantic Segmentation of Forest Stands of Pure Species as a Global Optimization Problem

NASA Astrophysics Data System (ADS)

Dechesne, C.; Mallet, C.; Le Bris, A.; Gouet-Brunet, V.

2017-05-01

Forest stand delineation is a fundamental task for forest management purposes, that is still mainly manually performed through visual inspection of geospatial (very) high spatial resolution images. Stand detection has been barely addressed in the literature which has mainly focused, in forested environments, on individual tree extraction and tree species classification. From a methodological point of view, stand detection can be considered as a semantic segmentation problem. It offers two advantages. First, one can retrieve the dominant tree species per segment. Secondly, one can benefit from existing low-level tree species label maps from the literature as a basis for high-level object extraction. Thus, the semantic segmentation issue becomes a regularization issue in a weakly structured environment and can be formulated in an energetical framework. This papers aims at investigating which regularization strategies of the literature are the most adapted to delineate and classify forest stands of pure species. Both airborne lidar point clouds and multispectral very high spatial resolution images are integrated for that purpose. The local methods (such as filtering and probabilistic relaxation) are not adapted for such problem since the increase of the classification accuracy is below 5%. The global methods, based on an energy model, tend to be more efficient with an accuracy gain up to 15%. The segmentation results using such models have an accuracy ranging from 96% to 99%.

Comparison of High and Low Density Airborne LIDAR Data for Forest Road Quality Assessment

NASA Astrophysics Data System (ADS)

Kiss, K.; Malinen, J.; Tokola, T.

2016-06-01

Good quality forest roads are important for forest management. Airborne laser scanning data can help create automatized road quality detection, thus avoiding field visits. Two different pulse density datasets have been used to assess road quality: high-density airborne laser scanning data from Kiihtelysvaara and low-density data from Tuusniemi, Finland. The field inventory mainly focused on the surface wear condition, structural condition, flatness, road side vegetation and drying of the road. Observations were divided into poor, satisfactory and good categories based on the current Finnish quality standards used for forest roads. Digital Elevation Models were derived from the laser point cloud, and indices were calculated to determine road quality. The calculated indices assessed the topographic differences on the road surface and road sides. The topographic position index works well in flat terrain only, while the standardized elevation index described the road surface better if the differences are bigger. Both indices require at least a 1 metre resolution. High-density data is necessary for analysis of the road surface, and the indices relate mostly to the surface wear and flatness. The classification was more precise (31-92%) than on low-density data (25-40%). However, ditch detection and classification can be carried out using the sparse dataset as well (with a success rate of 69%). The use of airborne laser scanning data can provide quality information on forest roads.

Urban forest topographical mapping using UAV LIDAR

NASA Astrophysics Data System (ADS)

Putut Ash Shidiq, Iqbal; Wibowo, Adi; Kusratmoko, Eko; Indratmoko, Satria; Ardhianto, Ronni; Prasetyo Nugroho, Budi

2017-12-01

Topographical data is highly needed by many parties, such as government institution, mining companies and agricultural sectors. It is not just about the precision, the acquisition time and data processing are also carefully considered. In relation with forest management, a high accuracy topographic map is necessary for planning, close monitoring and evaluating forest changes. One of the solution to quickly and precisely mapped topography is using remote sensing system. In this study, we test high-resolution data using Light Detection and Ranging (LiDAR) collected from unmanned aerial vehicles (UAV) to map topography and differentiate vegetation classes based on height in urban forest area of University of Indonesia (UI). The semi-automatic and manual classifications were applied to divide point clouds into two main classes, namely ground and vegetation. There were 15,806,380 point clouds obtained during the post-process, in which 2.39% of it were detected as ground.

A discrimlnant function approach to ecological site classification in northern New England

Treesearch

James M. Fincher; Marie-Louise Smith

1994-01-01

Describes one approach to ecologically based classification of upland forest community types of the White and Green Mountain physiographic regions. The classification approach is based on an intensive statistical analysis of the relationship between the communities and soil-site factors. Discriminant functions useful in distinguishing between types based on soil-site...

Using ecological zones to increase the detail of Landsat classifications

NASA Technical Reports Server (NTRS)

Fox, L., III; Mayer, K. E.

1981-01-01

Changes in classification detail of forest species descriptions were made for Landsat data on 2.2 million acres in northwestern California. Because basic forest canopy structures may exhibit very similar E-M energy reflectance patterns in different environmental regions, classification labels based on Landsat spectral signatures alone become very generalized when mapping large heterogeneous ecological regions. By adding a seven ecological zone stratification, a 167% improvement in classification detail was made over the results achieved without it. The seven zone stratification is a less costly alternative to the inclusion of complex collateral information, such as terrain data and soil type, into the Landsat data base when making inventories of areas greater than 500,000 acres.

Satellite inventory of Minnesota forest resources

NASA Technical Reports Server (NTRS)

Bauer, Marvin E.; Burk, Thomas E.; Ek, Alan R.; Coppin, Pol R.; Lime, Stephen D.; Walsh, Terese A.; Walters, David K.; Befort, William; Heinzen, David F.

1993-01-01

The methods and results of using Landsat Thematic Mapper (TM) data to classify and estimate the acreage of forest covertypes in northeastern Minnesota are described. Portions of six TM scenes covering five counties with a total area of 14,679 square miles were classified into six forest and five nonforest classes. The approach involved the integration of cluster sampling, image processing, and estimation. Using cluster sampling, 343 plots, each 88 acres in size, were photo interpreted and field mapped as a source of reference data for classifier training and calibration of the TM data classifications. Classification accuracies of up to 75 percent were achieved; most misclassification was between similar or related classes. An inverse method of calibration, based on the error rates obtained from the classifications of the cluster plots, was used to adjust the classification class proportions for classification errors. The resulting area estimates for total forest land in the five-county area were within 3 percent of the estimate made independently by the USDA Forest Service. Area estimates for conifer and hardwood forest types were within 0.8 and 6.0 percent respectively, of the Forest Service estimates. A trial of a second method of estimating the same classes as the Forest Service resulted in standard errors of 0.002 to 0.015. A study of the use of multidate TM data for change detection showed that forest canopy depletion, canopy increment, and no change could be identified with greater than 90 percent accuracy. The project results have been the basis for the Minnesota Department of Natural Resources and the Forest Service to define and begin to implement an annual system of forest inventory which utilizes Landsat TM data to detect changes in forest cover.

Differential privacy-based evaporative cooling feature selection and classification with relief-F and random forests.

PubMed

Le, Trang T; Simmons, W Kyle; Misaki, Masaya; Bodurka, Jerzy; White, Bill C; Savitz, Jonathan; McKinney, Brett A

2017-09-15

Classification of individuals into disease or clinical categories from high-dimensional biological data with low prediction error is an important challenge of statistical learning in bioinformatics. Feature selection can improve classification accuracy but must be incorporated carefully into cross-validation to avoid overfitting. Recently, feature selection methods based on differential privacy, such as differentially private random forests and reusable holdout sets, have been proposed. However, for domains such as bioinformatics, where the number of features is much larger than the number of observations p≫n , these differential privacy methods are susceptible to overfitting. We introduce private Evaporative Cooling, a stochastic privacy-preserving machine learning algorithm that uses Relief-F for feature selection and random forest for privacy preserving classification that also prevents overfitting. We relate the privacy-preserving threshold mechanism to a thermodynamic Maxwell-Boltzmann distribution, where the temperature represents the privacy threshold. We use the thermal statistical physics concept of Evaporative Cooling of atomic gases to perform backward stepwise privacy-preserving feature selection. On simulated data with main effects and statistical interactions, we compare accuracies on holdout and validation sets for three privacy-preserving methods: the reusable holdout, reusable holdout with random forest, and private Evaporative Cooling, which uses Relief-F feature selection and random forest classification. In simulations where interactions exist between attributes, private Evaporative Cooling provides higher classification accuracy without overfitting based on an independent validation set. In simulations without interactions, thresholdout with random forest and private Evaporative Cooling give comparable accuracies. We also apply these privacy methods to human brain resting-state fMRI data from a study of major depressive disorder. Code available at http://insilico.utulsa.edu/software/privateEC . brett-mckinney@utulsa.edu. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Geomorphology and forest management in New Zealand's erodible steeplands: An overview

NASA Astrophysics Data System (ADS)

Phillips, Chris; Marden, Michael; Basher, Les R.

2018-04-01

In this paper we outline how geomorphological understanding has underpinned forest management in New Zealand's erodible steeplands, where it contributes to current forest management, and suggest where it will be of value in the future. We focus on the highly erodible soft-rock hill country of the East Coast region of North Island, but cover other parts of New Zealand where appropriate. We conclude that forestry will continue to make a significant contribution to New Zealand's economy, but several issues need to be addressed. The most pressing concerns are the incidence of post-harvest, storm-initiated landslides and debris flows arising from steepland forests following timber harvesting. There are three areas where geomorphological information and understanding are required to support the forest industry - development of an improved national erosion susceptibility classification to support a new national standard for plantation forestry; terrain analysis to support improved hazard and risk assessment at detailed operational scales; and understanding of post-harvest shallow landslide-debris flows, including their prediction and management.

Ensemble classification of individual Pinus crowns from multispectral satellite imagery and airborne LiDAR

NASA Astrophysics Data System (ADS)

Kukunda, Collins B.; Duque-Lazo, Joaquín; González-Ferreiro, Eduardo; Thaden, Hauke; Kleinn, Christoph

2018-03-01

Distinguishing tree species is relevant in many contexts of remote sensing assisted forest inventory. Accurate tree species maps support management and conservation planning, pest and disease control and biomass estimation. This study evaluated the performance of applying ensemble techniques with the goal of automatically distinguishing Pinus sylvestris L. and Pinus uncinata Mill. Ex Mirb within a 1.3 km2 mountainous area in Barcelonnette (France). Three modelling schemes were examined, based on: (1) high-density LiDAR data (160 returns m-2), (2) Worldview-2 multispectral imagery, and (3) Worldview-2 and LiDAR in combination. Variables related to the crown structure and height of individual trees were extracted from the normalized LiDAR point cloud at individual-tree level, after performing individual tree crown (ITC) delineation. Vegetation indices and the Haralick texture indices were derived from Worldview-2 images and served as independent spectral variables. Selection of the best predictor subset was done after a comparison of three variable selection procedures: (1) Random Forests with cross validation (AUCRFcv), (2) Akaike Information Criterion (AIC) and (3) Bayesian Information Criterion (BIC). To classify the species, 9 regression techniques were combined using ensemble models. Predictions were evaluated using cross validation and an independent dataset. Integration of datasets and models improved individual tree species classification (True Skills Statistic, TSS; from 0.67 to 0.81) over individual techniques and maintained strong predictive power (Relative Operating Characteristic, ROC = 0.91). Assemblage of regression models and integration of the datasets provided more reliable species distribution maps and associated tree-scale mapping uncertainties. Our study highlights the potential of model and data assemblage at improving species classifications needed in present-day forest planning and management.

Status of Vegetation Classification in Redwood Ecosystems

Treesearch

Thomas M. Mahony; John D. Stuart

2007-01-01

Vegetation classifications, based primarily on physiognomic variability and canopy dominants and derived principally from remotely sensed imagery, have been completed for the entire redwood range (Eyre 1980, Fox 1989). However, systematic, quantitative, floristic-based vegetation classifications in old-growth redwood forests have not been completed for large portions...

Forest cover type analysis of New England forests using innovative WorldView-2 imagery

NASA Astrophysics Data System (ADS)

Kovacs, Jenna M.

For many years, remote sensing has been used to generate land cover type maps to create a visual representation of what is occurring on the ground. One significant use of remote sensing is the identification of forest cover types. New England forests are notorious for their especially complex forest structure and as a result have been, and continue to be, a challenge when classifying forest cover types. To most accurately depict forest cover types occurring on the ground, it is essential to utilize image data that have a suitable combination of both spectral and spatial resolution. The WorldView-2 (WV2) commercial satellite, launched in 2009, is the first of its kind, having both high spectral and spatial resolutions. WV2 records eight bands of multispectral imagery, four more than the usual high spatial resolution sensors, and has a pixel size of 1.85 meters at the nadir. These additional bands have the potential to improve classification detail and classification accuracy of forest cover type maps. For this reason, WV2 imagery was utilized on its own, and in combination with Landsat 5 TM (LS5) multispectral imagery, to evaluate whether these image data could more accurately classify forest cover types. In keeping with recent developments in image analysis, an Object-Based Image Analysis (OBIA) approach was used to segment images of Pawtuckaway State Park and nearby private lands, an area representative of the typical complex forest structure found in the New England region. A Classification and Regression Tree (CART) analysis was then used to classify image segments at two levels of classification detail. Accuracies for each forest cover type map produced were generated using traditional and area-based error matrices, and additional standard accuracy measures (i.e., KAPPA) were generated. The results from this study show that there is value in analyzing imagery with both high spectral and spatial resolutions, and that WV2's new and innovative bands can be useful for the classification of complex forest structures.

Development of computer software to analyze entire LANDSAT scenes and to summarize classification results of variable-size polygons

NASA Technical Reports Server (NTRS)

Turner, B. J. (Principal Investigator); Baumer, G. M.; Myers, W. L.; Sykes, S. G.

1981-01-01

The Forest Pest Management Division (FPMD) of the Pennsylvania Bureau of Forestry has the responsibility for conducting annual surveys of the State's forest lands to accurately detect, map, and appraise forest insect infestations. A standardized, timely, and cost-effective method of accurately surveying forests and their condition should enhance the probability of suppressing infestations. The repetitive and synoptic coverage provided by LANDSAT (formerly ERTS) makes such satellite-derived data potentially attractive as a survey medium for monitoring forest insect damage over large areas. Forest Pest Management Division personnel have expressed keen interest in LANDSAT data and have informally cooperated with NASA/Goddard Space Flight Center (GSFC) since 1976 in the development of techniques to facilitate their use. The results of this work indicate that it may be feasible to use LANDSAT digital data to conduct annual surveys of insect defoliation of hardwood forests.

Plant association and management guide for the western hemlock zone.

Treesearch

Christopher Topik; Nancy M. Halverson; Dale G. Brockway

1986-01-01

This guide presents the plant association classification for the western hemlock zone of the Gifford Pinchot National Forest. The bulk of the forest below about 3000 feet in elevation is included in this zone, comprising about one half of the entire landbase. Much of this area is blanketed with productive stands of Douglas-fir.

Lidar-based individual tree species classification using convolutional neural network

NASA Astrophysics Data System (ADS)

Mizoguchi, Tomohiro; Ishii, Akira; Nakamura, Hiroyuki; Inoue, Tsuyoshi; Takamatsu, Hisashi

2017-06-01

Terrestrial lidar is commonly used for detailed documentation in the field of forest inventory investigation. Recent improvements of point cloud processing techniques enabled efficient and precise computation of an individual tree shape parameters, such as breast-height diameter, height, and volume. However, tree species are manually specified by skilled workers to date. Previous works for automatic tree species classification mainly focused on aerial or satellite images, and few works have been reported for classification techniques using ground-based sensor data. Several candidate sensors can be considered for classification, such as RGB or multi/hyper spectral cameras. Above all candidates, we use terrestrial lidar because it can obtain high resolution point cloud in the dark forest. We selected bark texture for the classification criteria, since they clearly represent unique characteristics of each tree and do not change their appearance under seasonable variation and aged deterioration. In this paper, we propose a new method for automatic individual tree species classification based on terrestrial lidar using Convolutional Neural Network (CNN). The key component is the creation step of a depth image which well describe the characteristics of each species from a point cloud. We focus on Japanese cedar and cypress which cover the large part of domestic forest. Our experimental results demonstrate the effectiveness of our proposed method.

Land cover and forest formation distributions for St. Kitts, Nevis, St. Eustatius, Grenada and Barbados from decision tree classification of cloud-cleared satellite imagery. Caribbean Journal of Science. 44(2):175-198.

Treesearch

E.H. Helmer; T.A. Kennaway; D.H. Pedreros; M.L. Clark; H. Marcano-Vega; L.L. Tieszen; S.R. Schill; C.M.S. Carrington

2008-01-01

Satellite image-based mapping of tropical forests is vital to conservation planning. Standard methods for automated image classification, however, limit classification detail in complex tropical landscapes. In this study, we test an approach to Landsat image interpretation on four islands of the Lesser Antilles, including Grenada and St. Kitts, Nevis and St. Eustatius...

The Greek National Observatory of Forest Fires (NOFFi)

NASA Astrophysics Data System (ADS)

Tompoulidou, Maria; Stefanidou, Alexandra; Grigoriadis, Dionysios; Dragozi, Eleni; Stavrakoudis, Dimitris; Gitas, Ioannis Z.

2016-08-01

Efficient forest fire management is a key element for alleviating the catastrophic impacts of wildfires. Overall, the effective response to fire events necessitates adequate planning and preparedness before the start of the fire season, as well as quantifying the environmental impacts in case of wildfires. Moreover, the estimation of fire danger provides crucial information required for the optimal allocation and distribution of the available resources. The Greek National Observatory of Forest Fires (NOFFi)—established by the Greek Forestry Service in collaboration with the Laboratory of Forest Management and Remote Sensing of the Aristotle University of Thessaloniki and the International Balkan Center—aims to develop a series of modern products and services for supporting the efficient forest fire prevention management in Greece and the Balkan region, as well as to stimulate the development of transnational fire prevention and impacts mitigation policies. More specifically, NOFFi provides three main fire-related products and services: a) a remote sensing-based fuel type mapping methodology, b) a semi-automatic burned area mapping service, and c) a dynamically updatable fire danger index providing mid- to long-term predictions. The fuel type mapping methodology was developed and applied across the country, following an object-oriented approach and using Landsat 8 OLI satellite imagery. The results showcase the effectiveness of the generated methodology in obtaining highly accurate fuel type maps on a national level. The burned area mapping methodology was developed as a semi-automatic object-based classification process, carefully crafted to minimize user interaction and, hence, be easily applicable on a near real-time operational level as well as for mapping historical events. NOFFi's products can be visualized through the interactive Fire Forest portal, which allows the involvement and awareness of the relevant stakeholders via the Public Participation GIS (PPGIS) tool.

Ecological type classification for California: the Forest Service approach

Treesearch

Barbara H. Allen

1987-01-01

National legislation has mandated the development and use of an ecological data base to improve resource decision making, while State and Federal agencies have agreed to cooperate in standardizing resource classification and inventory data. In the Pacific Southwest Region, which includes nearly 20 million acres (8.3 million ha) in California, the Forest Service, U.S....

Landsat TM Classifications For SAFIS Using FIA Field Plots

Treesearch

William H. Cooke; Andrew J. Hartsell

2001-01-01

Wall-to-wall Landsat Thematic Mapper (TM) classification efforts in Georgia require field validation. We developed a new crown modeling procedure based on Forest Health Monitoring (FHM) data to test Forest Inventory and Analysis (FIA) data. These models simulate the proportion of tree crowns that reflect light on a FIA subplot basis. We averaged subplot crown...

Evaluating the Effectiveness of Flood Control Strategies in Contrasting Urban Watersheds and Implications for Houston's Future Flood Vulnerability

NASA Astrophysics Data System (ADS)

Ganguly, S.; Kumar, U.; Nemani, R. R.; Kalia, S.; Michaelis, A.

2016-12-01

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS - national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91% was achieved, which is a 6% improvement in unmixing based classification relative to per-pixel based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

Peculiarities of use of ECOC and AdaBoost based classifiers for thematic processing of hyperspectral data

NASA Astrophysics Data System (ADS)

Dementev, A. O.; Dmitriev, E. V.; Kozoderov, V. V.; Egorov, V. D.

2017-10-01

Hyperspectral imaging is up-to-date promising technology widely applied for the accurate thematic mapping. The presence of a large number of narrow survey channels allows us to use subtle differences in spectral characteristics of objects and to make a more detailed classification than in the case of using standard multispectral data. The difficulties encountered in the processing of hyperspectral images are usually associated with the redundancy of spectral information which leads to the problem of the curse of dimensionality. Methods currently used for recognizing objects on multispectral and hyperspectral images are usually based on standard base supervised classification algorithms of various complexity. Accuracy of these algorithms can be significantly different depending on considered classification tasks. In this paper we study the performance of ensemble classification methods for the problem of classification of the forest vegetation. Error correcting output codes and boosting are tested on artificial data and real hyperspectral images. It is demonstrates, that boosting gives more significant improvement when used with simple base classifiers. The accuracy in this case in comparable the error correcting output code (ECOC) classifier with Gaussian kernel SVM base algorithm. However the necessity of boosting ECOC with Gaussian kernel SVM is questionable. It is demonstrated, that selected ensemble classifiers allow us to recognize forest species with high enough accuracy which can be compared with ground-based forest inventory data.

Time Series of Images to Improve Tree Species Classification

NASA Astrophysics Data System (ADS)

Miyoshi, G. T.; Imai, N. N.; de Moraes, M. V. A.; Tommaselli, A. M. G.; Näsi, R.

2017-10-01

Tree species classification provides valuable information to forest monitoring and management. The high floristic variation of the tree species appears as a challenging issue in the tree species classification because the vegetation characteristics changes according to the season. To help to monitor this complex environment, the imaging spectroscopy has been largely applied since the development of miniaturized sensors attached to Unmanned Aerial Vehicles (UAV). Considering the seasonal changes in forests and the higher spectral and spatial resolution acquired with sensors attached to UAV, we present the use of time series of images to classify four tree species. The study area is an Atlantic Forest area located in the western part of São Paulo State. Images were acquired in August 2015 and August 2016, generating three data sets of images: only with the image spectra of 2015; only with the image spectra of 2016; with the layer stacking of images from 2015 and 2016. Four tree species were classified using Spectral angle mapper (SAM), Spectral information divergence (SID) and Random Forest (RF). The results showed that SAM and SID caused an overfitting of the data whereas RF showed better results and the use of the layer stacking improved the classification achieving a kappa coefficient of 18.26 %.

Field guide for forested plant associations of the Wenatchee National Forest.

Treesearch

T.R. Lillybridge; B.L. Kovalchik; C.K. Williams; B.G. Smith

1995-01-01

A classification of forest vegetation is presented for the Wenatchee National Forest (NF). It is based on potential vegetation, with the plant association as the basic unit. The sample includes about 570 intensive plots and 840 reconnaissance plots distributed across the Wenatchee National Forest and the southwest portion of the Okanogan National Forest from 1975...

Potential of VIIRS Time Series Data for Aiding the USDA Forest Service Early Warning System for Forest Health Threats: A Gypsy Moth Defoliation Case Study

NASA Technical Reports Server (NTRS)

Spruce, Joseph P.; Ryan, Robert E.; Smoot, James; Kuper, Phillip; Prados, Donald; Russell, Jeffrey; Ross, Kenton; Gasser, Gerald; Sader, Steven; McKellip, Rodney

2007-01-01

This report details one of three experiments performed during FY 2007 for the NASA RPC (Rapid Prototyping Capability) at Stennis Space Center. This RPC experiment assesses the potential of VIIRS (Visible/Infrared Imager/Radiometer Suite) and MODIS (Moderate Resolution Imaging Spectroradiometer) data for detecting and monitoring forest defoliation from the non-native Eurasian gypsy moth (Lymantria dispar). The intent of the RPC experiment was to assess the degree to which VIIRS data can provide forest disturbance monitoring information as an input to a forest threat EWS (Early Warning System) as compared to the level of information that can be obtained from MODIS data. The USDA Forest Service (USFS) plans to use MODIS products for generating broad-scaled, regional monitoring products as input to an EWS for forest health threat assessment. NASA SSC is helping the USFS to evaluate and integrate currently available satellite remote sensing technologies and data products for the EWS, including the use of MODIS products for regional monitoring of forest disturbance. Gypsy moth defoliation of the mid-Appalachian highland region was selected as a case study. Gypsy moth is one of eight major forest insect threats listed in the Healthy Forest Restoration Act (HFRA) of 2003; the gypsy moth threatens eastern U.S. hardwood forests, which are also a concern highlighted in the HFRA of 2003. This region was selected for the project because extensive gypsy moth defoliation occurred there over multiple years during the MODIS operational period. This RPC experiment is relevant to several nationally important mapping applications, including agricultural efficiency, coastal management, ecological forecasting, disaster management, and carbon management. In this experiment, MODIS data and VIIRS data simulated from MODIS were assessed for their ability to contribute broad, regional geospatial information on gypsy moth defoliation. Landsat and ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) data were used to assess the quality of gypsy moth defoliation mapping products derived from MODIS data and from simulated VIIRS data. The project focused on use of data from MODIS Terra as opposed to MODIS Aqua mainly because only MODIS Terra data was collected during 2000 and 2001-years with comparatively high amounts of gypsy moth defoliation within the study area. The project assessed the quality of VIIRS data simulation products. Hyperion data was employed to assess the quality of MODIS-based VIIRS simulation datasets using image correlation analysis techniques. The ART (Application Research Toolbox) software was used for data simulation. Correlation analysis between MODIS-simulated VIIRS data and Hyperion-simulated VIIRS data for red, NIR (near-infrared), and NDVI (Normalized Difference Vegetation Index) image data products collectively indicate that useful, effective VIIRS simulations can be produced using Hyperion and MODIS data sources. The r(exp 2) for red, NIR, and NDVI products were 0.56, 0.63, and 0.62, respectively, indicating a moderately high correlation between the 2 data sources. Temporal decorrelation from different data acquisition times and image misregistration may have lowered correlation results. The RPC experiment also generated MODIS-based time series data products using the TSPT (Time Series Product Tool) software. Time series of simulated VIIRS NDVI products were produced at approximately 400-meter resolution GSD (Ground Sampling Distance) at nadir for comparison to MODIS NDVI products at either 250- or 500-meter GSD. The project also computed MODIS (MOD02) NDMI (Normalized Difference Moisture Index) products at 500-meter GSD for comparison to NDVI-based products. For each year during 2000-2006, MODIS and VIIRS (simulated from MOD02) time series were computed during the peak gypsy moth defoliation time frame in the study area (approximately June 10 through July 27). Gypsy moth defoliation mapping products from simated VIIRS and MOD02 time series were produced using multiple methods, including image classification and change detection via image differencing. The latter enabled an automated defoliation detection product computed using percent change in maximum NDVI for a peak defoliation period during 2001 compared to maximum NDVI across the entire 2000-2006 time frame. Final gypsy moth defoliation mapping products were assessed for accuracy using randomly sampled locations found on available geospatial reference data (Landsat and ASTER data in conjunction with defoliation map data from the USFS). Extensive gypsy moth defoliation patches were evident on screen displays of multitemporal color composites derived from MODIS data and from simulated VIIRS vegetation index data. Such defoliation was particularly evident for 2001, although widespread denuded forests were also seen for 2000 and 2003. These visualizations were validated using aforementioned reference data. Defoliation patches were visible on displays of MODIS-based NDVI and NDMI data. The viewing of apparent defoliation patches on all of these products necessitated adoption of a specialized temporal data processing method (e.g., maximum NDVI during the peak defoliation time frame). The frequency of cloud cover necessitated this approach. Multitemporal simulated VIIRS and MODIS Terra data both produced effective general classifications of defoliated forest versus other land cover. For 2001, the MOD02-simulated VIIRS 400-meter NDVI classification produced a similar yet slightly lower overall accuracy (87.28 percent with 0.72 Kappa) than the MOD02 250-meter NDVI classification (88.44 percent with 0.75 Kappa). The MOD13 250-meter NDVI classification had a lower overall accuracy (79.13 percent) and a much lower Kappa (0.46). The report discusses accuracy assessment results in much more detail, comparing overall classification and individual class accuracy statistics for simulated VIIRS 400-meter NDVI, MOD02 250-meter NDVI, MOD02-500 meter NDVI, MOD13 250-meter NDVI, and MOD02 500-meter NDMI classifications. Automated defoliation detection products from simulated VIIRS and MOD02 data for 2001 also yielded similar, relatively high overall classification accuracy (85.55 percent for the VIIRS 400-meter NDVI versus 87.28 percent for the MOD02 250-meter NDVI). In contrast, the USFS aerial sketch map of gypsy moth defoliation showed a lower overall classification accuracy at 73.64 percent. The overall classification Kappa values were also similar for the VIIRS (approximately 0.67 Kappa) versus the MOD02 (approximately 0.72 Kappa) automated defoliation detection product, which were much higher than the values exhibited by the USFS sketch map product (overall Kappa of approximately 0.47). The report provides additional details on the accuracy of automated gypsy moth defoliation detection products compared with USFS sketch maps. The results suggest that VIIRS data can be effectively simulated from MODIS data and that VIIRS data will produce gypsy moth defoliation mapping products that are similar to MODIS-based products. The results of the RPC experiment indicate that VIIRS and MODIS data products have good potential for integration into the forest threat EWS. The accuracy assessment was performed only for 2001 because of time constraints and a relative scarcity of cloud-free Landsat and ASTER data for the peak defoliation period of the other years in the 2000-2006 time series. Additional work should be performed to assess the accuracy of gypsy moth defoliation detection products for additional years.The study area (mid-Appalachian highlands) and application (gypsy moth forest defoliation) are not necessarily representative of all forested regions and of all forest threat disturbance agents. Additional work should be performed on other inland and coastal regions as well as for other major forest threats.

Image matching as a data source for forest inventory - Comparison of Semi-Global Matching and Next-Generation Automatic Terrain Extraction algorithms in a typical managed boreal forest environment

NASA Astrophysics Data System (ADS)

Kukkonen, M.; Maltamo, M.; Packalen, P.

2017-08-01

Image matching is emerging as a compelling alternative to airborne laser scanning (ALS) as a data source for forest inventory and management. There is currently an open discussion in the forest inventory community about whether, and to what extent, the new method can be applied to practical inventory campaigns. This paper aims to contribute to this discussion by comparing two different image matching algorithms (Semi-Global Matching [SGM] and Next-Generation Automatic Terrain Extraction [NGATE]) and ALS in a typical managed boreal forest environment in southern Finland. Spectral features from unrectified aerial images were included in the modeling and the potential of image matching in areas without a high resolution digital terrain model (DTM) was also explored. Plot level predictions for total volume, stem number, basal area, height of basal area median tree and diameter of basal area median tree were modeled using an area-based approach. Plot level dominant tree species were predicted using a random forest algorithm, also using an area-based approach. The statistical difference between the error rates from different datasets was evaluated using a bootstrap method. Results showed that ALS outperformed image matching with every forest attribute, even when a high resolution DTM was used for height normalization and spectral information from images was included. Dominant tree species classification with image matching achieved accuracy levels similar to ALS regardless of the resolution of the DTM when spectral metrics were used. Neither of the image matching algorithms consistently outperformed the other, but there were noticeably different error rates depending on the parameter configuration, spectral band, resolution of DTM, or response variable. This study showed that image matching provides reasonable point cloud data for forest inventory purposes, especially when a high resolution DTM is available and information from the understory is redundant.

Multi-label spacecraft electrical signal classification method based on DBN and random forest

PubMed Central

Li, Ke; Yu, Nan; Li, Pengfei; Song, Shimin; Wu, Yalei; Li, Yang; Liu, Meng

2017-01-01

In spacecraft electrical signal characteristic data, there exists a large amount of data with high-dimensional features, a high computational complexity degree, and a low rate of identification problems, which causes great difficulty in fault diagnosis of spacecraft electronic load systems. This paper proposes a feature extraction method that is based on deep belief networks (DBN) and a classification method that is based on the random forest (RF) algorithm; The proposed algorithm mainly employs a multi-layer neural network to reduce the dimension of the original data, and then, classification is applied. Firstly, we use the method of wavelet denoising, which was used to pre-process the data. Secondly, the deep belief network is used to reduce the feature dimension and improve the rate of classification for the electrical characteristics data. Finally, we used the random forest algorithm to classify the data and comparing it with other algorithms. The experimental results show that compared with other algorithms, the proposed method shows excellent performance in terms of accuracy, computational efficiency, and stability in addressing spacecraft electrical signal data. PMID:28486479

Multi-label spacecraft electrical signal classification method based on DBN and random forest.

PubMed

Li, Ke; Yu, Nan; Li, Pengfei; Song, Shimin; Wu, Yalei; Li, Yang; Liu, Meng

2017-01-01

In spacecraft electrical signal characteristic data, there exists a large amount of data with high-dimensional features, a high computational complexity degree, and a low rate of identification problems, which causes great difficulty in fault diagnosis of spacecraft electronic load systems. This paper proposes a feature extraction method that is based on deep belief networks (DBN) and a classification method that is based on the random forest (RF) algorithm; The proposed algorithm mainly employs a multi-layer neural network to reduce the dimension of the original data, and then, classification is applied. Firstly, we use the method of wavelet denoising, which was used to pre-process the data. Secondly, the deep belief network is used to reduce the feature dimension and improve the rate of classification for the electrical characteristics data. Finally, we used the random forest algorithm to classify the data and comparing it with other algorithms. The experimental results show that compared with other algorithms, the proposed method shows excellent performance in terms of accuracy, computational efficiency, and stability in addressing spacecraft electrical signal data.

Operational considerations for the application of remotely sensed forest data from LANDSAT or other airborne platforms

NASA Technical Reports Server (NTRS)

Baker, G. R.; Fethe, T. P.

1975-01-01

Research in the application of remotely sensed data from LANDSAT or other airborne platforms to the efficient management of a large timber based forest industry was divided into three phases: (1) establishment of a photo/ground sample correlation, (2) investigation of techniques for multi-spectral digital analysis, and (3) development of a semi-automated multi-level sampling system. To properly verify results, three distinct test areas were selected: (1) Jacksonville Mill Region, Lower Coastal Plain, Flatwoods, (2) Pensacola Mill Region, Middle Coastal Plain, and (3) Mississippi Mill Region, Middle Coastal Plain. The following conclusions were reached: (1) the probability of establishing an information base suitable for management requirements through a photo/ground double sampling procedure, alleviating the ground sampling effort, is encouraging, (2) known classification techniques must be investigated to ascertain the level of precision possible in separating the many densities involved, and (3) the multi-level approach must be related to an information system that is executable and feasible.

Land-cover classification in a moist tropical region of Brazil with Landsat TM imagery.

PubMed

Li, Guiying; Lu, Dengsheng; Moran, Emilio; Hetrick, Scott

2011-01-01

This research aims to improve land-cover classification accuracy in a moist tropical region in Brazil by examining the use of different remote sensing-derived variables and classification algorithms. Different scenarios based on Landsat Thematic Mapper (TM) spectral data and derived vegetation indices and textural images, and different classification algorithms - maximum likelihood classification (MLC), artificial neural network (ANN), classification tree analysis (CTA), and object-based classification (OBC), were explored. The results indicated that a combination of vegetation indices as extra bands into Landsat TM multispectral bands did not improve the overall classification performance, but the combination of textural images was valuable for improving vegetation classification accuracy. In particular, the combination of both vegetation indices and textural images into TM multispectral bands improved overall classification accuracy by 5.6% and kappa coefficient by 6.25%. Comparison of the different classification algorithms indicated that CTA and ANN have poor classification performance in this research, but OBC improved primary forest and pasture classification accuracies. This research indicates that use of textural images or use of OBC are especially valuable for improving the vegetation classes such as upland and liana forest classes having complex stand structures and having relatively large patch sizes.

Land-cover classification in a moist tropical region of Brazil with Landsat TM imagery

PubMed Central

LI, GUIYING; LU, DENGSHENG; MORAN, EMILIO; HETRICK, SCOTT

2011-01-01

This research aims to improve land-cover classification accuracy in a moist tropical region in Brazil by examining the use of different remote sensing-derived variables and classification algorithms. Different scenarios based on Landsat Thematic Mapper (TM) spectral data and derived vegetation indices and textural images, and different classification algorithms – maximum likelihood classification (MLC), artificial neural network (ANN), classification tree analysis (CTA), and object-based classification (OBC), were explored. The results indicated that a combination of vegetation indices as extra bands into Landsat TM multispectral bands did not improve the overall classification performance, but the combination of textural images was valuable for improving vegetation classification accuracy. In particular, the combination of both vegetation indices and textural images into TM multispectral bands improved overall classification accuracy by 5.6% and kappa coefficient by 6.25%. Comparison of the different classification algorithms indicated that CTA and ANN have poor classification performance in this research, but OBC improved primary forest and pasture classification accuracies. This research indicates that use of textural images or use of OBC are especially valuable for improving the vegetation classes such as upland and liana forest classes having complex stand structures and having relatively large patch sizes. PMID:22368311

Mapping Successional Stages in a Wet Tropical Forest Using Landsat ETM+ and Forest Inventory Data

NASA Technical Reports Server (NTRS)

Goncalves, Fabio G.; Yatskov, Mikhail; dos Santos, Joao Roberto; Treuhaft, Robert N.; Law, Beverly E.

2010-01-01

In this study, we test whether an existing classification technique based on the integration of Landsat ETM+ and forest inventory data enables detailed characterization of successional stages in a wet tropical forest site. The specific objectives were: (1) to map forest age classes across the La Selva Biological Station in Costa Rica; and (2) to quantify uncertainties in the proposed approach in relation to field data and existing vegetation maps. Although significant relationships between vegetation height entropy (a surrogate for forest age) and ETM+ data were detected, the classification scheme tested in this study was not suitable for characterizing spatial variation in age at La Selva, as evidenced by the error matrix and the low Kappa coefficient (12.9%). Factors affecting the performance of the classification at this particular study site include the smooth transition in vegetation structure between intermediate and advanced successional stages, and the low sensitivity of NDVI to variations in vertical structure at high biomass levels.

Understanding ecosystem service preferences across residential classifications near Mt. Baker Snoqualmie National Forest, Washington (USA).

Treesearch

Katherine Williams; Kelly Biedenweg; Lee Cerveny

2017-01-01

Ecosystem services consistently group together both spatially and cognitively into “bundles”. Understanding socio-economic predictors of these bundles is essential to informing a management approach that emphasizes equitable distribution of ecosystem services. We received 1796 completed surveys from stakeholders of the Mt. Baker-Snoqualmie National Forest (WA, USA)...

Development of an ecological classification system for the Cooper Creek watershed of the Chattahoochee National Forest: a first approximation

Treesearch

W. Henry McNab; Ronald B. Stephens; Erika M. Mavity; Joanne E. Baggs; James M. Wentworth; Richard D. Rightmyer; Alex J. Jaume; Brian D. Jackson; Michael P. Joyce

2015-01-01

The 2004 management plan for the Chattahoochee National Forest states that many future resource objectives and goals have an ecological basis. Assessment of resource needs in the Cooper Creek watershed area of the southern Appalachian Mountains of north Georgia were identified with awareness of ecological constraints and suitability. An interdisciplinary team of...

Preliminary Evaluation of Methods for Classifying Forest Site Productivity Based on Species Composition in Western North Carolina

Treesearch

W. Henry McNab; F. Thomas Lloyd; David L. Loftis

2002-01-01

The species indicator approach to forest site classification was evaluated for 210 relatively undisturbed plots established by the USDA Forest Service Forest Inventory and Analysis uni (FIA) in western North Carolina. Plots were classified by low, medium, and high levels of productivity based on 10-year individual tree basal area increment data standardized for initial...

Using vegetation indices as input into ramdom forest for soybean and weed classification

USDA-ARS?s Scientific Manuscript database

Weed management is a major component of a soybean (Glycine max L.) production system; thus, managers need tools to help them distinguish soybean from weeds. Vegetation indices derived from light reflectance properties of plants have shown promise as tools to enhance differences among plants. The o...

Monitoring 2009 Forest Disturbance across the Conterminous United States, Based on Near-Real Time and Historical MODIS 250 Meter NDVI Products

NASA Astrophysics Data System (ADS)

Spruce, J.; Hargrove, W. W.; Gasser, G.; Smoot, J. C.; Kuper, P.

2009-12-01

This presentation discusses a study on the use of MODIS NDVI data for viewing regional patterns of forest disturbance across the conterminous United States. This capability is a part of a national forest threat early warning system (EWS) being developed by the USDA Forest Service’s Eastern and Western Environmental Threat Centers with help from NASA Stennis Space Center and the Oak Ridge National Laboratory. The viewing capability of the EWS was recently demonstrated for 2009, using near-real time (NRT) MODIS NDVI data from the USGS eMODIS Web site and historical NDVI data from standard MOD13 products. For this study, a historical maximum NDVI baseline for CONUS was computed from fused Aqua and Terra MOD13 data for June 10-July 27 of each year during 2000-2006. Comparable 2009 MODIS NDVI imagery was computed from fusion and re-compositing of eMODIS NRT Aqua and Terra 7-day products. For the historical data, time series data processing software was used to remove poor quality data and to mitigate data gaps mainly due to clouds. Although the NRT component was not as rigorously processed to mitigate noise, the processing still yielded largely cloud-free clean, coherent CONUS NDVI imagery initially with only 21-days of compositing. The principal end product of the study was a forest disturbance visualization product based on an NDVI RGB image that combines data from 2 dates (i.e. time frames). For this RGB, the historical maximum NDVI for the observed temporal window was assigned to the red color gun and the 2009 NRT product for the same time frame was assigned to the blue and green guns. The resulting image was masked with a USFS FIA 250-m type map to include only forested areas. The forest disturbance areas on the forest-masked 2-date NDVI RGB are shown in red tones with non-disturbed closed canopy forest generally shown in medium to bright gray tones. This product highlighted several broad-scaled forest canopy disturbances for the observed time in 2009, including damage from caterpillars, bark beetles, ice storms, hail and wind storms, and wildfire. The MODIS forest disturbance products compared well with reference data (e.g., Landsat, aerial sketch maps, and news accounts). These products have been useful in aiding development of the forest threat EWS. Information on location and extent of regional forest disturbance is important to Federal, State, and private sector forest managers. The 2-date RGB product for 2009 was also processed into a classification of forest disturbance for the Colorado Front Range. Validation of this classification is underway. Regional forest disturbance classifications in conjunction with available CONUS forest biomass products could be useful for assessing carbon impacts from biotic threats such as mountain pine beetle and from abiotic threats related to climate change. The latency of the NRT eMODIS products addresses an important need of the USFS EWS.

Sub-pixel image classification for forest types in East Texas

NASA Astrophysics Data System (ADS)

Westbrook, Joey

Sub-pixel classification is the extraction of information about the proportion of individual materials of interest within a pixel. Landcover classification at the sub-pixel scale provides more discrimination than traditional per-pixel multispectral classifiers for pixels where the material of interest is mixed with other materials. It allows for the un-mixing of pixels to show the proportion of each material of interest. The materials of interest for this study are pine, hardwood, mixed forest and non-forest. The goal of this project was to perform a sub-pixel classification, which allows a pixel to have multiple labels, and compare the result to a traditional supervised classification, which allows a pixel to have only one label. The satellite image used was a Landsat 5 Thematic Mapper (TM) scene of the Stephen F. Austin Experimental Forest in Nacogdoches County, Texas and the four cover type classes are pine, hardwood, mixed forest and non-forest. Once classified, a multi-layer raster datasets was created that comprised four raster layers where each layer showed the percentage of that cover type within the pixel area. Percentage cover type maps were then produced and the accuracy of each was assessed using a fuzzy error matrix for the sub-pixel classifications, and the results were compared to the supervised classification in which a traditional error matrix was used. The overall accuracy of the sub-pixel classification using the aerial photo for both training and reference data had the highest (65% overall) out of the three sub-pixel classifications. This was understandable because the analyst can visually observe the cover types actually on the ground for training data and reference data, whereas using the FIA (Forest Inventory and Analysis) plot data, the analyst must assume that an entire pixel contains the exact percentage of a cover type found in a plot. An increase in accuracy was found after reclassifying each sub-pixel classification from nine classes with 10 percent interval each to five classes with 20 percent interval each. When compared to the supervised classification which has a satisfactory overall accuracy of 90%, none of the sub-pixel classification achieved the same level. However, since traditional per-pixel classifiers assign only one label to pixels throughout the landscape while sub-pixel classifications assign multiple labels to each pixel, the traditional 85% accuracy of acceptance for pixel-based classifications should not apply to sub-pixel classifications. More research is needed in order to define the level of accuracy that is deemed acceptable for sub-pixel classifications.

A Multi-temporal Analysis of Logging Impacts on Tropical Forest Structure Using Airborne Lidar Data

NASA Astrophysics Data System (ADS)

Keller, M. M.; Pinagé, E. R.; Duffy, P.; Longo, M.; dos-Santos, M. N.; Leitold, V.; Morton, D. C.

2017-12-01

The long-term impacts of selective logging on carbon cycling and ecosystem function in tropical-forests are still uncertain. Despite improvements in selective logging detection using satellite data, quantifying changes in forest structure from logging and recovery following logging is difficult using orbital data. We analyzed the dynamics of forest structure comparing logged and unlogged forests in the Eastern Brazilian Amazon (Paragominas Municipality, Pará State) using small footprint discrete return airborne lidar data acquired in 2012 and 2014. Logging operations were conducted at the 1200 ha study site from 2006 through 2013 using reduced impact logging techniques—management practices that minimize canopy and ground damage compared to more common conventional logging. Nevertheless, logging still reduced aboveground biomass by 10% to 20% in logged areas compared to intact forests. We aggregated lidar point-cloud data at spatial scales ranging from 50 m to 250 m and developed a binomial classification model based on the height distribution of lidar returns in 2012 and validated the model against the 2014 lidar acquisition. We accurately classified intact and logged forest classes compared with field data. Classification performance improved as spatial resolution increased (AUC = 0.974 at 250 m). We analyzed the differences in canopy gaps, understory damage (based on a relative density model), and biomass (estimated from total canopy height) of intact and logged classes. As expected, logging greatly increased both canopy gap formation and understory damage. However, while the area identified as canopy gap persisted for at least 8 years (from the oldest logging treatments in 2006 to the most recent lidar acquisition in 2014), the effects of ground damage were mostly erased by vigorous understory regrowth after about 5 years. The rate of new gap formation was 6 to 7 times greater in recently logged forests compared to undisturbed forests. New gaps opened at a rate of 1.8 times greater than background even 8 years following logging demonstrating the occurrence of delayed tree mortality. Our study showed that even low-intensity anthropogenic disturbances can cause persistent changes in tropical forest structure and dynamics.

Hydrologic Landscape Regionalisation Using Deductive Classification and Random Forests

PubMed Central

Brown, Stuart C.; Lester, Rebecca E.; Versace, Vincent L.; Fawcett, Jonathon; Laurenson, Laurie

2014-01-01

Landscape classification and hydrological regionalisation studies are being increasingly used in ecohydrology to aid in the management and research of aquatic resources. We present a methodology for classifying hydrologic landscapes based on spatial environmental variables by employing non-parametric statistics and hybrid image classification. Our approach differed from previous classifications which have required the use of an a priori spatial unit (e.g. a catchment) which necessarily results in the loss of variability that is known to exist within those units. The use of a simple statistical approach to identify an appropriate number of classes eliminated the need for large amounts of post-hoc testing with different number of groups, or the selection and justification of an arbitrary number. Using statistical clustering, we identified 23 distinct groups within our training dataset. The use of a hybrid classification employing random forests extended this statistical clustering to an area of approximately 228,000 km2 of south-eastern Australia without the need to rely on catchments, landscape units or stream sections. This extension resulted in a highly accurate regionalisation at both 30-m and 2.5-km resolution, and a less-accurate 10-km classification that would be more appropriate for use at a continental scale. A smaller case study, of an area covering 27,000 km2, demonstrated that the method preserved the intra- and inter-catchment variability that is known to exist in local hydrology, based on previous research. Preliminary analysis linking the regionalisation to streamflow indices is promising suggesting that the method could be used to predict streamflow behaviour in ungauged catchments. Our work therefore simplifies current classification frameworks that are becoming more popular in ecohydrology, while better retaining small-scale variability in hydrology, thus enabling future attempts to explain and visualise broad-scale hydrologic trends at the scale of catchments and continents. PMID:25396410

Hydrologic landscape regionalisation using deductive classification and random forests.

PubMed

Brown, Stuart C; Lester, Rebecca E; Versace, Vincent L; Fawcett, Jonathon; Laurenson, Laurie

2014-01-01

Landscape classification and hydrological regionalisation studies are being increasingly used in ecohydrology to aid in the management and research of aquatic resources. We present a methodology for classifying hydrologic landscapes based on spatial environmental variables by employing non-parametric statistics and hybrid image classification. Our approach differed from previous classifications which have required the use of an a priori spatial unit (e.g. a catchment) which necessarily results in the loss of variability that is known to exist within those units. The use of a simple statistical approach to identify an appropriate number of classes eliminated the need for large amounts of post-hoc testing with different number of groups, or the selection and justification of an arbitrary number. Using statistical clustering, we identified 23 distinct groups within our training dataset. The use of a hybrid classification employing random forests extended this statistical clustering to an area of approximately 228,000 km2 of south-eastern Australia without the need to rely on catchments, landscape units or stream sections. This extension resulted in a highly accurate regionalisation at both 30-m and 2.5-km resolution, and a less-accurate 10-km classification that would be more appropriate for use at a continental scale. A smaller case study, of an area covering 27,000 km2, demonstrated that the method preserved the intra- and inter-catchment variability that is known to exist in local hydrology, based on previous research. Preliminary analysis linking the regionalisation to streamflow indices is promising suggesting that the method could be used to predict streamflow behaviour in ungauged catchments. Our work therefore simplifies current classification frameworks that are becoming more popular in ecohydrology, while better retaining small-scale variability in hydrology, thus enabling future attempts to explain and visualise broad-scale hydrologic trends at the scale of catchments and continents.

Multi-Level Wild Land Fire Fighting Management Support System for an Optimized Guidance of Ground and Air Forces

NASA Astrophysics Data System (ADS)

Almer, Alexander; Schnabel, Thomas; Perko, Roland; Raggam, Johann; Köfler, Armin; Feischl, Richard

2016-04-01

Climate change will lead to a dramatic increase in damage from forest fires in Europe by the end of this century. In the Mediterranean region, the average annual area affected by forest fires has quadrupled since the 1960s (WWF, 2012). The number of forest fires is also on the increase in Central and Northern Europe. The Austrian forest fire database shows a total of 584 fires for the period 2012 to 2014, while even large areas of Sweden were hit by forest fires in August 2014, which were brought under control only after two weeks of intense fire-fighting efforts supported by European civil protection modules. Based on these facts, the improvements in forest fire control are a major international issue in the quest to protect human lives and resources as well as to reduce the negative environmental impact of these fires to a minimum. Within this paper the development of a multi-functional airborne management support system within the frame of the Austrian national safety and security research programme (KIRAS) is described. The main goal of the developments is to assist crisis management tasks of civil emergency teams and armed forces in disaster management by providing multi spectral, near real-time airborne image data products. As time, flexibility and reliability as well as objective information are crucial aspects in emergency management, the used components are tailored to meet these requirements. An airborne multi-functional management support system was developed as part of the national funded project AIRWATCH, which enables real-time monitoring of natural disasters based on optical and thermal images. Airborne image acquisition, a broadband line of sight downlink and near real-time processing solutions allow the generation of an up-to-date geo-referenced situation map. Furthermore, this paper presents ongoing developments for innovative extensions and research activities designed to optimize command operations in national and international fire-fighting missions. The ongoing development focuses on the following topics: (1) Development of a multi-level management solution to coordinate and guide different airborne and terrestrial deployed firefighting modules as well as related data processing and data distribution activities. (2) Further, a targeted control of the thermal sensor based on a rotating mirror system to extend the "area performance" (covered area per hour) in time critical situations for the monitoring requirements during forest fire events. (3) Novel computer vision methods for analysis of thermal sensor signatures, which allow an automatic classification of different forest fire types and situations. (4) A module for simulation-based decision support for planning and evaluation of resource usage and the effectiveness of performed fire-fighting measures. (5) Integration of wearable systems to assist ground teams in rescue operations as well as a mobile information system into innovative command and fire-fighting vehicles. In addition, the paper gives an outlook on future perspectives including a first concept for the integration of the near real-time multilevel forest fire fighting management system into an "EU Civil Protection Team" to support the EU civil protection modules and the Emergency Response Coordination Centre in Brussels. Keywords: Airborne sensing, multi sensor imaging, near real-time fire monitoring, simulation-based decision support, forest firefighting management, firefighting impact analysis.

Discrimination of crop types with TerraSAR-X-derived information

NASA Astrophysics Data System (ADS)

Sonobe, Rei; Tani, Hiroshi; Wang, Xiufeng; Kobayashi, Nobuyuki; Shimamura, Hideki

Although classification maps are required for management and for the estimation of agricultural disaster compensation, those techniques have yet to be established. This paper describes the comparison of three different classification algorithms for mapping crops in Hokkaido, Japan, using TerraSAR-X (including TanDEM-X) dual-polarimetric data. In the study area, beans, beets, grasslands, maize, potatoes and winter wheat were cultivated. In this study, classification using TerraSAR-X-derived information was performed. Coherence values, polarimetric parameters and gamma nought values were also obtained and evaluated regarding their usefulness in crop classification. Accurate classification may be possible with currently existing supervised learning models. A comparison between the classification and regression tree (CART), support vector machine (SVM) and random forests (RF) algorithms was performed. Even though J-M distances were lower than 1.0 on all TerraSAR-X acquisition days, good results were achieved (e.g., separability between winter wheat and grass) due to the characteristics of the machine learning algorithm. It was found that SVM performed best, achieving an overall accuracy of 95.0% based on the polarimetric parameters and gamma nought values for HH and VV polarizations. The misclassified fields were less than 100 a in area and 79.5-96.3% were less than 200 a with the exception of grassland. When some feature such as a road or windbreak forest is present in the TerraSAR-X data, the ratio of its extent to that of the field is relatively higher for the smaller fields, which leads to misclassifications.

Land cover and forest formation distributions for St. Kitts, Nevis, St. Eustatius, Grenada and Barbados from decision tree classification of cloud-cleared satellite imagery

USGS Publications Warehouse

Helmer, E.H.; Kennaway, T.A.; Pedreros, D.H.; Clark, M.L.; Marcano-Vega, H.; Tieszen, L.L.; Ruzycki, T.R.; Schill, S.R.; Carrington, C.M.S.

2008-01-01

Satellite image-based mapping of tropical forests is vital to conservation planning. Standard methods for automated image classification, however, limit classification detail in complex tropical landscapes. In this study, we test an approach to Landsat image interpretation on four islands of the Lesser Antilles, including Grenada and St. Kitts, Nevis and St. Eustatius, testing a more detailed classification than earlier work in the latter three islands. Secondly, we estimate the extents of land cover and protected forest by formation for five islands and ask how land cover has changed over the second half of the 20th century. The image interpretation approach combines image mosaics and ancillary geographic data, classifying the resulting set of raster data with decision tree software. Cloud-free image mosaics for one or two seasons were created by applying regression tree normalization to scene dates that could fill cloudy areas in a base scene. Such mosaics are also known as cloud-filled, cloud-minimized or cloud-cleared imagery, mosaics, or composites. The approach accurately distinguished several classes that more standard methods would confuse; the seamless mosaics aided reference data collection; and the multiseason imagery allowed us to separate drought deciduous forests and woodlands from semi-deciduous ones. Cultivated land areas declined 60 to 100 percent from about 1945 to 2000 on several islands. Meanwhile, forest cover has increased 50 to 950%. This trend will likely continue where sugar cane cultivation has dominated. Like the island of Puerto Rico, most higher-elevation forest formations are protected in formal or informal reserves. Also similarly, lowland forests, which are drier forest types on these islands, are not well represented in reserves. Former cultivated lands in lowland areas could provide lands for new reserves of drier forest types. The land-use history of these islands may provide insight for planners in countries currently considering lowland forest clearing for agriculture. Copyright 2008 College of Arts and Sciences.

Wilderness ecology: a method of sampling and summarizing data for plant community classification.

Treesearch

Lewis F. Ohmann; Robert R. Ream

1971-01-01

Presents a flexible sampling scheme that researchers and land managers may use in surveying and classifying plant communities of forest lands. Includes methods, data sheets, and computer summarization printouts.

Improving classification accuracy using multi-date IRS/LISS data and development of thermal stress index for Asiatic lion habitat

NASA Astrophysics Data System (ADS)

Gupta, Rajendra Kumar

The increase in lion and leopard population in the GIR wild life sanctuary and National Park (Gir Protected Area) demands periodic and precision monitoring of habitat at close intervals using space based remote sensing data. Besides characterizing the different forest classes, remote sensing needs to support for the assessment of thermal stress zones and identification of possible corridors for lion dispersion to new home ranges. The study focuses on assessing the thematic forest classification accuracies in percentage terms(CA) attainable using single date post-monsoon (CA=60, kappa = 0.514) as well as leaf shedding (CA=48.4, kappa = 0.372) season data in visible and Near-IR spectral bands of IRS/LISS-III at 23.5 m spatial resolution; and improvement of CA by using joint two date (multi-temporal) data sets (CA=87.2, kappa = 0.843) in the classification. The 188 m spatial resolution IRS/WiFS and 23.5 m spatial resolution LISS-III data were used to study the possible corridors for dispersion of Lions from GIR protected areas (PA). A relative thermal stress index (RTSI) for Gir PA has been developed using NOAA/ AVHRR data sets of post-monsoon, leaf shedded and summer seasons. The paper discusses the role of RTSI as a tool to work out forest management plans using leaf shedded season data to combat the thermal stress in the habitat, by identifying locations for artificial water holes during the ensuing summer season.

Using a terrestrial ecosystem survey to estimate the historical density of ponderosa pine trees

Treesearch

Scott R. Abella; Charles W. Denton; David G. Brewer; Wayne A. Robbie; Rory W. Steinke; W. Wallace Covington

2011-01-01

Maps of historical tree densities for project areas and landscapes may be useful for a variety of management purposes such as determining site capabilities and planning forest thinning treatments. We used the U.S. Forest Service Region 3 terrestrial ecosystem survey in a novel way to determine if the ecosystem classification is a useful a guide for estimating...

Trail deterioration as an indicator of trail use in an urban forest recreation area

Treesearch

Thomas A. More

1980-01-01

The average width of a trail was used to predict trail use in an urban forest recreation area. Results show that width indicates use only very generally at best. Consequently, simply inspecting the physical condition of a trail may lead to erroneous conclusions about its use. Managers requiring more than a simple light use/heavy use classification should adopt more...

Forest type mapping with satellite data

NASA Technical Reports Server (NTRS)

Dodge, A. G., Jr.; Bryant, E. S.

1976-01-01

Computer classification of data from Landsat, an earth-orbiting satellite, has resulted in measurements and maps of forest types for two New Hampshire counties. The acreages of hardwood and softwood types and total forested areas compare favorably with Forest Service figures for the same areas. These techniques have advantages for field application, particularly in states having forest taxation laws based on general productivity.

Land cover change assessment using object-oriented classification based on image segmentation in the Binah river watershed (Togo and Benin)

NASA Astrophysics Data System (ADS)

Badjana, M. H.; Helmschrot, J.; Wala, K.; Flugel, W. A.; Afouda, A.; Akpagana, K.

2014-12-01

Assessing and monitoring land cover changes over time, especially in Sub-Saharan Africa characterized by both a high population growth and the highest rate of land degradation in the world is of high relevance for sustainable land management, water security and food production. In this study, land cover changes between 1972 and 2013 were investigated in the Binah river watershed (North of Togo and Benin) using advanced remote sensing and GIS technologies to support sustainable land and water resources management efforts. To this end, multi-temporal satellite images - Landsat MSS (1972), TM (1987) and ETM+ (2013) were processed using object-oriented classification based on image segmentation and post-classification comparison methods. Five main land cover classes namely agricultural land, forest land, savannah, settlements and water bodies have been identified with overall accuracies of 75.11% (1972), 81.82% (1987), and 86.1% (2013) and respective Kappa statistics of 0.67, 0.76 and 0.83. These classification results helped to explicitly assess the spatio-temporal pattern of land cover within the basin. The results indicate that savannah as the main vegetation type in the basin has decreased from 63.3% of the basin area in 1972 to 60.4% in 1987 and 35.6% in 2013. Also the forest land which covered 20.7% in 1972 has decreased to 12.7% in 1987 and 11.7% in 2013. This severe decrease in vegetation mainly resulted from the extension of agricultural areas and settlements, which is, thus, considered as the main driving force. In fact, agricultural land increased of 61.4% from 1972 to 1987, 81.4% from 1987 to 2013 and almost twice from 1972 to 2013 while human settlements increased from 0.8% of the basin area in 1972 to 2.5% in 1987 and 7.7% in 2013. The transition maps illustrate the conversion of savannah to agricultural land at each time step relating to slash and burn agriculture, but also demonstrate the threat of environmental degradation of the savannah biome. However, at the same time, some proportions of agricultural land were converted to savannah relating to fallow agriculture. As a first assessment for the Binah river watershed, this study provides useful guidelines for vegetation restoration and conservation, efforts in managing land degradation and implementing integrated land and water resources management plans.

Land Covers Classification Based on Random Forest Method Using Features from Full-Waveform LIDAR Data

NASA Astrophysics Data System (ADS)

Ma, L.; Zhou, M.; Li, C.

2017-09-01

In this study, a Random Forest (RF) based land covers classification method is presented to predict the types of land covers in Miyun area. The returned full-waveforms which were acquired by a LiteMapper 5600 airborne LiDAR system were processed, including waveform filtering, waveform decomposition and features extraction. The commonly used features that were distance, intensity, Full Width at Half Maximum (FWHM), skewness and kurtosis were extracted. These waveform features were used as attributes of training data for generating the RF prediction model. The RF prediction model was applied to predict the types of land covers in Miyun area as trees, buildings, farmland and ground. The classification results of these four types of land covers were obtained according to the ground truth information acquired from CCD image data of the same region. The RF classification results were compared with that of SVM method and show better results. The RF classification accuracy reached 89.73% and the classification Kappa was 0.8631.

Mapping forest functional type in a forest-shrubland ecotone using SPOT imagery and predictive habitat distribution modelling

USGS Publications Warehouse

Assal, Timothy J.; Anderson, Patrick J.; Sibold, Jason

2015-01-01

The availability of land cover data at local scales is an important component in forest management and monitoring efforts. Regional land cover data seldom provide detailed information needed to support local management needs. Here we present a transferable framework to model forest cover by major plant functional type using aerial photos, multi-date Système Pour l’Observation de la Terre (SPOT) imagery, and topographic variables. We developed probability of occurrence models for deciduous broad-leaved forest and needle-leaved evergreen forest using logistic regression in the southern portion of the Wyoming Basin Ecoregion. The model outputs were combined into a synthesis map depicting deciduous and coniferous forest cover type. We evaluated the models and synthesis map using a field-validated, independent data source. Results showed strong relationships between forest cover and model variables, and the synthesis map was accurate with an overall correct classification rate of 0.87 and Cohen’s kappa value of 0.81. The results suggest our method adequately captures the functional type, size, and distribution pattern of forest cover in a spatially heterogeneous landscape.

Forest Ecosystem Services and Eco-Compensation Mechanisms in China

NASA Astrophysics Data System (ADS)

Deng, Hongbing; Zheng, Peng; Liu, Tianxing; Liu, Xin

2011-12-01

Forests are a major terrestrial ecosystem providing multiple ecosystem services. However, the importance of forests is frequently underestimated from an economic perspective because of the externalities and public good properties of these services. Forest eco-compensation is a transfer mechanism that serves to internalize the externalities of forest ecosystem services by compensating individuals or companies for the losses or costs resulting from the provision of these services. China's current forest eco-compensation system is centered mainly on noncommercial forest. The primary measures associated with ecosystem services are (1) a charge on destructive activities, such as indiscriminate logging, and (2) compensation for individual or local activities and investments in forest conservation. The Compensation Fund System for Forest Ecological Benefits was first listed in the Forest Law of the People's Republic of China in 1998. In 2004, the Central Government Financial Compensation Fund, an important source for the Compensation Fund for Forest Ecological Benefits, was formally established. To improve the forest eco-compensation system, it is crucial to design and establish compensation criteria for noncommercial forests. These criteria should take both theoretical and practical concerns into account, and they should be based on the quantitative valuation of ecosystem services. Although some initial headway has been made on this task, the implementation of an effective forest eco-compensation system in China still has deficiencies and still faces problems. Implementing classification-based and dynamic management for key noncommercial forests and establishing an eco-compensation mechanism with multiple funding sources in the market economy are the key measures needed to conquer these problems and improve the forest eco-compensation system and China's forestry development in sequence.

Landscape risk factors for Lyme disease in the eastern broadleaf forest province of the Hudson River valley and the effect of explanatory data classification resolution.

PubMed

Messier, Kyle P; Jackson, Laura E; White, Jennifer L; Hilborn, Elizabeth D

2015-01-01

This study assessed how landcover classification affects associations between landscape characteristics and Lyme disease rate. Landscape variables were derived from the National Land Cover Database (NLCD), including native classes (e.g., deciduous forest, developed low intensity) and aggregate classes (e.g., forest, developed). Percent of each landcover type, median income, and centroid coordinates were calculated by census tract. Regression results from individual and aggregate variable models were compared with the dispersion parameter-based R(2) (Rα(2)) and AIC. The maximum Rα(2) was 0.82 and 0.83 for the best aggregate and individual model, respectively. The AICs for the best models differed by less than 0.5%. The aggregate model variables included forest, developed, agriculture, agriculture-squared, y-coordinate, y-coordinate-squared, income and income-squared. The individual model variables included deciduous forest, deciduous forest-squared, developed low intensity, pasture, y-coordinate, y-coordinate-squared, income, and income-squared. Results indicate that regional landscape models for Lyme disease rate are robust to NLCD landcover classification resolution. Published by Elsevier Ltd.

Remote sensing change detection methods to track deforestation and growth in threatened rainforests in Madre de Dios, Peru

USGS Publications Warehouse

Shermeyer, Jacob S.; Haack, Barry N.

2015-01-01

Two forestry-change detection methods are described, compared, and contrasted for estimating deforestation and growth in threatened forests in southern Peru from 2000 to 2010. The methods used in this study rely on freely available data, including atmospherically corrected Landsat 5 Thematic Mapper and Moderate Resolution Imaging Spectroradiometer (MODIS) vegetation continuous fields (VCF). The two methods include a conventional supervised signature extraction method and a unique self-calibrating method called MODIS VCF guided forest/nonforest (FNF) masking. The process chain for each of these methods includes a threshold classification of MODIS VCF, training data or signature extraction, signature evaluation, k-nearest neighbor classification, analyst-guided reclassification, and postclassification image differencing to generate forest change maps. Comparisons of all methods were based on an accuracy assessment using 500 validation pixels. Results of this accuracy assessment indicate that FNF masking had a 5% higher overall accuracy and was superior to conventional supervised classification when estimating forest change. Both methods succeeded in classifying persistently forested and nonforested areas, and both had limitations when classifying forest change.

Evolving forest fire burn severity classification algorithms for multispectral imagery

NASA Astrophysics Data System (ADS)

Brumby, Steven P.; Harvey, Neal R.; Bloch, Jeffrey J.; Theiler, James P.; Perkins, Simon J.; Young, Aaron C.; Szymanski, John J.

2001-08-01

Between May 6 and May 18, 2000, the Cerro Grande/Los Alamos wildfire burned approximately 43,000 acres (17,500 ha) and 235 residences in the town of Los Alamos, NM. Initial estimates of forest damage included 17,000 acres (6,900 ha) of 70-100% tree mortality. Restoration efforts following the fire were complicated by the large scale of the fire, and by the presence of extensive natural and man-made hazards. These conditions forced a reliance on remote sensing techniques for mapping and classifying the burn region. During and after the fire, remote-sensing data was acquired from a variety of aircraft-based and satellite-based sensors, including Landsat 7. We now report on the application of a machine learning technique, implemented in a software package called GENIE, to the classification of forest fire burn severity using Landsat 7 ETM+ multispectral imagery. The details of this automatic classification are compared to the manually produced burn classification, which was derived from field observations and manual interpretation of high-resolution aerial color/infrared photography.

Developing New Coastal Forest Restoration Products Based on Landsat, ASTER, and MODIS Data

DTIC Science & Technology

2010-06-01

hydrology, wildfire, and conversion to non-forest land use. In some cases, such forest disturbance has led to forest loss or loss of regeneration capacity...classification of bald cypress and tupelo gum trees in Thematic Mapper imagery,” Photogrammetric Engineering and Remote Sensing, vol. 63, pp. 717–725, 1997. [14

A mangrove forest map of China in 2015: Analysis of time series Landsat 7/8 and Sentinel-1A imagery in Google Earth Engine cloud computing platform

NASA Astrophysics Data System (ADS)

Chen, Bangqian; Xiao, Xiangming; Li, Xiangping; Pan, Lianghao; Doughty, Russell; Ma, Jun; Dong, Jinwei; Qin, Yuanwei; Zhao, Bin; Wu, Zhixiang; Sun, Rui; Lan, Guoyu; Xie, Guishui; Clinton, Nicholas; Giri, Chandra

2017-09-01

Due to rapid losses of mangrove forests caused by anthropogenic disturbances and climate change, accurate and contemporary maps of mangrove forests are needed to understand how mangrove ecosystems are changing and establish plans for sustainable management. In this study, a new classification algorithm was developed using the biophysical characteristics of mangrove forests in China. More specifically, these forests were mapped by identifying: (1) greenness, canopy coverage, and tidal inundation from time series Landsat data, and (2) elevation, slope, and intersection-with-sea criterion. The annual mean Normalized Difference Vegetation Index (NDVI) was found to be a key variable in determining the classification thresholds of greenness, canopy coverage, and tidal inundation of mangrove forests, which are greatly affected by tide dynamics. In addition, the integration of Sentinel-1A VH band and modified Normalized Difference Water Index (mNDWI) shows great potential in identifying yearlong tidal and fresh water bodies, which is related to mangrove forests. This algorithm was developed using 6 typical Regions of Interest (ROIs) as algorithm training and was run on the Google Earth Engine (GEE) cloud computing platform to process 1941 Landsat images (25 Path/Row) and 586 Sentinel-1A images circa 2015. The resultant mangrove forest map of China at 30 m spatial resolution has an overall/users/producer's accuracy greater than 95% when validated with ground reference data. In 2015, China's mangrove forests had a total area of 20,303 ha, about 92% of which was in the Guangxi Zhuang Autonomous Region, Guangdong, and Hainan Provinces. This study has demonstrated the potential of using the GEE platform, time series Landsat and Sentine-1A SAR images to identify and map mangrove forests along the coastal zones. The resultant mangrove forest maps are likely to be useful for the sustainable management and ecological assessments of mangrove forests in China.

Classification and evaluation for forest sites on the Northern Cumberland Plateau

Treesearch

Glendon W. Smalley

1986-01-01

Presents a comprehensive forest site classifictation system for the North Cumberland Plateau in north-central Tennessee and eastern Kentucky. The system is based on physiograhpy, geology, soils, topography, and vegetation.

Land cover's refined classification based on multi source of remote sensing information fusion: a case study of national geographic conditions census in China

NASA Astrophysics Data System (ADS)

Cheng, Tao; Zhang, Jialong; Zheng, Xinyan; Yuan, Rujin

2018-03-01

The project of The First National Geographic Conditions Census developed by Chinese government has designed the data acquisition content and indexes, and has built corresponding classification system mainly based on the natural property of material. However, the unified standard for land cover classification system has not been formed; the production always needs converting to meet the actual needs. Therefore, it proposed a refined classification method based on multi source of remote sensing information fusion. It takes the third-level classes of forest land and grassland for example, and has collected the thematic data of Vegetation Map of China (1:1,000,000), attempts to develop refined classification utilizing raster spatial analysis model. Study area is selected, and refined classification is achieved by using the proposed method. The results show that land cover within study area is divided principally among 20 classes, from subtropical broad-leaved forest (31131) to grass-forb community type of low coverage grassland (41192); what's more, after 30 years in the study area, climatic factors, developmental rhythm characteristics and vegetation ecological geographical characteristics have not changed fundamentally, only part of the original vegetation types have changed in spatial distribution range or land cover types. Research shows that refined classification for the third-level classes of forest land and grassland could make the results take on both the natural attributes of the original and plant community ecology characteristics, which could meet the needs of some industry application, and has certain practical significance for promoting the product of The First National Geographic Conditions Census.

How extreme weather events can influence the way of thinking about forest management?

NASA Astrophysics Data System (ADS)

Ziemblińska, Klaudia; Merbold, Lutz; Urbaniak, Marek; Haeni, Matthias; Olejnik, Janusz

2014-05-01

One third of the total area of Poland, which is covered by forests, is currently managed by "The State National Forest Holding" - the biggest organization in Europe managing forests. Common management practice is based on clear-cutting the vegetation to maintaining forests and ensuring regrowth. While sufficient information exists on the quantity of harvested biomass and particularly its economic value, little knowledge exists on the overall environmental impact of such management including the carbon budgets of forests in Poland. At the same time these forests are very vulnerable to extreme events such as wind throws. Large wind throws can be used as an experimental platform to study both, the effects of extreme events itself but also the effects of management such as clear-cuts, due to the fact that after such kind of natural disasters similar steps then following clear-cuts are implemented. These activities include the removal of whole trees, collection of branches and pulling out stems with heavy machinery, causing additional disturbance. In this study, we aim at providing information to fill the current knowledge gap of changing C budget after clear-cuts and wind throws. We hypothesize large C losses after clear-cuts and ask whether one can improve current forest management to "save" C and/or enhance C sequestration? To answer this specific question we used the eddy covariance (EC) method to adequately measure the net ecosystem exchange of carbon dioxide (NEE) between a deforested area and the atmosphere (treatment) and compare it to measurements from an intact forest of the same type (control). Both sites have the same soil type (brunic arenosoil - after FAO classification) which is sandy and relatively not fertile. Moreover, main species and composition were similar. The treatment area was chosen after the occurrence of a 20min-lasting tornado in July 2012 in Western Poland. The storm resulted in the destruction of more than 500 ha of 75-year old pine forest and provided a unique situation to assess the C budget of a pine forest after wind throw leading to the construction of the Trzebciny EC tower (treatment site). Measurements of CO2 and H2O exchange continue since the beginning of 2013. Measurements from both sites were directly compared to an already established monitoring station (65-year old Tuczno forest, control). We observed a huge difference in NEE between an intact middle age coniferous forest (control site, net gain of 463 g(C-CO2) m-2 in 2013) and an area of similar forest that was destroyed by a tornado and cleared thereafter (treatment site, net loss of about 518 g(C-CO2) m-2 in 2013). Our results provide a great opportunity to re-evaluate current forest management in Poland and will provide a first step towards adjusting forestry management and policy to become less susceptible to climate change (especially extreme events).

Characterization and spatial distribution of mangrove forest types based on ALOS-PALSAR mosaic 25m-resolution in Southeast Asia

NASA Astrophysics Data System (ADS)

Darmawan, S.; Takeuchi, W.; Nakazono, E.; Parwati, E.; Dien, V. T.; Oo, K. S.; Wikantika, K.; Sari, D. K.

2016-06-01

The objective of this research is to investigate characteristics of mangrove forest types and to identify spatial distribution of mangrove forest based on ALOS PALSAR mosaic 25m- resolution in Southeast Asia. Methodology consists of collecting of ALOS PALSAR image for overall Southeast Asia region, preprocessing include converting DN to NRCS and filtering, collecting regions of interest of mangrove forest in Southeast Asia, plotting, characterization and classification. Result on this research we found characteristics of mangrove forest on HH values around -10.88 dB to -6.65 dB and on HV value around -16.49 dB to -13.26 dB. On polarization of HH which the highest backscattering value is mangrove forest in Preak Piphot River Cambodia, Thái Thủy Thai Binh Vietnam, and Vạn Ninh tp. Móng Cái Quảng Ninh Vietnam whereas the lowest backscattering value is mangrove forest in Thailand area. On polarization of HV which the highest backscattering value is mangrove forest in Preak Piphot River Cambodia, Sorong and Teluk Bintuni Indonesia whereas the lowest backscattering value is mangrove forest in Subang Indonesia, Giao Thiện Giao Thuỷ Nam Định, Vietnam and Puyu Mueng Satun Thailand. Based on characterization, we create a rule criteria for classification of mangrove areas and non mangrove area. Finally we found spatial distribution of mangrove forest based on ALOS PALSAR 25m-resolution in Southeast Asia.

A learning scheme for reach to grasp movements: on EMG-based interfaces using task specific motion decoding models.

PubMed

Liarokapis, Minas V; Artemiadis, Panagiotis K; Kyriakopoulos, Kostas J; Manolakos, Elias S

2013-09-01

A learning scheme based on random forests is used to discriminate between different reach to grasp movements in 3-D space, based on the myoelectric activity of human muscles of the upper-arm and the forearm. Task specificity for motion decoding is introduced in two different levels: Subspace to move toward and object to be grasped. The discrimination between the different reach to grasp strategies is accomplished with machine learning techniques for classification. The classification decision is then used in order to trigger an EMG-based task-specific motion decoding model. Task specific models manage to outperform "general" models providing better estimation accuracy. Thus, the proposed scheme takes advantage of a framework incorporating both a classifier and a regressor that cooperate advantageously in order to split the task space. The proposed learning scheme can be easily used to a series of EMG-based interfaces that must operate in real time, providing data-driven capabilities for multiclass problems, that occur in everyday life complex environments.

Vegetation and soils

USGS Publications Warehouse

Burke, M.K.; King, S.L.; Eisenbies, M.H.; Gartner, D.

2000-01-01

Intro paragraph: Characterization of bottomland hardwood vegetation in relatively undisturbed forests can provide critical information for developing effective wetland creation and restoration techniques and for assessing the impacts of management and development. Classification is a useful technique in characterizing vegetation because it summarizes complex data sets, assists in hypothesis generation about factors influencing community variation, and helps refine models of community structure. Hierarchical classification of communities is particularly useful for showing relationships among samples (Gauche 1982).

A novel transferable individual tree crown delineation model based on Fishing Net Dragging and boundary classification

NASA Astrophysics Data System (ADS)

Liu, Tao; Im, Jungho; Quackenbush, Lindi J.

2015-12-01

This study provides a novel approach to individual tree crown delineation (ITCD) using airborne Light Detection and Ranging (LiDAR) data in dense natural forests using two main steps: crown boundary refinement based on a proposed Fishing Net Dragging (FiND) method, and segment merging based on boundary classification. FiND starts with approximate tree crown boundaries derived using a traditional watershed method with Gaussian filtering and refines these boundaries using an algorithm that mimics how a fisherman drags a fishing net. Random forest machine learning is then used to classify boundary segments into two classes: boundaries between trees and boundaries between branches that belong to a single tree. Three groups of LiDAR-derived features-two from the pseudo waveform generated along with crown boundaries and one from a canopy height model (CHM)-were used in the classification. The proposed ITCD approach was tested using LiDAR data collected over a mountainous region in the Adirondack Park, NY, USA. Overall accuracy of boundary classification was 82.4%. Features derived from the CHM were generally more important in the classification than the features extracted from the pseudo waveform. A comprehensive accuracy assessment scheme for ITCD was also introduced by considering both area of crown overlap and crown centroids. Accuracy assessment using this new scheme shows the proposed ITCD achieved 74% and 78% as overall accuracy, respectively, for deciduous and mixed forest.

Leave islands as refugia for low-mobility species in managed forest mosaics

Treesearch

Stephanie J. Wessell-Kelly; Deanna H. Olson

2013-01-01

In recent years, forest management in the Pacifi c Northwest has shifted from one based largely on resource extraction to one based on ecosystem management principles. Forest management based on these principles involves simultaneously balancing and sustaining multiple forest resource values, including silvicultural, social, economic, and ecological objectives. Leave...

Mapping the temporary and perennial character of whole river networks

NASA Astrophysics Data System (ADS)

González-Ferreras, A. M.; Barquín, J.

2017-08-01

Knowledge of the spatial distribution of temporary and perennial river channels in a whole catchment is important for effective integrated basin management and river biodiversity conservation. However, this information is usually not available or is incomplete. In this study, we present a statistically based methodology to classify river segments from a whole river network (Deva-Cares catchment, Northern Spain) as temporary or perennial. This method is based on an a priori classification of a subset of river segments as temporary or perennial, using field surveys and aerial images, and then running Random Forest models to predict classification membership for the rest of the river network. The independent variables and the river network were derived following a computer-based geospatial simulation of riverine landscapes. The model results show high values of overall accuracy, sensitivity, and specificity for the evaluation of the fitted model to the training and testing data set (≥0.9). The most important independent variables were catchment area, area occupied by broadleaf forest, minimum monthly precipitation in August, and average catchment elevation. The final map shows 7525 temporary river segments (1012.5 km) and 3731 perennial river segments (662.5 km). A subsequent validation of the mapping results using River Habitat Survey data and expert knowledge supported the validity of the proposed maps. We conclude that the proposed methodology is a valid method for mapping the limits of flow permanence that could substantially increase our understanding of the spatial links between terrestrial and aquatic interfaces, improving the research, management, and conservation of river biodiversity and functioning.

A structural classification for inland northwest forest vegetation.

Treesearch

Kevin L. O' Hara; Penelope A. Latham; Paul Hessburg; Bradley G. Smith

1996-01-01

Existing approaches to vegetation classification range from those bassed on potential vegetation to others based on existing vegetation composition, or existing structural or physiognomic characteristics. Examples of these classifications are numerous, and in some cases, date back hundreds of years (Mueller-Dumbois and Ellenberg 1974). Small-scale or stand level...

Predicting tree species presence and basal area in Utah: A comparison of stochastic gradient boosting, generalized additive models, and tree-based methods

Treesearch

Gretchen G. Moisen; Elizabeth A. Freeman; Jock A. Blackard; Tracey S. Frescino; Niklaus E. Zimmermann; Thomas C. Edwards

2006-01-01

Many efforts are underway to produce broad-scale forest attribute maps by modelling forest class and structure variables collected in forest inventories as functions of satellite-based and biophysical information. Typically, variants of classification and regression trees implemented in Rulequest's© See5 and Cubist (for binary and continuous responses,...

Analyzing riparian forest cover changes along the Firniz River in the Mediterranean City of Kahramanmaras in Turkey.

PubMed

Akay, Abdullah E; Sivrikaya, Fatih; Gulci, Sercan

2014-05-01

Riparian forests adjacent to surface water are important transitional zones which maintain and enrich biodiversity and ensure the sustainability in a forest ecosystem. Also, riparian forests maintain water quality, reduce sediment delivery, enhance habitat areas for aquatic life and wildlife, and provide ecological corridors between the upland and the downstream. However, the riparian ecosystems have been degraded mainly due to human development, forest operations, and agricultural activities. In order to evaluate the impacts of these factors on riparian forests, it is necessary to estimate trends in forest cover changes. This study aims to analyze riparian forest cover changes along the Firniz River located in Mediterranean city of Kahramanmaras in Turkey. Changes in riparian forest cover from 1989 to 2010 have been determined by implementing supervised classification method on a series of Landsat TM imagery of the study area. The results indicated that the classification process applied on 1989 and 2010 images provided overall accuracy of 80.08 and 75 %, respectively. It was found that the most common land use class within the riparian zone was productive forest, followed by degraded forest, agricultural areas, and other land use classes. The results also indicated that the areas of degraded forest and forest openings increased, while productive forest and agricultural areas decreased between the years of 1989 and 2010. The amount of agricultural areas decreased due to the reduction in the population of rural people. According to these results, it can be concluded that special forest management and operation techniques should be implemented to restore the forest ecosystem in riparian areas.

Object based technique for delineating and mapping 15 tree species using VHR WorldView-2 imagery

NASA Astrophysics Data System (ADS)

Mustafa, Yaseen T.; Habeeb, Hindav N.

2014-10-01

Monitoring and analyzing forests and trees are required task to manage and establish a good plan for the forest sustainability. To achieve such a task, information and data collection of the trees are requested. The fastest way and relatively low cost technique is by using satellite remote sensing. In this study, we proposed an approach to identify and map 15 tree species in the Mangish sub-district, Kurdistan Region-Iraq. Image-objects (IOs) were used as the tree species mapping unit. This is achieved using the shadow index, normalized difference vegetation index and texture measurements. Four classification methods (Maximum Likelihood, Mahalanobis Distance, Neural Network, and Spectral Angel Mapper) were used to classify IOs using selected IO features derived from WorldView-2 imagery. Results showed that overall accuracy was increased 5-8% using the Neural Network method compared with other methods with a Kappa coefficient of 69%. This technique gives reasonable results of various tree species classifications by means of applying the Neural Network method with IOs techniques on WorldView-2 imagery.

Aspen biology, community classification, and management in the Blue Mountains

Treesearch

David K. Swanson; Craig L. Schmitt; Diane M. Shirley; Vicky Erickson; Kenneth J. Schuetz; Michael L. Tatum; David C. Powell

2010-01-01

Quaking aspen (Populus tremuloides Michx.) is a valuable species that is declining in the Blue Mountains of northeastern Oregon. This publication is a compilation of over 20 years of aspen management experience by USDA Forest Service workers in the Blue Mountains. It includes a summary of aspen biology and occurrence in the Blue Mountains, and a...

Mapping forest tree species over large areas with partially cloudy Landsat imagery

NASA Astrophysics Data System (ADS)

Turlej, K.; Radeloff, V.

2017-12-01

Forests provide numerous services to natural systems and humankind, but which services forest provide depends greatly on their tree species composition. That makes it important to track not only changes in forest extent, something that remote sensing excels in, but also to map tree species. The main goal of our work was to map tree species with Landsat imagery, and to identify how to maximize mapping accuracy by including partially cloudy imagery. Our study area covered one Landsat footprint (26/28) in Northern Wisconsin, USA, with temperate and boreal forests. We selected this area because it contains numerous tree species and variable forest composition providing an ideal study area to test the limits of Landsat data. We quantified how species-level classification accuracy was affected by a) the number of acquisitions, b) the seasonal distribution of observations, and c) the amount of cloud contamination. We classified a single year stack of Landsat-7, and -8 images data with a decision tree algorithm to generate a map of dominant tree species at the pixel- and stand-level. We obtained three important results. First, we achieved producer's accuracies in the range 70-80% and user's accuracies in range 80-90% for the most abundant tree species in our study area. Second, classification accuracy improved with more acquisitions, when observations were available from all seasons, and is the best when images with up to 40% cloud cover are included. Finally, classifications for pure stands were 10 to 30 percentage points better than those for mixed stands. We conclude that including partially cloudy Landsat imagery allows to map forest tree species with accuracies that were previously only possible for rare years with many cloud-free observations. Our approach thus provides important information for both forest management and science.

The application of LANDSAT remote sensing technology to natural resources management. Section 1: Introduction to VICAR - Image classification module. Section 2: Forest resource assessment of Humboldt County.

NASA Technical Reports Server (NTRS)

Fox, L., III (Principal Investigator); Mayer, K. E.

1980-01-01

A teaching module on image classification procedures using the VICAR computer software package was developed to optimize the training benefits for users of the VICAR programs. The field test of the module is discussed. An intensive forest land inventory strategy was developed for Humboldt County. The results indicate that LANDSAT data can be computer classified to yield site specific forest resource information with high accuracy (82%). The "Douglas-fir 80%" category was found to cover approximately 21% of the county and "Mixed Conifer 80%" covering about 13%. The "Redwood 80%" resource category, which represented dense old growth trees as well as large second growth, comprised 4.0% of the total vegetation mosaic. Furthermore, the "Brush" and "Brush-Regeneration" categories were found to be a significant part of the vegetative community, with area estimates of 9.4 and 10.0%.

Forest Stand Segmentation Using Airborne LIDAR Data and Very High Resolution Multispectral Imagery

NASA Astrophysics Data System (ADS)

Dechesne, Clément; Mallet, Clément; Le Bris, Arnaud; Gouet, Valérie; Hervieu, Alexandre

2016-06-01

Forest stands are the basic units for forest inventory and mapping. Stands are large forested areas (e.g., ≥ 2 ha) of homogeneous tree species composition. The accurate delineation of forest stands is usually performed by visual analysis of human operators on very high resolution (VHR) optical images. This work is highly time consuming and should be automated for scalability purposes. In this paper, a method based on the fusion of airborne laser scanning data (or lidar) and very high resolution multispectral imagery for automatic forest stand delineation and forest land-cover database update is proposed. The multispectral images give access to the tree species whereas 3D lidar point clouds provide geometric information on the trees. Therefore, multi-modal features are computed, both at pixel and object levels. The objects are individual trees extracted from lidar data. A supervised classification is performed at the object level on the computed features in order to coarsely discriminate the existing tree species in the area of interest. The analysis at tree level is particularly relevant since it significantly improves the tree species classification. A probability map is generated through the tree species classification and inserted with the pixel-based features map in an energetical framework. The proposed energy is then minimized using a standard graph-cut method (namely QPBO with α-expansion) in order to produce a segmentation map with a controlled level of details. Comparison with an existing forest land cover database shows that our method provides satisfactory results both in terms of stand labelling and delineation (matching ranges between 94% and 99%).

Object-Based Land Use Classification of Agricultural Land by Coupling Multi-Temporal Spectral Characteristics and Phenological Events in Germany

NASA Astrophysics Data System (ADS)

Knoefel, Patrick; Loew, Fabian; Conrad, Christopher

2015-04-01

Crop maps based on classification of remotely sensed data are of increased attendance in agricultural management. This induces a more detailed knowledge about the reliability of such spatial information. However, classification of agricultural land use is often limited by high spectral similarities of the studied crop types. More, spatially and temporally varying agro-ecological conditions can introduce confusion in crop mapping. Classification errors in crop maps in turn may have influence on model outputs, like agricultural production monitoring. One major goal of the PhenoS project ("Phenological structuring to determine optimal acquisition dates for Sentinel-2 data for field crop classification"), is the detection of optimal phenological time windows for land cover classification purposes. Since many crop species are spectrally highly similar, accurate classification requires the right selection of satellite images for a certain classification task. In the course of one growing season, phenological phases exist where crops are separable with higher accuracies. For this purpose, coupling of multi-temporal spectral characteristics and phenological events is promising. The focus of this study is set on the separation of spectrally similar cereal crops like winter wheat, barley, and rye of two test sites in Germany called "Harz/Central German Lowland" and "Demmin". However, this study uses object based random forest (RF) classification to investigate the impact of image acquisition frequency and timing on crop classification uncertainty by permuting all possible combinations of available RapidEye time series recorded on the test sites between 2010 and 2014. The permutations were applied to different segmentation parameters. Then, classification uncertainty was assessed and analysed, based on the probabilistic soft-output from the RF algorithm at the per-field basis. From this soft output, entropy was calculated as a spatial measure of classification uncertainty. The results indicate that uncertainty estimates provide a valuable addition to traditional accuracy assessments and helps the user to allocate error in crop maps.

Vegetation and Soils

Treesearch

Sammy L. King; Mark H. Eisenbies; David Gartner

2000-01-01

Characterization of bottomland hardwood vegetation in relatively undisturbed forests can provide critical information for developing effective wetland creation and restoration techniques and for assessing the impacts of management and development. Classification is a useful technique in characterizing vegetation because it summarizes complex data sets, assists in...

Headwater streams and forest management: does ecoregional context influence logging effects on benthic communities?

USGS Publications Warehouse

Medhurst, R. Bruce; Wipfli, Mark S.; Binckley, Chris; Polivka, Karl; Hessburg, Paul F.; Salter, R. Brion

2010-01-01

Effects of forest management on stream communities have been widely documented, but the role that climate plays in the disturbance outcomes is not understood. In order to determine whether the effect of disturbance from forest management on headwater stream communities varies by climate, we evaluated benthic macroinvertebrate communities in 24 headwater streams that differed in forest management (logged-roaded vs. unlogged-unroaded, hereafter logged and unlogged) within two ecological sub-regions (wet versus dry) within the eastern Cascade Range, Washington, USA. In both ecoregions, total macroinvertebrate density was highest at logged sites (P = 0.001) with gathering-collectors and shredders dominating. Total taxonomic richness and diversity did not differ between ecoregions or forest management types. Shredder densities were positively correlated with total deciduous and Sitka alder (Alnus sinuata) riparian cover. Further, differences in shredder density between logged and unlogged sites were greater in the wet ecoregion (logging × ecoregion interaction; P = 0.006) suggesting that differences in post-logging forest succession between ecoregions were responsible for differences in shredder abundance. Headwater stream benthic community structure was influenced by logging and regional differences in climate. Future development of ecoregional classification models at the subbasin scale, and use of functional metrics in addition to structural metrics, may allow for more accurate assessments of anthropogenic disturbances in mountainous regions where mosaics of localized differences in climate are common.

Using NASA Techniques to Atmospherically Correct AWiFS Data for Carbon Sequestration Studies

NASA Technical Reports Server (NTRS)

Holekamp, Kara L.

2007-01-01

Carbon dioxide is a greenhouse gas emitted in a number of ways, including the burning of fossil fuels and the conversion of forest to agriculture. Research has begun to quantify the ability of vegetative land cover and oceans to absorb and store carbon dioxide. The USDA (U.S. Department of Agriculture) Forest Service is currently evaluating a DSS (decision support system) developed by researchers at the NASA Ames Research Center called CASA-CQUEST (Carnegie-Ames-Stanford Approach-Carbon Query and Evaluation Support Tools). CASA-CQUEST is capable of estimating levels of carbon sequestration based on different land cover types and of predicting the effects of land use change on atmospheric carbon amounts to assist land use management decisions. The CASA-CQUEST DSS currently uses land cover data acquired from MODIS (the Moderate Resolution Imaging Spectroradiometer), and the CASA-CQUEST project team is involved in several projects that use moderate-resolution land cover data derived from Landsat surface reflectance. Landsat offers higher spatial resolution than MODIS, allowing for increased ability to detect land use changes and forest disturbance. However, because of the rate at which changes occur and the fact that disturbances can be hidden by regrowth, updated land cover classifications may be required before the launch of the Landsat Data Continuity Mission, and consistent classifications will be needed after that time. This candidate solution investigates the potential of using NASA atmospheric correction techniques to produce science-quality surface reflectance data from the Indian Remote Sensing Advanced Wide-Field Sensor on the RESOURCESAT-1 mission to produce land cover classification maps for the CASA-CQUEST DSS.

Mapping permafrost in the boreal forest with Thematic Mapper satellite data

NASA Technical Reports Server (NTRS)

Morrissey, L. A.; Strong, L. L.; Card, D. H.

1986-01-01

A geographic data base incorporating Landsat TM data was used to develop and evaluate logistic discriminant functions for predicting the distribution of permafrost in a boreal forest watershed. The data base included both satellite-derived information and ancillary map data. Five permafrost classifications were developed from a stratified random sample of the data base and evaluated by comparison with a photo-interpreted permafrost map using contingency table analysis and soil temperatures recorded at sites within the watershed. A classification using a TM thermal band and a TM-derived vegetation map as independent variables yielded the highest mapping accuracy for all permafrost categories.

Assessment of spruce (Picea obovata) abundance by spectral unmixing algorithm for sustainable forest management in highland Natural Reserve (case study of Zigalga Range, South-Ural State Natural Reserve, Russia).

NASA Astrophysics Data System (ADS)

Mikheeva, Anna; Moiseev, Pavel

2017-04-01

In mountain territories climate change affects forest productivity and growth, which results in the tree line advancing and increasing of the forest density. These changes pose new challenges for forest managers whose responsibilities include forest resources inventory, monitoring and protection of ecosystems, and assessment of forest vulnerability. These activities require a range of sources of information, including exact squares of forested areas, forest densities and species abundances. Picea obovata, dominant tree species in South-Ural State Natural Reserve, Russia has regenerated, propagated and increased its relative cover during the recent 70 years. A remarkable shift of the upper limit of Picea obovata up to 60-80 m upslope was registered by repeating photography, especially on gentle slopes. The stands of Picea obovata are monitored by Reserve inspectors on the test plots to ensure that forests maintain or improve their productivity, these studies also include projective cover measurements. However, it is impossible to cover the entire territory of the Reserve by detailed field observations. Remote sensing data from Terra ASTER imagery provides valuable information for large territories (scene covers an area of 60 x 60 km) and can be used for quantitative mapping of forest and non-forest vegetation at regional scale (spatial resolution is 15-30 m for visible and infrared bands). A case study of estimating Picea obovata abundance was conducted for forest and forest-tundra sites of Zigalga Range, using 9-band ASTER multispectral imagery of 23.08.2007, field data and spectral unmixing algorithm. This type of algorithms intends to derive object and its abundance from a mixed pixel of multispectral imagery which can be further converted to object's projective cover. Atmospheric correction was applied to the imagery prior to spectral unmixing, and then pure spectra of Picea obovata were extracted from the image in 10 points and averaged. These points located in Zigalga Range and were visited in summer 2016. We used Mixture-tuned Match Filtering (MTMF) algorithm, a non-linear subpixel classification technique which allows to separate the spectral mixture containing unknown objects, and to derive only known ones. The results of spectral unmixing classification were abundance maps of Picea obovata. The values were statistically determined (there was only selected abundances with high probabilities of presence and low probabilities of absence) and then constrained to the interval [0; 1]. Verification of maps was made at the sites of Iremel Mountains on the same ASTER image, where projective cover of Picea obovata was measured in the field in 147 points. The correlation coefficient between the spectral unmixing abundances and field-measured abundances was 0.7; not a very high value is due to the low sensitivity of the algorithm to detect abundances less than 0.25. The proposed method provides a tool for defining the Picea obovata boundaries more accurately than per-pixel automatic classification and locating new spruce islands in the mixing tree line environment. The abundances can be obtained for large areas with minimum field work which makes this approach cost-effective in providing timely information to nature reserve managers for adapting forest management actions to climate change.

Floating Forests: Validation of a Citizen Science Effort to Answer Global Ecological Questions

NASA Astrophysics Data System (ADS)

Rosenthal, I.; Byrnes, J.; Cavanaugh, K. C.; Haupt, A. J.; Trouille, L.; Bell, T. W.; Rassweiler, A.; Pérez-Matus, A.; Assis, J.

2017-12-01

Researchers undertaking long term, large-scale ecological analyses face significant challenges for data collection and processing. Crowdsourcing via citizen science can provide an efficient method for analyzing large data sets. However, many scientists have raised questions about the quality of data collected by citizen scientists. Here we use Floating-Forests (http://floatingforests.org), a citizen science platform for creating a global time series of giant kelp abundance, to show that ensemble classifications of satellite data can ensure data quality. Citizen scientists view satellite images of coastlines and classify kelp forests by tracing all visible patches of kelp. Each image is classified by fifteen citizen scientists before being retired. To validate citizen science results, all fifteen classifications are converted to a raster and overlaid on a calibration dataset generated from previous studies. Results show that ensemble classifications from citizen scientists are consistently accurate when compared to calibration data. Given that all source images were acquired by Landsat satellites, we expect this consistency to hold across all regions. At present, we have over 6000 web-based citizen scientists' classifications of almost 2.5 million images of kelp forests in California and Tasmania. These results are not only useful for remote sensing of kelp forests, but also for a wide array of applications that combine citizen science with remote sensing.

Mapping wetland and forest landscapes in Siberia with Landsat data

NASA Astrophysics Data System (ADS)

Maksyutov, Shamil; Kleptsova, Irina; Glagolev, Mikhail; Sedykh, Vladimir; Kuzmenko, Ekaterina; Silaev, Anton; Frolov, Alexander; Nikolaeva, Svetlana; Fedorov, Alexander

2014-05-01

Landsat data availability provides opportunity for improving the knowledge of the Siberian ecosystems necessary for quantifying the response of the regional carbon cycle to the climate change. We developed a new wetland map based on Landsat data for whole West Siberia aiming at scaling up the methane emission observations. Mid-summer Landsat scenes were used in supervised classification method, based on ground truth data obtained during multiple field surveys. The method allows distinguishing following wetland types: pine-dwarf shrubs-sphagnum bogs or ryams, ridge-hollows complexes, shallow-water complexes, sedge-sphagnum poor fens, herbaceous-sphagnum poor fens, sedge-(moss) poor fens and fens, wooded swamps or sogra, palsa complexes. In our estimates wetlands cover 36% of the taiga area. Total methane emission from WS taiga mires is estimated as 3.6 TgC/yr,which is 77% larger as compared to the earlier estimate based on partial Landsat mapping combined with low resolution map due to higher fraction of fen area. We make an attempt to develop a forest typology system useful for a dynamic vegetation modeling and apply it to the analysis of the forest type distribution for several test areas in West and East Siberia, aiming at capability of mapping whole Siberian forests based on Landsat data. Test region locations are: two in West Siberian middle taiga (Laryegan and Nyagan), and one in East Siberia near Yakutsk. The ground truth data are based on analysis of the field survey, forest inventory data from the point of view of the successional forest type classification. Supervised classification was applied to the areas where ample ground truth and inventory data are available, using several limited area maps and vegetation survey. In Laryegan basin the upland forest areas are dominated (as climax forest species) by Scots pine on sandy soils and Siberian pine with presence of fir and spruce on the others. Those types are separable using Landsat spectral data alone. In the permafrost area around Yakutsk the most widespread succession type is birch to larch succession. Three stages of the birch to larch succession are detectable from Landsat image. When Landsat data is used in both West and East Siberia, distinction between deciduous broad-leaved species (birch, aspen, and willow) is difficult due to similarity in spectral signatures. Same problem exists for distinguishing between dark coniferous species (Siberian pine, fir and spruce). Forest classification can be improved by applying landscape type analysis, such as separation into floodplain, terrace, sloping hills.

Forest ecosystems of a Lower Gulf Coastal Plainlandscape: multifactor classification and analysis

Treesearch

P. Charles Goebel; Brian J. Palik; L. Katherine Kirkman; Mark B. Drew; Larry West; Dee C. Pederson

2001-01-01

The most common forestland classification techniques applied in the southeastern United States are vegetation-based. While not completely ignored, the application of multifactor, hierarchical ecosystem classifications are limited despite their widespread use in other regions of the eastern United States. We present one of the few truly integrated ecosystem...

Evaluation of Skylab (EREP) data for forest and rangeland surveys. [Georgia, South Dakota, Colorado, and California

NASA Technical Reports Server (NTRS)

Aldrich, R. C. (Principal Investigator); Dana, R. W.; Greentree, W. J.; Roberts, E. H.; Norick, N. X.; Waite, T. H.; Francis, R. E.; Driscoll, R. S.; Weber, F. P.

1975-01-01

The author has identified the following significant results. Four widely separated sites (near Augusta, Georgia; Lead, South Dakota; Manitou, Colorado; and Redding, California) were selected as typical sites for forest inventory, forest stress, rangeland inventory, and atmospheric and solar measurements, respectively. Results indicated that Skylab S190B color photography is good for classification of Level 1 forest and nonforest land (90 to 95 percent correct) and could be used as a data base for sampling by small and medium scale photography using regression techniques. The accuracy of Level 2 forest and nonforest classes, however, varied from fair to poor. Results of plant community classification tests indicate that both visual and microdensitometric techniques can separate deciduous, conifirous, and grassland classes to the region level in the Ecoclass hierarchical classification system. There was no consistency in classifying tree categories at the series level by visual photointerpretation. The relationship between ground measurements and large scale photo measurements of foliar cover had a correlation coefficient of greater than 0.75. Some of the relationships, however, were site dependent.

Phylogenetic classification of the world's tropical forests.

PubMed

Slik, J W Ferry; Franklin, Janet; Arroyo-Rodríguez, Víctor; Field, Richard; Aguilar, Salomon; Aguirre, Nikolay; Ahumada, Jorge; Aiba, Shin-Ichiro; Alves, Luciana F; K, Anitha; Avella, Andres; Mora, Francisco; Aymard C, Gerardo A; Báez, Selene; Balvanera, Patricia; Bastian, Meredith L; Bastin, Jean-François; Bellingham, Peter J; van den Berg, Eduardo; da Conceição Bispo, Polyanna; Boeckx, Pascal; Boehning-Gaese, Katrin; Bongers, Frans; Boyle, Brad; Brambach, Fabian; Brearley, Francis Q; Brown, Sandra; Chai, Shauna-Lee; Chazdon, Robin L; Chen, Shengbin; Chhang, Phourin; Chuyong, George; Ewango, Corneille; Coronado, Indiana M; Cristóbal-Azkarate, Jurgi; Culmsee, Heike; Damas, Kipiro; Dattaraja, H S; Davidar, Priya; DeWalt, Saara J; Din, Hazimah; Drake, Donald R; Duque, Alvaro; Durigan, Giselda; Eichhorn, Karl; Eler, Eduardo Schmidt; Enoki, Tsutomu; Ensslin, Andreas; Fandohan, Adandé Belarmain; Farwig, Nina; Feeley, Kenneth J; Fischer, Markus; Forshed, Olle; Garcia, Queila Souza; Garkoti, Satish Chandra; Gillespie, Thomas W; Gillet, Jean-Francois; Gonmadje, Christelle; Granzow-de la Cerda, Iñigo; Griffith, Daniel M; Grogan, James; Hakeem, Khalid Rehman; Harris, David J; Harrison, Rhett D; Hector, Andy; Hemp, Andreas; Homeier, Jürgen; Hussain, M Shah; Ibarra-Manríquez, Guillermo; Hanum, I Faridah; Imai, Nobuo; Jansen, Patrick A; Joly, Carlos Alfredo; Joseph, Shijo; Kartawinata, Kuswata; Kearsley, Elizabeth; Kelly, Daniel L; Kessler, Michael; Killeen, Timothy J; Kooyman, Robert M; Laumonier, Yves; Laurance, Susan G; Laurance, William F; Lawes, Michael J; Letcher, Susan G; Lindsell, Jeremy; Lovett, Jon; Lozada, Jose; Lu, Xinghui; Lykke, Anne Mette; Mahmud, Khairil Bin; Mahayani, Ni Putu Diana; Mansor, Asyraf; Marshall, Andrew R; Martin, Emanuel H; Calderado Leal Matos, Darley; Meave, Jorge A; Melo, Felipe P L; Mendoza, Zhofre Huberto Aguirre; Metali, Faizah; Medjibe, Vincent P; Metzger, Jean Paul; Metzker, Thiago; Mohandass, D; Munguía-Rosas, Miguel A; Muñoz, Rodrigo; Nurtjahy, Eddy; de Oliveira, Eddie Lenza; Onrizal; Parolin, Pia; Parren, Marc; Parthasarathy, N; Paudel, Ekananda; Perez, Rolando; Pérez-García, Eduardo A; Pommer, Ulf; Poorter, Lourens; Qie, Lan; Piedade, Maria Teresa F; Pinto, José Roberto Rodrigues; Poulsen, Axel Dalberg; Poulsen, John R; Powers, Jennifer S; Prasad, Rama Chandra; Puyravaud, Jean-Philippe; Rangel, Orlando; Reitsma, Jan; Rocha, Diogo S B; Rolim, Samir; Rovero, Francesco; Rozak, Andes; Ruokolainen, Kalle; Rutishauser, Ervan; Rutten, Gemma; Mohd Said, Mohd Nizam; Saiter, Felipe Z; Saner, Philippe; Santos, Braulio; Dos Santos, João Roberto; Sarker, Swapan Kumar; Schmitt, Christine B; Schoengart, Jochen; Schulze, Mark; Sheil, Douglas; Sist, Plinio; Souza, Alexandre F; Spironello, Wilson Roberto; Sposito, Tereza; Steinmetz, Robert; Stevart, Tariq; Suganuma, Marcio Seiji; Sukri, Rahayu; Sultana, Aisha; Sukumar, Raman; Sunderland, Terry; Supriyadi; Suresh, H S; Suzuki, Eizi; Tabarelli, Marcelo; Tang, Jianwei; Tanner, Ed V J; Targhetta, Natalia; Theilade, Ida; Thomas, Duncan; Timberlake, Jonathan; de Morisson Valeriano, Márcio; van Valkenburg, Johan; Van Do, Tran; Van Sam, Hoang; Vandermeer, John H; Verbeeck, Hans; Vetaas, Ole Reidar; Adekunle, Victor; Vieira, Simone A; Webb, Campbell O; Webb, Edward L; Whitfeld, Timothy; Wich, Serge; Williams, John; Wiser, Susan; Wittmann, Florian; Yang, Xiaobo; Adou Yao, C Yves; Yap, Sandra L; Zahawi, Rakan A; Zakaria, Rahmad; Zang, Runguo

2018-02-20

Knowledge about the biogeographic affinities of the world's tropical forests helps to better understand regional differences in forest structure, diversity, composition, and dynamics. Such understanding will enable anticipation of region-specific responses to global environmental change. Modern phylogenies, in combination with broad coverage of species inventory data, now allow for global biogeographic analyses that take species evolutionary distance into account. Here we present a classification of the world's tropical forests based on their phylogenetic similarity. We identify five principal floristic regions and their floristic relationships: ( i ) Indo-Pacific, ( ii ) Subtropical, ( iii ) African, ( iv ) American, and ( v ) Dry forests. Our results do not support the traditional neo- versus paleotropical forest division but instead separate the combined American and African forests from their Indo-Pacific counterparts. We also find indications for the existence of a global dry forest region, with representatives in America, Africa, Madagascar, and India. Additionally, a northern-hemisphere Subtropical forest region was identified with representatives in Asia and America, providing support for a link between Asian and American northern-hemisphere forests. Copyright © 2018 the Author(s). Published by PNAS.

Phylogenetic classification of the world’s tropical forests

PubMed Central

Franklin, Janet; Arroyo-Rodríguez, Víctor; Field, Richard; Aguilar, Salomon; Aguirre, Nikolay; Ahumada, Jorge; Aiba, Shin-Ichiro; K, Anitha; Avella, Andres; Mora, Francisco; Aymard C., Gerardo A.; Báez, Selene; Balvanera, Patricia; Bastian, Meredith L.; Bastin, Jean-François; Bellingham, Peter J.; van den Berg, Eduardo; da Conceição Bispo, Polyanna; Boeckx, Pascal; Boehning-Gaese, Katrin; Bongers, Frans; Boyle, Brad; Brearley, Francis Q.; Brown, Sandra; Chai, Shauna-Lee; Chazdon, Robin L.; Chen, Shengbin; Chhang, Phourin; Chuyong, George; Ewango, Corneille; Coronado, Indiana M.; Cristóbal-Azkarate, Jurgi; Culmsee, Heike; Damas, Kipiro; Dattaraja, H. S.; Davidar, Priya; DeWalt, Saara J.; Din, Hazimah; Drake, Donald R.; Durigan, Giselda; Eichhorn, Karl; Eler, Eduardo Schmidt; Enoki, Tsutomu; Ensslin, Andreas; Fandohan, Adandé Belarmain; Farwig, Nina; Feeley, Kenneth J.; Fischer, Markus; Forshed, Olle; Garcia, Queila Souza; Garkoti, Satish Chandra; Gillespie, Thomas W.; Gillet, Jean-Francois; Gonmadje, Christelle; Granzow-de la Cerda, Iñigo; Griffith, Daniel M.; Grogan, James; Hakeem, Khalid Rehman; Harris, David J.; Harrison, Rhett D.; Hector, Andy; Hemp, Andreas; Hussain, M. Shah; Ibarra-Manríquez, Guillermo; Hanum, I. Faridah; Imai, Nobuo; Jansen, Patrick A.; Joly, Carlos Alfredo; Joseph, Shijo; Kartawinata, Kuswata; Kearsley, Elizabeth; Kelly, Daniel L.; Kessler, Michael; Killeen, Timothy J.; Kooyman, Robert M.; Laumonier, Yves; Laurance, William F.; Lawes, Michael J.; Letcher, Susan G.; Lovett, Jon; Lozada, Jose; Lu, Xinghui; Lykke, Anne Mette; Mahmud, Khairil Bin; Mahayani, Ni Putu Diana; Mansor, Asyraf; Marshall, Andrew R.; Martin, Emanuel H.; Calderado Leal Matos, Darley; Meave, Jorge A.; Melo, Felipe P. L.; Mendoza, Zhofre Huberto Aguirre; Metali, Faizah; Medjibe, Vincent P.; Metzger, Jean Paul; Metzker, Thiago; Mohandass, D.; Munguía-Rosas, Miguel A.; Muñoz, Rodrigo; Nurtjahy, Eddy; de Oliveira, Eddie Lenza; Onrizal; Parolin, Pia; Parren, Marc; Parthasarathy, N.; Paudel, Ekananda; Perez, Rolando; Pérez-García, Eduardo A.; Pommer, Ulf; Poorter, Lourens; Qie, Lan; Piedade, Maria Teresa F.; Pinto, José Roberto Rodrigues; Poulsen, Axel Dalberg; Poulsen, John R.; Powers, Jennifer S.; Prasad, Rama Chandra; Puyravaud, Jean-Philippe; Rangel, Orlando; Reitsma, Jan; Rocha, Diogo S. B.; Rolim, Samir; Rovero, Francesco; Ruokolainen, Kalle; Rutishauser, Ervan; Rutten, Gemma; Mohd. Said, Mohd. Nizam; Saiter, Felipe Z.; Saner, Philippe; Santos, Braulio; dos Santos, João Roberto; Sarker, Swapan Kumar; Schoengart, Jochen; Schulze, Mark; Sheil, Douglas; Sist, Plinio; Souza, Alexandre F.; Spironello, Wilson Roberto; Sposito, Tereza; Steinmetz, Robert; Stevart, Tariq; Suganuma, Marcio Seiji; Sukri, Rahayu; Sukumar, Raman; Sunderland, Terry; Supriyadi; Suresh, H. S.; Suzuki, Eizi; Tabarelli, Marcelo; Tang, Jianwei; Tanner, Ed V. J.; Targhetta, Natalia; Theilade, Ida; Thomas, Duncan; Timberlake, Jonathan; de Morisson Valeriano, Márcio; van Valkenburg, Johan; Van Do, Tran; Van Sam, Hoang; Vandermeer, John H.; Verbeeck, Hans; Vetaas, Ole Reidar; Adekunle, Victor; Vieira, Simone A.; Webb, Campbell O.; Webb, Edward L.; Whitfeld, Timothy; Wich, Serge; Williams, John; Wiser, Susan; Wittmann, Florian; Yang, Xiaobo; Adou Yao, C. Yves; Yap, Sandra L.; Zahawi, Rakan A.; Zakaria, Rahmad; Zang, Runguo

2018-01-01

Knowledge about the biogeographic affinities of the world’s tropical forests helps to better understand regional differences in forest structure, diversity, composition, and dynamics. Such understanding will enable anticipation of region-specific responses to global environmental change. Modern phylogenies, in combination with broad coverage of species inventory data, now allow for global biogeographic analyses that take species evolutionary distance into account. Here we present a classification of the world’s tropical forests based on their phylogenetic similarity. We identify five principal floristic regions and their floristic relationships: (i) Indo-Pacific, (ii) Subtropical, (iii) African, (iv) American, and (v) Dry forests. Our results do not support the traditional neo- versus paleotropical forest division but instead separate the combined American and African forests from their Indo-Pacific counterparts. We also find indications for the existence of a global dry forest region, with representatives in America, Africa, Madagascar, and India. Additionally, a northern-hemisphere Subtropical forest region was identified with representatives in Asia and America, providing support for a link between Asian and American northern-hemisphere forests. PMID:29432167

Classification of Forest Regrowth Stage using Polarimetric Decomposition and Foliage Projective Cover

NASA Astrophysics Data System (ADS)

Clewley, D.; Lucas, R.; Bunting, P.; Moghaddam, M.

2012-12-01

Within Queensland, Australia extensive clearing of vegetation for agriculture has occurred within the Brigalow Belt Bioregion (BBB), reducing forests dominated by Acacia harpophylla (brigalow) to 10 % of their former extent. Where cleared land is left abandoned or unmanaged regeneration is rapid, Regenerating vegetation represents a more efficient and cost effective method for carbon sequestration than direct planting and offers a number of benefits over plantation forest, particularly in terms of provision of habitat for native fauna. To effectively protect regenerating vegetation, maps of the distribution of forests at different stages of regeneration are required. Whilst mapping approaches have traditionally focused on optical data, the high canopy cover of brigalow regrowth in all but the very early stages limits discrimination of forests at different stages of growth. The combination of optical data, namely Landsat derived Foliage Projective Cover (FPC) and Advanced Land Observing Satellite (ALOS) Phased Array L-band Synthetic Aperture Radar (SAR) backscatter data have previously been investigated for mapping regrowth. This study therefore aimed to investigate the potential of the alpha-Entropy (α/H) decomposition (S Cloude and E Pottier, "An entropy based classification scheme for land applications of polarimetric SAR," 1997, IEEE Transactions on Geoscience and Remote Sensing, vol. 35, no. 1, pp. 68-78) applied to polarimetric ALOS PALSAR backscatter for mapping regrowth stage combined with FPC data to account for canopy variations. The study focused on the Tara Downs subregion, located in the Western Darling Downs, within the south of the BBB. PALSAR data were acquired over the study site in fully-polarimetric mode (incidence angle mid swath ~ 26 degrees). From these data α/H layers were generated and stacked with FPC data. Considering only those areas known to contain brigalow prior to clearing and with an FPC > 9 %, k-means clustering was applied, with the number of clusters set to three. The position of each cluster, within α/H space was then used to determine the appropriate regrowth stage, based on the zones defined by Cloude and Pottier (1997). The classification was compared to an existing regrowth stage classification of the area derived from time-series interpretation of aerial photography and high resolution satellite data. The overall accuracy of the classification was 47 %, with confusion attributed to the differing methods of classification in that the separation of regrowth stage based on age did not account for variation in structure, associated with differences in soil, topography and clearing history. Conversely, the proposed classification method is based on scattering properties, which vary as a function of forest structure. The approach has demonstrated the potential of α/H layers derived from PALSAR data and FPC for discriminating and mapping different stages of regrowth. A particular advantage of the technique is that regrowth stages are assigned based on scattering characteristics, placing less reliance on field data which is not always available. Further work is being undertaken to evaluate alternative supervised and rule-based approaches to classification, such that a more consistent mapping methodology can be developed.

Determination of pumper truck intervention ratios in zones with high fire potential by using geographical information system

NASA Astrophysics Data System (ADS)

Aricak, Burak; Kucuk, Omer; Enez, Korhan

2014-01-01

Fighting forest fires not only depends on the forest type, topography, and weather conditions, but is also closely related to the technical properties of fire-fighting equipment. Firefighting is an important part of fire management planning. However, because of the complex nature of forests, creating thematic layers to generate potential fire risk maps is difficult. The use of remote sensing data has become an efficient method for the discrete classification of potential fire risks. The study was located in the Central District of the Kastamonu Regional Forest Directorate, covering an area of 24,320 ha, 15,685 ha of which is forested. On the basis of stand age, crown closure, and tree species, the sizes and distributions of potential fire risk zones within the study area were determined using high-resolution GeoEye satellite imagery and geographical information system data. The status of pumper truck intervention in zones with high fire risk and the sufficiency of existing forest roads within an existing forest network were discussed based on combustible matter characteristics. Pumper truck intervention was 83% for high-risk zones, 79% for medium-risk zones, and 78% for low-risk zones. A pumper truck intervention area map along existing roads was also created.

Preliminary inventory and classification of indigenous afromontane forests on the Blyde River Canyon Nature Reserve, Mpumalanga, South Africa

PubMed Central

Lötter, Mervyn C; Beck, Hans T

2004-01-01

Background Mixed evergreen forests form the smallest, most widely distributed and fragmented biome in southern Africa. Within South Africa, 44% of this vegetation type has been transformed. Afromontane forest only covers 0.56 % of South Africa, yet it contains 5.35% of South Africa's plant species. Prior to this investigation of the indigenous forests on the Blyde River Canyon Nature Reserve (BRCNR), very little was known about the size, floristic composition and conservation status of the forest biome conserved within the reserve. We report here an inventory of the forest size, fragmentation, species composition and the basic floristic communities along environmental gradients. Results A total of 2111 ha of forest occurs on Blyde River Canyon Nature Reserve. The forest is fragmented, with a total of 60 forest patches recorded, varying from 0.21 ha to 567 ha in size. On average, patch size was 23 ha. Two forest communities – high altitude moist afromontane forest and low altitude dry afromontane forest – are identified. Sub-communities are recognized based on canopy development and slope, respectively. An altitudinal gradient accounts for most of the variation within the forest communities. Conclusion BRCNR has a fragmented network of small forest patches that together make up 7.3% of the reserve's surface area. These forest patches host a variety of forest-dependent trees, including some species considered rare, insufficiently known, or listed under the Red Data List of South African Plants. The fragmented nature of the relatively small forest patches accentuates the need for careful fire management and stringent alien plant control. PMID:15287991

Change in the forested and developed landscape of the Lake Tahoe basin, California and Nevada, USA, 1940-2002

USGS Publications Warehouse

Raumann, C.G.; Cablk, Mary E.

2008-01-01

The current ecological state of the Lake Tahoe basin has been shaped by significant landscape-altering human activity and management practices since the mid-1850s; first through widespread timber harvesting from the 1850s to 1920s followed by urban development from the 1950s to the present. Consequences of landscape change, both from development and forest management practices including fire suppression, have prompted rising levels of concern for the ecological integrity of the region. The impacts from these activities include decreased water quality, degraded biotic communities, and increased fire hazard. To establish an understanding of the Lake Tahoe basin's landscape change in the context of forest management and development we mapped, quantified, and described the spatial and temporal distribution and variability of historical changes in land use and land cover in the southern Lake Tahoe basin (279 km2) from 1940 to 2002. Our assessment relied on post-classification change detection of multi-temporal land-use/cover and impervious-surface-area data that were derived through manual interpretation, image processing, and GIS data integration for four dates of imagery: 1940, 1969, 1987, and 2002. The most significant land conversion during the 62-year study period was an increase in developed lands with a corresponding decrease in forests, wetlands, and shrublands. Forest stand densities increased throughout the 62-year study period, and modern thinning efforts resulted in localized stand density decreases in the latter part of the study period. Additionally forests were gained from succession, and towards the end of the study period extensive tree mortality occurred. The highest rates of change occurred between 1940 and 1969, corresponding with dramatic development, then rates declined through 2002 for all observed landscape changes except forest density decrease and tree mortality. Causes of landscape change included regional population growth, tourism demands, timber harvest for local use, fire suppression, bark beetle attack, and fuels reduction activities. Results from this study offer land managers within the Lake Tahoe basin and in similar regions a basis for making better informed land-use and management decisions to potentially minimize detrimental ecological impacts of landscape change. The perspective to be gained is based on quantitative retrospection of the effects of human-driven changes and the impacts of management action or inaction to the forested landscape. ?? 2008 Elsevier B.V. All rights reserved.

Influence of multi-source and multi-temporal remotely sensed and ancillary data on the accuracy of random forest classification of wetlands in northern Minnesota

USGS Publications Warehouse

Corcoran, Jennifer M.; Knight, Joseph F.; Gallant, Alisa L.

2013-01-01

Wetland mapping at the landscape scale using remotely sensed data requires both affordable data and an efficient accurate classification method. Random forest classification offers several advantages over traditional land cover classification techniques, including a bootstrapping technique to generate robust estimations of outliers in the training data, as well as the capability of measuring classification confidence. Though the random forest classifier can generate complex decision trees with a multitude of input data and still not run a high risk of over fitting, there is a great need to reduce computational and operational costs by including only key input data sets without sacrificing a significant level of accuracy. Our main questions for this study site in Northern Minnesota were: (1) how does classification accuracy and confidence of mapping wetlands compare using different remote sensing platforms and sets of input data; (2) what are the key input variables for accurate differentiation of upland, water, and wetlands, including wetland type; and (3) which datasets and seasonal imagery yield the best accuracy for wetland classification. Our results show the key input variables include terrain (elevation and curvature) and soils descriptors (hydric), along with an assortment of remotely sensed data collected in the spring (satellite visible, near infrared, and thermal bands; satellite normalized vegetation index and Tasseled Cap greenness and wetness; and horizontal-horizontal (HH) and horizontal-vertical (HV) polarization using L-band satellite radar). We undertook this exploratory analysis to inform decisions by natural resource managers charged with monitoring wetland ecosystems and to aid in designing a system for consistent operational mapping of wetlands across landscapes similar to those found in Northern Minnesota.

Testing random forest classification for identifying lava flows and mapping age groups on a single Landsat 8 image

NASA Astrophysics Data System (ADS)

Li, Long; Solana, Carmen; Canters, Frank; Kervyn, Matthieu

2017-10-01

Mapping lava flows using satellite images is an important application of remote sensing in volcanology. Several volcanoes have been mapped through remote sensing using a wide range of data, from optical to thermal infrared and radar images, using techniques such as manual mapping, supervised/unsupervised classification, and elevation subtraction. So far, spectral-based mapping applications mainly focus on the use of traditional pixel-based classifiers, without much investigation into the added value of object-based approaches and into advantages of using machine learning algorithms. In this study, Nyamuragira, characterized by a series of > 20 overlapping lava flows erupted over the last century, was used as a case study. The random forest classifier was tested to map lava flows based on pixels and objects. Image classification was conducted for the 20 individual flows and for 8 groups of flows of similar age using a Landsat 8 image and a DEM of the volcano, both at 30-meter spatial resolution. Results show that object-based classification produces maps with continuous and homogeneous lava surfaces, in agreement with the physical characteristics of lava flows, while lava flows mapped through the pixel-based classification are heterogeneous and fragmented including much "salt and pepper noise". In terms of accuracy, both pixel-based and object-based classification performs well but the former results in higher accuracies than the latter except for mapping lava flow age groups without using topographic features. It is concluded that despite spectral similarity, lava flows of contrasting age can be well discriminated and mapped by means of image classification. The classification approach demonstrated in this study only requires easily accessible image data and can be applied to other volcanoes as well if there is sufficient information to calibrate the mapping.

Landscape scale mapping of forest inventory data by nearest neighbor classification

Treesearch

Andrew Lister

2009-01-01

One of the goals of the Forest Service, U.S. Department of Agriculture's Forest Inventory and Analysis (FIA) program is large-area mapping. FIA scientists have tried many methods in the past, including geostatistical methods, linear modeling, nonlinear modeling, and simple choropleth and dot maps. Mapping methods that require individual model-based maps to be...

Unveiling Undercover Cropland Inside Forests Using Landscape Variables: A Supplement to Remote Sensing Image Classification

PubMed Central

Ayanu, Yohannes; Conrad, Christopher; Jentsch, Anke; Koellner, Thomas

2015-01-01

The worldwide demand for food has been increasing due to the rapidly growing global population, and agricultural lands have increased in extent to produce more food crops. The pattern of cropland varies among different regions depending on the traditional knowledge of farmers and availability of uncultivated land. Satellite images can be used to map cropland in open areas but have limitations for detecting undergrowth inside forests. Classification results are often biased and need to be supplemented with field observations. Undercover cropland inside forests in the Bale Mountains of Ethiopia was assessed using field observed percentage cover of land use/land cover classes, and topographic and location parameters. The most influential factors were identified using Boosted Regression Trees and used to map undercover cropland area. Elevation, slope, easterly aspect, distance to settlements, and distance to national park were found to be the most influential factors determining undercover cropland area. When there is very high demand for growing food crops, constrained under restricted rights for clearing forest, cultivation could take place within forests as an undercover. Further research on the impact of undercover cropland on ecosystem services and challenges in sustainable management is thus essential. PMID:26098107

Unveiling Undercover Cropland Inside Forests Using Landscape Variables: A Supplement to Remote Sensing Image Classification.

PubMed

Ayanu, Yohannes; Conrad, Christopher; Jentsch, Anke; Koellner, Thomas

2015-01-01

The worldwide demand for food has been increasing due to the rapidly growing global population, and agricultural lands have increased in extent to produce more food crops. The pattern of cropland varies among different regions depending on the traditional knowledge of farmers and availability of uncultivated land. Satellite images can be used to map cropland in open areas but have limitations for detecting undergrowth inside forests. Classification results are often biased and need to be supplemented with field observations. Undercover cropland inside forests in the Bale Mountains of Ethiopia was assessed using field observed percentage cover of land use/land cover classes, and topographic and location parameters. The most influential factors were identified using Boosted Regression Trees and used to map undercover cropland area. Elevation, slope, easterly aspect, distance to settlements, and distance to national park were found to be the most influential factors determining undercover cropland area. When there is very high demand for growing food crops, constrained under restricted rights for clearing forest, cultivation could take place within forests as an undercover. Further research on the impact of undercover cropland on ecosystem services and challenges in sustainable management is thus essential.

Fine-scale habitat use by orang-utans in a disturbed peat swamp forest, central Kalimantan, and implications for conservation management.

PubMed

Morrogh-Bernard, Helen C; Husson, Simon J; Harsanto, Fransiskus A; Chivers, David J

2014-01-01

This study was conducted to see how orang-utans (Pongo pygmaeus wurmbii) were coping with fine-scale habitat disturbance in a selectively logged peat swamp forest in Central Kalimantan, Borneo. Seven habitat classes were defined, and orang-utans were found to use all of these, but were selective in their preference for certain classes over others. Overall, the tall forest classes (≥20 m) were preferred. They were preferred for feeding, irrespective of canopy connectivity, whereas classes with a connected canopy (canopy cover ≥75%), irrespective of canopy height, were preferred for resting and nesting, suggesting that tall trees are preferred for feeding and connected canopy for security and protection. The smaller forest classes (≤10 m high) were least preferred and were used mainly for travelling from patch to patch. Thus, selective logging is demonstrated here to be compatible with orang-utan survival as long as large food trees and patches of primary forest remain. Logged forest, therefore, should not automatically be designated as 'degraded'. These findings have important implications for forest management, forest classification and the designation of protected areas for orang-utan conservation.

Ecological Land Classification: Applications to Identify the Productive Potential of Southern Forests

Treesearch

Dennis L. Mengel; D. Thompson Tew; [Editors

1991-01-01

Eighteen papers representing four categories-Regional Overviews; Classification System Development; Classification System Interpretation; Mapping/GIS Applications in Classification Systems-present the state of the art in forest-land classification and evaluation in the South. In addition, nine poster papers are presented.

Investigation on changes in complex vegetation coverage using multi-temporal landsat data of Western Black Sea region--a case study.

PubMed

Coban, Huseyin Oguz; Koc, Ayhan; Eker, Mehmet

2010-01-01

Previous studies have been able to successfully detect changes in gently-sloping forested areas with low-diversity and homogeneous vegetation cover using medium-resolution satellite data such as landsat. The aim of the present study is to examine the capacity of multi-temporal landsat data to identify changes in forested areas with mixed vegetation and generally located on steep slopes or non-uniform topography landsat thematic mapper (TM) and landsat enhanced thematic mapperplus (ETM+) data for the years 1987-2000 was used to detect changes within a 19,500 ha forested area in the Western Black sea region of Turkey. The data comply with the forest cover type maps previously created for forest management plans of the research area. The methods used to detect changes were: post-classification comparison, image differencing, image rationing and NDVI (Normalized Difference Vegetation Index) differencing methods. Following the supervised classification process, error matrices were used to evaluate the accuracy of classified images obtained. The overall accuracy has been calculated as 87.59% for 1987 image and as 91.81% for 2000 image. General kappa statistics have been calculated as 0.8543 and 0.9038 for 1987 and 2000, respectively. The changes identified via the post-classification comparison method were compared with other change detetion methods. Maximum coherence was found to be 74.95% at 4/3 band rate. The NDVI difference and 3rd band difference methods achieved the same coherence with slight variations. The results suggest that landsat satellite data accurately conveys the temporal changes which occur on steeply-sloping forested areas with a mixed structure, providing a limited amount of detail but with a high level of accuracy. Moreover it has been decided that the post-classification comparison method can meet the needs of forestry activities better than other methods as it provides information about the direction of these changes.

Computer aided diagnosis system for the Alzheimer's disease based on partial least squares and random forest SPECT image classification.

PubMed

Ramírez, J; Górriz, J M; Segovia, F; Chaves, R; Salas-Gonzalez, D; López, M; Alvarez, I; Padilla, P

2010-03-19

This letter shows a computer aided diagnosis (CAD) technique for the early detection of the Alzheimer's disease (AD) by means of single photon emission computed tomography (SPECT) image classification. The proposed method is based on partial least squares (PLS) regression model and a random forest (RF) predictor. The challenge of the curse of dimensionality is addressed by reducing the large dimensionality of the input data by downscaling the SPECT images and extracting score features using PLS. A RF predictor then forms an ensemble of classification and regression tree (CART)-like classifiers being its output determined by a majority vote of the trees in the forest. A baseline principal component analysis (PCA) system is also developed for reference. The experimental results show that the combined PLS-RF system yields a generalization error that converges to a limit when increasing the number of trees in the forest. Thus, the generalization error is reduced when using PLS and depends on the strength of the individual trees in the forest and the correlation between them. Moreover, PLS feature extraction is found to be more effective for extracting discriminative information from the data than PCA yielding peak sensitivity, specificity and accuracy values of 100%, 92.7%, and 96.9%, respectively. Moreover, the proposed CAD system outperformed several other recently developed AD CAD systems. Copyright 2010 Elsevier Ireland Ltd. All rights reserved.

Mapping post-fire forest regeneration and vegetation recovery using a combination of very high spatial resolution and hyperspectral satellite imagery

NASA Astrophysics Data System (ADS)

Mitri, George H.; Gitas, Ioannis Z.

2013-02-01

Careful evaluation of forest regeneration and vegetation recovery after a fire event provides vital information useful in land management. The use of remotely sensed data is considered to be especially suitable for monitoring ecosystem dynamics after fire. The aim of this work was to map post-fire forest regeneration and vegetation recovery on the Mediterranean island of Thasos by using a combination of very high spatial (VHS) resolution (QuickBird) and hyperspectral (EO-1 Hyperion) imagery and by employing object-based image analysis. More specifically, the work focused on (1) the separation and mapping of three major post-fire classes (forest regeneration, other vegetation recovery, unburned vegetation) existing within the fire perimeter, and (2) the differentiation and mapping of the two main forest regeneration classes, namely, Pinus brutia regeneration, and Pinus nigra regeneration. The data used in this study consisted of satellite images and field observations of homogeneous regenerated and revegetated areas. The methodology followed two main steps: a three-level image segmentation, and, a classification of the segmented images. The process resulted in the separation of classes related to the aforementioned objectives. The overall accuracy assessment revealed very promising results (approximately 83.7% overall accuracy, with a Kappa Index of Agreement of 0.79). The achieved accuracy was 8% higher when compared to the results reported in a previous work in which only the EO-1 Hyperion image was employed in order to map the same classes. Some classification confusions involving the classes of P. brutia regeneration and P. nigra regeneration were observed. This could be attributed to the absence of large and dense homogeneous areas of regenerated pine trees in the study area.

The National Vegetation Classification Standard applied to the remote sensing classification of two semiarid environments

USGS Publications Warehouse

Ramsey, Elijah W.; Nelson, G.A.; Echols, D.; Sapkota, S.K.

2002-01-01

The National Vegetation Classification Standard (NVCS) was implemented at two US National Park Service (NPS) sites in Texas, the Padre Island National Seashore (PINS) and the Lake Meredith National Recreation Area (LM-NRA), to provide information for NPS oil and gas management plans. Because NVCS landcover classifications did not exist for these two areas prior to this study, we created landcover classes, through intensive ground and aerial reconnaissance, that characterized the general landscape features and at the same time complied with NVCS guidelines. The created landcover classes were useful for the resource management and were conducive to classification with optical remote sensing systems, such as the Landsat Thematic Mapper (TM). In the LMNRA, topographic elevation data were added to the TM data to reduce confusion between cliff, high plains, and forest classes. Classification accuracies (kappa statistics) of 89.9% (0.89) and 88.2% (0.87) in PINS and LMNRA, respectively, verified that the two NPS landholdings were adequately mapped with TM data. Improved sensor systems with higher spectral and spatial resolutions will ultimately refine the broad classes defined in this classification; however, the landcover classifications created in this study have already provided valuable information for the management of both NPS lands. Habitat information provided by the classifications has aided in the placement of inventory and monitoring plots, has assisted oil and gas operators by providing information on sensitive habitats, and has allowed park managers to better use resources when fighting wildland fires and in protecting visitors and the infrastructure of NPS lands.

The National Vegetation Classification Standard applied to the remote sensing classification of two semiarid environments.

PubMed

Ramsey, Elijah W; Nelson, Gene A; Echols, Darrell; Sapkota, Sijan K

2002-05-01

The National Vegetation Classification Standard (NVCS) was implemented at two US National Park Service (NPS) sites in Texas, the Padre Island National Seashore (PINS) and the Lake Meredith National Recreation Area (LMNRA), to provide information for NPS oil and gas management plans. Because NVCS landcover classifications did not exist for these two areas prior to this study, we created landcover classes, through intensive ground and aerial reconnaissance, that characterized the general landscape features and at the same time complied with NVCS guidelines. The created landcover classes were useful for the resource management and were conducive to classification with optical remote sensing systems, such as the Landsat Thematic Mapper (TM). In the LMNRA, topographic elevation data were added to the TM data to reduce confusion between cliff, high plains, and forest classes. Classification accuracies (kappa statistics) of 89.9% (0.89) and 88.2% (0.87) in PINS and LMNRA, respectively, verified that the two NPS landholdings were adequately mapped with TM data. Improved sensor systems with higher spectral and spatial resolutions will ultimately refine the broad classes defined in this classification; however, the landcover classifications created in this study have already provided valuable information for the management of both NPS lands. Habitat information provided by the classifications has aided in the placement of inventory and monitoring plots, has assisted oil and gas operators by providing information on sensitive habitats, and has allowed park managers to better use resources when fighting wildland fires and in protecting visitors and the infrastructure of NPS lands.

Special Forest Products on the Green Mountain and Finger Lakes National Forests: a research-based approach to management

Treesearch

Marla R. Emery; Clare Ginger

2014-01-01

Special forest products (SFPs) are gathered from more than 200 vascular and fungal species on the Green Mountain National Forest (GMNF) and Finger Lakes National Forest (FLNF). This report documents those SFPs and proposes an approach to managing them in the context of legislation directing the U.S. Forest Service to institute a program of active SFP management. Based...

Classification and area estimation of land covers in Kansas using ground-gathered and LANDSAT digital data

NASA Technical Reports Server (NTRS)

May, G. A.; Holko, M. L.; Anderson, J. E.

1983-01-01

Ground-gathered data and LANDSAT multispectral scanner (MSS) digital data from 1981 were analyzed to produce a classification of Kansas land areas into specific types called land covers. The land covers included rangeland, forest, residential, commercial/industrial, and various types of water. The analysis produced two outputs: acreage estimates with measures of precision, and map-type or photo products of the classification which can be overlaid on maps at specific scales. State-level acreage estimates were obtained and substate-level land cover classification overlays and estimates were generated for selected geographical areas. These products were found to be of potential use in managing land and water resources.

Mississippi Alluvial Valley

USGS Publications Warehouse

Reinecke, K.J.; Kaminski, R.M.; Moorhead, D.J.; Hodges, J.D.; Nasser, J.R.; Smith, L.M.; Pederson, R.L.; Kaminski, R.M.

1989-01-01

Available data are summarized according to the following major topics: (1) characteristics of the Mississippi Alluvial Valley (MAV); (2) waterfowl populations associated with the MAV; (3) habitat requirements of migrating and wintering waterfowl in the MAV; (4) current habitat management practices in the MAV, including croplands, moist-soil impoundments, and forested wetlands; (5) status and classification of winter habitat in the MAV; and (6) research and management information needs.

Fuels and fire in land-management planning. Part 1. Forest-fuel classification.

Treesearch

Wayne G. Maxwell; Franklin R. Ward

1981-01-01

This report describes a way to collect and classify the total fuel complex within a planning area. The information can be used as input for appraising and rating probable fire behavior and calculating expected costs and losses from various land uses and management alternatives, reported separately as Part 2 and Part 3 of this series. This total package can be used...

Accuracy and efficiency of area classifications based on tree tally

Treesearch

Michael S. Williams; Hans T. Schreuder; Raymond L. Czaplewski

2001-01-01

Inventory data are often used to estimate the area of the land base that is classified as a specific condition class. Examples include areas classified as old-growth forest, private ownership, or suitable habitat for a given species. Many inventory programs rely on classification algorithms of varying complexity to determine condition class. These algorithms can be...

High Spatial resolution remote sensing for salt marsh change detection on Fire Island National Seashore

NASA Astrophysics Data System (ADS)

Campbell, A.; Wang, Y.

2017-12-01

Salt marshes are under increasing pressure due to anthropogenic stressors including sea level rise, nutrient enrichment, herbivory and disturbances. Salt marsh losses risk the important ecosystem services they provide including biodiversity, water filtration, wave attenuation, and carbon sequestration. This study determines salt marsh change on Fire Island National Seashore, a barrier island along the south shore of Long Island, New York. Object-based image analysis was used to classifying Worldview-2, high resolution satellite, and topobathymetric LiDAR. The site was impacted by Hurricane Sandy in October of 2012 causing a breach in the Barrier Island and extensive overwash. In situ training data from vegetation plots were used to train the Random Forest classifier. The object-based Worldview-2 classification achieved an overall classification accuracy of 92.75. Salt marsh change for the study site was determined by comparing the 2015 classification with a 1997 classification. The study found a shift from high marsh to low marsh and a reduction in Phragmites on Fire Island. Vegetation losses were observed along the edge of the marsh and in the marsh interior. The analysis agreed with many of the trends found throughout the region including the reduction of high marsh and decline of salt marsh. The reduction in Phragmites could be due to the species shrinking niche between rising seas and dune vegetation on barrier islands. The complex management issues facing salt marsh across the United States including sea level rise and eutrophication necessitate very high resolution classification and change detection of salt marsh to inform management decisions such as restoration, salt marsh migration, and nutrient inputs.

[Spatial pattern of land surface dead combustible fuel load in Huzhong forest area in Great Xing'an Mountains].

PubMed

Liu, Zhi-Hua; Chang, Yu; Chen, Hong-Wei; Zhou, Rui; Jing, Guo-Zhi; Zhang, Hong-Xin; Zhang, Chang-Meng

2008-03-01

By using geo-statistics and based on time-lag classification standard, a comparative study was made on the land surface dead combustible fuels in Huzhong forest area in Great Xing'an Mountains. The results indicated that the first level land surface dead combustible fuel, i. e., 1 h time-lag dead fuel, presented stronger spatial auto-correlation, with an average of 762.35 g x m(-2) and contributing to 55.54% of the total load. Its determining factors were species composition and stand age. The second and third levels land surface dead combustible fuel, i. e., 10 h and 100 h time-lag dead fuels, had a sum of 610.26 g x m(-2), and presented weaker spatial auto-correlation than 1 h time-lag dead fuel. Their determining factor was the disturbance history of forest stand. The complexity and heterogeneity of the factors determining the quality and quantity of forest land surface dead combustible fuels were the main reasons for the relatively inaccurate interpolation. However, the utilization of field survey data coupled with geo-statistics could easily and accurately interpolate the spatial pattern of forest land surface dead combustible fuel loads, and indirectly provide a practical basis for forest management.

25m-resolution Global Mosaic and Forest/Non-Forest map using PALSAR-2 data set

NASA Astrophysics Data System (ADS)

Itoh, T.; Shimada, M.; Motooka, T.; Hayashi, M.; Tadono, T.; DAN, R.; Isoguchi, O.; Yamanokuchi, T.

2017-12-01

A continuous observation of forests is important as information necessary for monitoring deforestation, climate change and environmental changes i.e. Reducing Emissions from Deforestation and Forest Degradation in Developing Countries (REDD+). Japan Aerospace Exploration Agency (JAXA) is conducting research on forest monitoring using satellite-based L-Band Synthetic Aperture Radars (SARs) continuously. Using the FBD (Fine Beam Dual polarizations) data of the Phased Array type L-band Synthetic Aperture Radar (PALSAR) onboard the Advanced Land Observing Satellite (ALOS), JAXA created the global 25 m-resolution mosaic images and the Forest/Non-Forest (FNF) maps dataset for forest monitoring. SAR can monitor forest areas under all weather conditions, and L-band is highly sensitive to forests and their changes, therefore it is suitable for forest observation. JAXA also created the global 25 m mosaics and FNF maps using ALOS-2/PALSAR-2 launched on 2014 as a successor to ALOS. FNF dataset by PALSAR and PALSAR-2 covers from 2007 to 2010, and from 2015 to 2016, respectively. Therefore, it is possible to monitor forest changes during approx. 10 years. The classification method is combination of the object-based classification and the thresholding of HH and HV polarized images, and the result of FNF was compared with Forest Resource Assessment (FRA, developed by FAO) and their inconsistency is less than 10 %. Also, by comparing with the optical image of Google Earth, rate of coincidence was 80 % or more. We will create PALSAR-2 global mosaics and FNF dataset continuously to contribute global forest monitoring.

An Effort to Map and Monitor Baldcypress Forest Areas in Coastal Louisiana, Using Landsat, MODIS, and ASTER Satellite Data

NASA Technical Reports Server (NTRS)

Spruce, Joseph P.; Sader, Steve; Smoot, James

2012-01-01

This presentation discusses a collaborative project to develop, test, and demonstrate baldcypress forest mapping and monitoring products for aiding forest conservation and restoration in coastal Louisiana. Low lying coastal forests in the region are being negatively impacted by multiple factors, including subsidence, salt water intrusion, sea level rise, persistent flooding, hydrologic modification, annual insect-induced forest defoliation, timber harvesting, and conversion to urban land uses. Coastal baldcypress forests provide invaluable ecological services in terms of wildlife habitat, forest products, storm buffers, and water quality benefits. Before this project, current maps of baldcypress forest concentrations and change did not exist or were out of date. In response, this project was initiated to produce: 1) current maps showing the extent and location of baldcypress dominated forests; and 2) wetland forest change maps showing temporary and persistent disturbance and loss since the early 1970s. Project products are being developed collaboratively with multiple state and federal agencies. Products are being validated using available reference data from aerial, satellite, and field survey data. Results include Landsat TM- based classifications of baldcypress in terms of cover type and percent canopy cover. Landsat MSS data was employed to compute a circa 1972 classification of swamp and bottomland hardwood forest types. Landsat data for 1972-2010 was used to compute wetland forest change products. MODIS-based change products were applied to view and assess insect-induced swamp forest defoliation. MODIS, Landsat, and ASTER satellite data products were used to help assess hurricane and flood impacts to coastal wetland forests in the region.

Change in the Minneapolis/St. Paul Metropolitan Area Oak Forests from 1991 to 1998

Treesearch

Kathleen Ward; Jennifer Juzwik

2005-01-01

Based on classifications of Landsat TM imagery, the total area of oak forests in the Minneapolis/St. Paul, Minnesota, metropolitan area decreased by 5.6 percent between 1991 and 1998, and oak forest losses ranged from 12 to 1,229 ha in six of seven ecological subsections. Maps and spatial data layers are provided.

Per-field crop classification in irrigated agricultural regions in middle Asia using random forest and support vector machine ensemble

NASA Astrophysics Data System (ADS)

Löw, Fabian; Schorcht, Gunther; Michel, Ulrich; Dech, Stefan; Conrad, Christopher

2012-10-01

Accurate crop identification and crop area estimation are important for studies on irrigated agricultural systems, yield and water demand modeling, and agrarian policy development. In this study a novel combination of Random Forest (RF) and Support Vector Machine (SVM) classifiers is presented that (i) enhances crop classification accuracy and (ii) provides spatial information on map uncertainty. The methodology was implemented over four distinct irrigated sites in Middle Asia using RapidEye time series data. The RF feature importance statistics was used as feature-selection strategy for the SVM to assess possible negative effects on classification accuracy caused by an oversized feature space. The results of the individual RF and SVM classifications were combined with rules based on posterior classification probability and estimates of classification probability entropy. SVM classification performance was increased by feature selection through RF. Further experimental results indicate that the hybrid classifier improves overall classification accuracy in comparison to the single classifiers as well as useŕs and produceŕs accuracy.

Development of a stand-scale forest biodiversity index based on the state forest inventory

Treesearch

Diego Van Den Meersschaut; Kris Vandekerkhove

2000-01-01

Ecological aspects are increasingly influencing silvicultural management. Estimating forest biodiversity has become one often major tools for evaluating management strategies. A stand-scale forest biodiversity index is developed, based on available data from the state forest inventory. The index combines aspects of forest structure, woody and herbal layer composition,...

An efficient ensemble learning method for gene microarray classification.

PubMed

Osareh, Alireza; Shadgar, Bita

2013-01-01

The gene microarray analysis and classification have demonstrated an effective way for the effective diagnosis of diseases and cancers. However, it has been also revealed that the basic classification techniques have intrinsic drawbacks in achieving accurate gene classification and cancer diagnosis. On the other hand, classifier ensembles have received increasing attention in various applications. Here, we address the gene classification issue using RotBoost ensemble methodology. This method is a combination of Rotation Forest and AdaBoost techniques which in turn preserve both desirable features of an ensemble architecture, that is, accuracy and diversity. To select a concise subset of informative genes, 5 different feature selection algorithms are considered. To assess the efficiency of the RotBoost, other nonensemble/ensemble techniques including Decision Trees, Support Vector Machines, Rotation Forest, AdaBoost, and Bagging are also deployed. Experimental results have revealed that the combination of the fast correlation-based feature selection method with ICA-based RotBoost ensemble is highly effective for gene classification. In fact, the proposed method can create ensemble classifiers which outperform not only the classifiers produced by the conventional machine learning but also the classifiers generated by two widely used conventional ensemble learning methods, that is, Bagging and AdaBoost.

Random Forest Application for NEXRAD Radar Data Quality Control

NASA Astrophysics Data System (ADS)

Keem, M.; Seo, B. C.; Krajewski, W. F.

2017-12-01

Identification and elimination of non-meteorological radar echoes (e.g., returns from ground, wind turbines, and biological targets) are the basic data quality control steps before radar data use in quantitative applications (e.g., precipitation estimation). Although WSR-88Ds' recent upgrade to dual-polarization has enhanced this quality control and echo classification, there are still challenges to detect some non-meteorological echoes that show precipitation-like characteristics (e.g., wind turbine or anomalous propagation clutter embedded in rain). With this in mind, a new quality control method using Random Forest is proposed in this study. This classification algorithm is known to produce reliable results with less uncertainty. The method introduces randomness into sampling and feature selections and integrates consequent multiple decision trees. The multidimensional structure of the trees can characterize the statistical interactions of involved multiple features in complex situations. The authors explore the performance of Random Forest method for NEXRAD radar data quality control. Training datasets are selected using several clear cases of precipitation and non-precipitation (but with some non-meteorological echoes). The model is structured using available candidate features (from the NEXRAD data) such as horizontal reflectivity, differential reflectivity, differential phase shift, copolar correlation coefficient, and their horizontal textures (e.g., local standard deviation). The influence of each feature on classification results are quantified by variable importance measures that are automatically estimated by the Random Forest algorithm. Therefore, the number and types of features in the final forest can be examined based on the classification accuracy. The authors demonstrate the capability of the proposed approach using several cases ranging from distinct to complex rain/no-rain events and compare the performance with the existing algorithms (e.g., MRMS). They also discuss operational feasibility based on the observed strength and weakness of the method.

Optimizing classification performance in an object-based very-high-resolution land use-land cover urban application

NASA Astrophysics Data System (ADS)

Georganos, Stefanos; Grippa, Tais; Vanhuysse, Sabine; Lennert, Moritz; Shimoni, Michal; Wolff, Eléonore

2017-10-01

This study evaluates the impact of three Feature Selection (FS) algorithms in an Object Based Image Analysis (OBIA) framework for Very-High-Resolution (VHR) Land Use-Land Cover (LULC) classification. The three selected FS algorithms, Correlation Based Selection (CFS), Mean Decrease in Accuracy (MDA) and Random Forest (RF) based Recursive Feature Elimination (RFE), were tested on Support Vector Machine (SVM), K-Nearest Neighbor, and Random Forest (RF) classifiers. The results demonstrate that the accuracy of SVM and KNN classifiers are the most sensitive to FS. The RF appeared to be more robust to high dimensionality, although a significant increase in accuracy was found by using the RFE method. In terms of classification accuracy, SVM performed the best using FS, followed by RF and KNN. Finally, only a small number of features is needed to achieve the highest performance using each classifier. This study emphasizes the benefits of rigorous FS for maximizing performance, as well as for minimizing model complexity and interpretation.

The Cooperative Forest Ecosystem Research Program

USGS Publications Warehouse

,

2002-01-01

Changes in priorities for forest management on federal and state lands in the Pacific Northwest have raised many questions about the best ways to manage young-forest stands, riparian areas, and forest landscapes. The Cooperative Forest Ecosystem Research (CFER) Program draws together scientists and managers from the U.S. Geological Survey, Bureau of Land Management, Oregon Department of Forestry, and Oregon State University to find science-based answers to these questions. Managers, researchers, and decisionmakers, working within the CFER program, are helping develop and disseminate the knowledge needed to carry out ecosystem-based management successfully in the Pacific Northwest.

K-Nearest Neighbor Estimation of Forest Attributes: Improving Mapping Efficiency

Treesearch

Andrew O. Finley; Alan R. Ek; Yun Bai; Marvin E. Bauer

2005-01-01

This paper describes our efforts in refining k-nearest neighbor forest attributes classification using U.S. Department of Agriculture Forest Service Forest Inventory and Analysis plot data and Landsat 7 Enhanced Thematic Mapper Plus imagery. The analysis focuses on FIA-defined forest type classification across St. Louis County in northeastern Minnesota. We outline...

Mixed-conifer forests of central Oregon: effects of logging and fire exclusion vary with environment.

PubMed

Merschel, Andrew G; Spies, Thomas A; Heyerdahl, Emily K

Twentieth-century land management has altered the structure and composition of mixed-conifer forests and decreased their resilience to fire, drought, and insects in many parts of the Interior West. These forests occur across a wide range of environmental settings and historical disturbance regimes, so their response to land management is likely to vary across landscapes and among ecoregions. However, this variation has not been well characterized and hampers the development of appropriate management and restoration plans. We identified mixed-conifer types in central Oregon based on historical structure and composition, and successional trajectories following recent changes in land use, and evaluated how these types were distributed across environmental gradients. We used field data from 171 sites sampled across a range of environmental settings in two subregions: the eastern Cascades and the Ochoco Mountains. We identified four forest types in the eastern Cascades and four analogous types with lower densities in the Ochoco Mountains. All types historically contained ponderosa pine, but differed in the historical and modern proportions of shade-tolerant vs. shade-intolerant tree species. The Persistent Ponderosa Pine and Recent Douglas-fir types occupied relatively hot–dry environments compared to Recent Grand Fir and Persistent Shade Tolerant sites, which occupied warm–moist and cold–wet environments, respectively. Twentieth-century selective harvesting halved the density of large trees, with some variation among forest types. In contrast, the density of small trees doubled or tripled early in the 20th century, probably due to land-use change and a relatively cool, wet climate. Contrary to the common perception that dry ponderosa pine forests are the most highly departed from historical conditions, we found a greater departure in the modern composition of small trees in warm–moist environments than in either hot–dry or cold–wet environments. Furthermore, shade-tolerant trees began infilling earlier in cold–wet than in hot–dry environments and also in topographically shaded sites in the Ochoco Mountains. Our new classification could be used to prioritize management that seeks to restore structure and composition or create resilience in mixed-conifer forests of the region.

Gambel oak growth forms: Management opportunities for increasing ecosystem diversity

Treesearch

Scott R. Abella

2008-01-01

Gambel oak (Quercus gambelii) clones have several different growth forms in southwestern ponderosa pine (Pinus ponderosa) forests, and these growth forms each provide unique wildlife habitat and resource values. The purposes of this note are to review published growth-form classifications for Gambel oak, provide examples of...

Analysis of Landsat-4 Thematic Mapper data for classification of forest stands in Baldwin County, Alabama

NASA Technical Reports Server (NTRS)

Hill, C. L.

1984-01-01

A computer-implemented classification has been derived from Landsat-4 Thematic Mapper data acquired over Baldwin County, Alabama on January 15, 1983. One set of spectral signatures was developed from the data by utilizing a 3x3 pixel sliding window approach. An analysis of the classification produced from this technique identified forested areas. Additional information regarding only the forested areas. Additional information regarding only the forested areas was extracted by employing a pixel-by-pixel signature development program which derived spectral statistics only for pixels within the forested land covers. The spectral statistics from both approaches were integrated and the data classified. This classification was evaluated by comparing the spectral classes produced from the data against corresponding ground verification polygons. This iterative data analysis technique resulted in an overall classification accuracy of 88.4 percent correct for slash pine, young pine, loblolly pine, natural pine, and mixed hardwood-pine. An accuracy assessment matrix has been produced for the classification.

Classification of forest-based ecotourism areas in Pocahontas County of West Virginia using GIS and pairwise comparison method

Treesearch

Ishwar Dhami; Jinyang. Deng

2012-01-01

Many previous studies have examined ecotourism primarily from the perspective of tourists while largely ignoring ecotourism destinations. This study used geographical information system (GIS) and pairwise comparison to identify forest-based ecotourism areas in Pocahontas County, West Virginia. The study adopted the criteria and scores developed by Boyd and Butler (1994...

A study of Minnesota forests and lakes using data from Earth Resources Technology Satellites

NASA Technical Reports Server (NTRS)

1974-01-01

Highlights of research and practical benefits are discussed for the following projects which utilized ERTS 1 data to provide municipal, state, federal, and industrial users with environmental resource information for the state of Minnesota: (1) forest disease detection and control; (2) evaluation of water quality by remote sensing techniques; (3) forest vegetation classification and management; (4) detection of saline soils in the Red River Valley; (5) snowmelt flood prediction; (6) remote sensing applications to hydrology; (7) Rice Creek watershed project; (8) water quality in Lake Superior and the Duluth Superior Harbor; and (9) determination of Lake Superior currents from turbidity patterns.

Mapping deforestation and urban expansion in Freetown, Sierra Leone, from pre- to post-war economic recovery.

PubMed

Mansaray, Lamin R; Huang, Jingfeng; Kamara, Alimamy A

2016-08-01

Freetown, the capital of Sierra Leone has experienced vast land-cover changes over the past three decades. In Sierra Leone, however, availability of updated land-cover data is still a problem even for environmental managers. This study was therefore, conducted to provide up-to-date land-cover data for Freetown. Multi-temporal Landsat data at 1986, 2001, and 2015 were obtained, and a maximum likelihood supervised classification was employed. Eight land-cover classes or categories were recognized as follows: water, wetland, built-up, dense forest, sparse forest, grassland, barren, and mangrove. Land-cover changes were mapped via post-classification change detection. The persistence, gain, and loss of each land-cover class, and selected land conversions were also quantified. An overall classification accuracy of 87.3 % and a Kappa statistic of 0.85 were obtained for the 2015 map. From 1986 to 2015, water, built-up, grassland, and barren had net gains, whereas forests, wetlands, and mangrove had net loses. Conversion analyses among forests, grassland, and built-up show that built-up had targeted grassland and avoided forests. This study also revealed that, the overall land-cover change at 2001-2015 was higher (28.5 %) than that recorded at 1986-2001 (20.9 %). This is attributable to the population increase in Freetown and the high economic growth and infrastructural development recorded countrywide after the civil war. In view of the rapid land-cover change and its associated environmental impacts, this study recommends the enactment of policies that would strike a balance between urbanization and environmental sustainability in Freetown.

A neural network approach for enhancing information extraction from multispectral image data

USGS Publications Warehouse

Liu, J.; Shao, G.; Zhu, H.; Liu, S.

2005-01-01

A back-propagation artificial neural network (ANN) was applied to classify multispectral remote sensing imagery data. The classification procedure included four steps: (i) noisy training that adds minor random variations to the sampling data to make the data more representative and to reduce the training sample size; (ii) iterative or multi-tier classification that reclassifies the unclassified pixels by making a subset of training samples from the original training set, which means the neural model can focus on fewer classes; (iii) spectral channel selection based on neural network weights that can distinguish the relative importance of each channel in the classification process to simplify the ANN model; and (iv) voting rules that adjust the accuracy of classification and produce outputs of different confidence levels. The Purdue Forest, located west of Purdue University, West Lafayette, Indiana, was chosen as the test site. The 1992 Landsat thematic mapper imagery was used as the input data. High-quality airborne photographs of the same Lime period were used for the ground truth. A total of 11 land use and land cover classes were defined, including water, broadleaved forest, coniferous forest, young forest, urban and road, and six types of cropland-grassland. The experiment, indicated that the back-propagation neural network application was satisfactory in distinguishing different land cover types at US Geological Survey levels II-III. The single-tier classification reached an overall accuracy of 85%. and the multi-tier classification an overall accuracy of 95%. For the whole test, region, the final output of this study reached an overall accuracy of 87%. ?? 2005 CASI.

[A review on fundamental studies of secondary forest management].

PubMed

Zhu, Jiaojun

2002-12-01

Secondary forest is also called as natural secondary forest, which regenerates on native forest that has been disturbed by severe natural or anthropogenic disturbances. The structural and dynamic organizations, growth, productivity and stand environment of secondary forests are significantly different from those of natural and artificial forests. Such significant differences make secondary forests have their own special characteristics in forestry. Secondary forests are the main body of forests in China. Therefore, their management plays a very important role in the projects of natural forest conservation and the construction of ecological environment in China or in the world. Based on a wide range of literature collection on secondary forest research, the fundamental studies of secondary forest management were discussed. The major topics are as follows: 1) basic characteristics of secondary forest, 2) principles of secondary forest management, 3) types of secondary forest, 4) community structure and succession dynamics of secondary forest, including niches, biodiversity, succession and so on, 5) main ecological processes of secondary forest, including regeneration, forest soil and forest environment. Additionally, the research needs and tendency related to secondary forest in the future were also given, based on the analyses of the main results and the problems in current management of secondary forest. The review may be helpful to the research of secondary forest management, and to the projects of natural forest conservation in China.

Forest structure and development: implications for forest management

Treesearch

Kevin L. O' Hara

2004-01-01

A general premise of forest managers is that modern silviculture should be based, in large part, on natural disturbance patterns and species' adaptations to these disturbances. An understanding of forest stand dynamics is therefore a prerequisite to sound forest management. This paper provides a brief overview of forest stand development, stand structures, and...

Atypical forest products, processes, and uses: a developing component of National Forest management

Treesearch

Mike Higgs; John Sebelius; Mike Miller

1995-01-01

The silvicultural practices prescribed under an ecosystem management regimen will alter the volume and character of National Forests' marketable raw material base. This alteration will affect forest-dependent communities that have traditionally relied upon these resources for their economic and social well being. Community based atypical forest products, processes...

Aspen community types of the Intermountain Region

Treesearch

Walter F. Mueggler

1988-01-01

This vegetation classification is based upon existing community structure and composition in the aspen-dominated forests of the Intermountain Region of the Forest Service. The 56 community types occur within eight tree-cover types. A diagnostic key using indicator species facilitates field identification of the community types. Vegetational composition, productivity,...

Comparative Performance Analysis of Support Vector Machine, Random Forest, Logistic Regression and k-Nearest Neighbours in Rainbow Trout (Oncorhynchus Mykiss) Classification Using Image-Based Features

PubMed Central

Císař, Petr; Labbé, Laurent; Souček, Pavel; Pelissier, Pablo; Kerneis, Thierry

2018-01-01

The main aim of this study was to develop a new objective method for evaluating the impacts of different diets on the live fish skin using image-based features. In total, one-hundred and sixty rainbow trout (Oncorhynchus mykiss) were fed either a fish-meal based diet (80 fish) or a 100% plant-based diet (80 fish) and photographed using consumer-grade digital camera. Twenty-three colour features and four texture features were extracted. Four different classification methods were used to evaluate fish diets including Random forest (RF), Support vector machine (SVM), Logistic regression (LR) and k-Nearest neighbours (k-NN). The SVM with radial based kernel provided the best classifier with correct classification rate (CCR) of 82% and Kappa coefficient of 0.65. Although the both LR and RF methods were less accurate than SVM, they achieved good classification with CCR 75% and 70% respectively. The k-NN was the least accurate (40%) classification model. Overall, it can be concluded that consumer-grade digital cameras could be employed as the fast, accurate and non-invasive sensor for classifying rainbow trout based on their diets. Furthermore, these was a close association between image-based features and fish diet received during cultivation. These procedures can be used as non-invasive, accurate and precise approaches for monitoring fish status during the cultivation by evaluating diet’s effects on fish skin. PMID:29596375

Comparative Performance Analysis of Support Vector Machine, Random Forest, Logistic Regression and k-Nearest Neighbours in Rainbow Trout (Oncorhynchus Mykiss) Classification Using Image-Based Features.

PubMed

Saberioon, Mohammadmehdi; Císař, Petr; Labbé, Laurent; Souček, Pavel; Pelissier, Pablo; Kerneis, Thierry

2018-03-29

The main aim of this study was to develop a new objective method for evaluating the impacts of different diets on the live fish skin using image-based features. In total, one-hundred and sixty rainbow trout ( Oncorhynchus mykiss ) were fed either a fish-meal based diet (80 fish) or a 100% plant-based diet (80 fish) and photographed using consumer-grade digital camera. Twenty-three colour features and four texture features were extracted. Four different classification methods were used to evaluate fish diets including Random forest (RF), Support vector machine (SVM), Logistic regression (LR) and k -Nearest neighbours ( k -NN). The SVM with radial based kernel provided the best classifier with correct classification rate (CCR) of 82% and Kappa coefficient of 0.65. Although the both LR and RF methods were less accurate than SVM, they achieved good classification with CCR 75% and 70% respectively. The k -NN was the least accurate (40%) classification model. Overall, it can be concluded that consumer-grade digital cameras could be employed as the fast, accurate and non-invasive sensor for classifying rainbow trout based on their diets. Furthermore, these was a close association between image-based features and fish diet received during cultivation. These procedures can be used as non-invasive, accurate and precise approaches for monitoring fish status during the cultivation by evaluating diet's effects on fish skin.

Decision-Tree, Rule-Based, and Random Forest Classification of High-Resolution Multispectral Imagery for Wetland Mapping and Inventory

EPA Science Inventory

Efforts are increasingly being made to classify the world’s wetland resources, an important ecosystem and habitat that is diminishing in abundance. There are multiple remote sensing classification methods, including a suite of nonparametric classifiers such as decision-tree...

A non-parametric, supervised classification of vegetation types on the Kaibab National Forest using decision trees

Treesearch

Suzanne M. Joy; R. M. Reich; Richard T. Reynolds

2003-01-01

Traditional land classification techniques for large areas that use Landsat Thematic Mapper (TM) imagery are typically limited to the fixed spatial resolution of the sensors (30m). However, the study of some ecological processes requires land cover classifications at finer spatial resolutions. We model forest vegetation types on the Kaibab National Forest (KNF) in...

First steps towards a novel European forest fuel classification systems and a European forest fuel map

NASA Astrophysics Data System (ADS)

Sebastián-López, Ana; Urbieta, Itziar R.; de La Fuente Blanco, David; García Mateo, Rubén.; Moreno Rodríguez, José Manuel; Eftichidis, George; Varela, Vassiliki; Cesari, Véronique; Mário Ribeiro, Luís.; Viegas, Domingos Xavier; Lanorte, Antonio; Lasaponara, Rosa; Camia, Andrea; San Miguel, Jesús

2010-05-01

Forest fires burn at the local scale, but their massive occurrence causes effects which have global dimensions. Furthermore climate change projections associate global warming to a significant increase in forest fire activity. Warmer and drier conditions are expected to increase the frequency, duration and intensity of fires, and greater amounts of fuel associated with forest areas in decline may cause more frequent and larger fires. These facts create the need for establishing strategies for harmonizing fire danger rating, fire risk assessment, and fire prevention policies at a supranational level. Albeit forest fires are a permanent threat for European ecosystems, particularly in the south, there is no commonly accepted fuel classification scheme adopted for operational use by the Member States of the EU. The European Commission (EC) DG Environment and JRC have launched a set of studies following a resolution of the European Parliament on the further development and enhancement of the European Forest Fire Information System (EFFIS), the EC focal point for information on forest fires in Europe. One of the studies that are being funded is the FUELMAP project. The objective of FUELMAP is to develop a novel fuel classification system and a new European fuel map that will be based on a comprehensive classification of fuel complexes representing the various vegetation types across EU27, plus Switzerland, Croatia and Turkey. The overall work plan is grounded on a throughout knowledge of European forest landscapes and the key features of fuel situations occurring in natural areas. The method makes extended use of existing databases available in the Member States and European Institutions. Specifically, our proposed classification combines relevant information on ecoregions, land cover and uses, potential and actual vegetation, and stand structure. GIS techniques are used in order to define the geographic extent of the classification units and for identifying the main driving factors that determine the spatial distribution of the resulting fuel complexes. Furthermore, relevant parameters influencing fire potential and effects such as fuel load, live/dead ratio, and fuels' size classes' distribution are considered. National- and local-scale datasets (vegetation maps, forest inventory plots, fuel maps...) will be also studied and compared. Local ground- truth data will be used to assess the accuracy of the classification and will contribute, along with literature values and experts' opinion, to characterize the fuels' physical properties. The resulting classification aims to support the characterization of the fire potential, serve as input in fire emissions models, and be used to assess the expected impact of fire in the European landscapes. The work plan includes the development of a GIS software tool to automatically update the fuel map from modified (up-to-date) input data layers. The fuel map of Europe is mainly intended to support the implementation of the EFFIS modules that can be enhanced by the use of improved information on forest fuel properties and spatial distribution, though it is also envisaged that the results of the project might be useful for other relevant applications at different spatial scales. To this purpose, the classification will be designed with a hierarchical and flexible structure for describing heterogeneous landscapes. The work is on-going and this presentation shows the first results towards the envisaged European fuel map.

Dynamic species classification of microorganisms across time, abiotic and biotic environments—A sliding window approach

PubMed Central

Griffiths, Jason I.; Fronhofer, Emanuel A.; Garnier, Aurélie; Seymour, Mathew; Altermatt, Florian; Petchey, Owen L.

2017-01-01

The development of video-based monitoring methods allows for rapid, dynamic and accurate monitoring of individuals or communities, compared to slower traditional methods, with far reaching ecological and evolutionary applications. Large amounts of data are generated using video-based methods, which can be effectively processed using machine learning (ML) algorithms into meaningful ecological information. ML uses user defined classes (e.g. species), derived from a subset (i.e. training data) of video-observed quantitative features (e.g. phenotypic variation), to infer classes in subsequent observations. However, phenotypic variation often changes due to environmental conditions, which may lead to poor classification, if environmentally induced variation in phenotypes is not accounted for. Here we describe a framework for classifying species under changing environmental conditions based on the random forest classification. A sliding window approach was developed that restricts temporal and environmentally conditions to improve the classification. We tested our approach by applying the classification framework to experimental data. The experiment used a set of six ciliate species to monitor changes in community structure and behavior over hundreds of generations, in dozens of species combinations and across a temperature gradient. Differences in biotic and abiotic conditions caused simplistic classification approaches to be unsuccessful. In contrast, the sliding window approach allowed classification to be highly successful, as phenotypic differences driven by environmental change, could be captured by the classifier. Importantly, classification using the random forest algorithm showed comparable success when validated against traditional, slower, manual identification. Our framework allows for reliable classification in dynamic environments, and may help to improve strategies for long-term monitoring of species in changing environments. Our classification pipeline can be applied in fields assessing species community dynamics, such as eco-toxicology, ecology and evolutionary ecology. PMID:28472193

Landsat-faciliated vegetation classification of the Kenai National Wildlife Refuge and adjacent areas, Alaska

USGS Publications Warehouse

Talbot, S. S.; Shasby, M.B.; Bailey, T.N.

1985-01-01

A Landsat-based vegetation map was prepared for Kenai National Wildlife Refuge and adjacent lands, 2 million and 2.5 million acres respectively. The refuge lies within the middle boreal sub zone of south central Alaska. Seven major classes and sixteen subclasses were recognized: forest (closed needleleaf, needleleaf woodland, mixed); deciduous scrub (lowland and montane, subalpine); dwarf scrub (dwarf shrub tundra, lichen tundra, dwarf shrub and lichen tundra, dwarf shrub peatland, string bog/wetlands); herbaceous (graminoid meadows and marshes); scarcely vegetated areas ; water (clear, moderately turbid, highly turbid); and glaciers. The methodology employed a cluster-block technique. Sample areas were described based on a combination of helicopter-ground survey, aerial photo interpretation, and digital Landsat data. Major steps in the Landsat analysis involved: preprocessing (geometric connection), spectral class labeling of sample areas, derivation of statistical parameters for spectral classes, preliminary classification of the entree study area using a maximum-likelihood algorithm, and final classification through ancillary information such as digital elevation data. The vegetation map (scale 1:250,000) was a pioneering effort since there were no intermediate-sclae maps of the area. Representative of distinctive regional patterns, the map was suitable for use in comprehensive conservation planning and wildlife management.

A Minimum Spanning Forest Based Method for Noninvasive Cancer Detection with Hyperspectral Imaging

PubMed Central

Pike, Robert; Lu, Guolan; Wang, Dongsheng; Chen, Zhuo Georgia; Fei, Baowei

2016-01-01

Goal The purpose of this paper is to develop a classification method that combines both spectral and spatial information for distinguishing cancer from healthy tissue on hyperspectral images in an animal model. Methods An automated algorithm based on a minimum spanning forest (MSF) and optimal band selection has been proposed to classify healthy and cancerous tissue on hyperspectral images. A support vector machine (SVM) classifier is trained to create a pixel-wise classification probability map of cancerous and healthy tissue. This map is then used to identify markers that are used to compute mutual information for a range of bands in the hyperspectral image and thus select the optimal bands. An MSF is finally grown to segment the image using spatial and spectral information. Conclusion The MSF based method with automatically selected bands proved to be accurate in determining the tumor boundary on hyperspectral images. Significance Hyperspectral imaging combined with the proposed classification technique has the potential to provide a noninvasive tool for cancer detection. PMID:26285052

Can a Forest/Nonforest Change Map Improve the Precision of Forest Area, Volume, Growth, Removals, and Mortality Estimates?

Treesearch

Dale D. Gormanson; Mark H. Hansen; Ronald E. McRoberts

2005-01-01

In an extensive forest inventory, stratifications that use dual-date forest/nonforest classifications of Landsat Thematic Mapper data approximately 10 years apart are tested against similar classifications that use data from only one date. Alternative stratifications that further define edge strata as pixels adjacent to a forest/nonforest boundary are included in the...

Global environmental change effects on plant community composition trajectories depend upon management legacies.

PubMed

Perring, Michael P; Bernhardt-Römermann, Markus; Baeten, Lander; Midolo, Gabriele; Blondeel, Haben; Depauw, Leen; Landuyt, Dries; Maes, Sybryn L; De Lombaerde, Emiel; Carón, Maria Mercedes; Vellend, Mark; Brunet, Jörg; Chudomelová, Markéta; Decocq, Guillaume; Diekmann, Martin; Dirnböck, Thomas; Dörfler, Inken; Durak, Tomasz; De Frenne, Pieter; Gilliam, Frank S; Hédl, Radim; Heinken, Thilo; Hommel, Patrick; Jaroszewicz, Bogdan; Kirby, Keith J; Kopecký, Martin; Lenoir, Jonathan; Li, Daijiang; Máliš, František; Mitchell, Fraser J G; Naaf, Tobias; Newman, Miles; Petřík, Petr; Reczyńska, Kamila; Schmidt, Wolfgang; Standovár, Tibor; Świerkosz, Krzysztof; Van Calster, Hans; Vild, Ondřej; Wagner, Eva Rosa; Wulf, Monika; Verheyen, Kris

2018-04-01

The contemporary state of functional traits and species richness in plant communities depends on legacy effects of past disturbances. Whether temporal responses of community properties to current environmental changes are altered by such legacies is, however, unknown. We expect global environmental changes to interact with land-use legacies given different community trajectories initiated by prior management, and subsequent responses to altered resources and conditions. We tested this expectation for species richness and functional traits using 1814 survey-resurvey plot pairs of understorey communities from 40 European temperate forest datasets, syntheses of management transitions since the year 1800, and a trait database. We also examined how plant community indicators of resources and conditions changed in response to management legacies and environmental change. Community trajectories were clearly influenced by interactions between management legacies from over 200 years ago and environmental change. Importantly, higher rates of nitrogen deposition led to increased species richness and plant height in forests managed less intensively in 1800 (i.e., high forests), and to decreases in forests with a more intensive historical management in 1800 (i.e., coppiced forests). There was evidence that these declines in community variables in formerly coppiced forests were ameliorated by increased rates of temperature change between surveys. Responses were generally apparent regardless of sites' contemporary management classifications, although sometimes the management transition itself, rather than historic or contemporary management types, better explained understorey responses. Main effects of environmental change were rare, although higher rates of precipitation change increased plant height, accompanied by increases in fertility indicator values. Analysis of indicator values suggested the importance of directly characterising resources and conditions to better understand legacy and environmental change effects. Accounting for legacies of past disturbance can reconcile contradictory literature results and appears crucial to anticipating future responses to global environmental change. © 2017 John Wiley & Sons Ltd.

An initial analysis of LANDSAT 4 Thematic Mapper data for the classification of agricultural, forested wetland, and urban land covers

NASA Technical Reports Server (NTRS)

Quattrochi, D. A.; Anderson, J. E.; Brannon, D. P.; Hill, C. L.

1982-01-01

An initial analysis of LANDSAT 4 thematic mapper (TM) data for the delineation and classification of agricultural, forested wetland, and urban land covers was conducted. A study area in Poinsett County, Arkansas was used to evaluate a classification of agricultural lands derived from multitemporal LANDSAT multispectral scanner (MSS) data in comparison with a classification of TM data for the same area. Data over Reelfoot Lake in northwestern Tennessee were utilized to evaluate the TM for delineating forested wetland species. A classification of the study area was assessed for accuracy in discriminating five forested wetland categories. Finally, the TM data were used to identify urban features within a small city. A computer generated classification of Union City, Tennessee was analyzed for accuracy in delineating urban land covers. An evaluation of digitally enhanced TM data using principal components analysis to facilitate photointerpretation of urban features was also performed.

Analysis of spatio-temporal land cover changes for hydrological impact assessment within the Nyando River Basin of Kenya.

PubMed

Olang, Luke Omondi; Kundu, Peter; Bauer, Thomas; Fürst, Josef

2011-08-01

The spatio-temporal changes in the land cover states of the Nyando Basin were investigated for auxiliary hydrological impact assessment. The predominant land cover types whose conversions could influence the hydrological response of the region were selected. Six Landsat images for 1973, 1986, and 2000 were processed to discern the changes based on a methodology that employs a hybrid of supervised and unsupervised classification schemes. The accuracy of the classifications were assessed using reference datasets processed in a GIS with the help of ground-based information obtained through participatory mapping techniques. To assess the possible hydrological effect of the detected changes during storm events, a physically based lumped approach for infiltration loss estimation was employed within five selected sub-basins. The results obtained indicated that forests in the basin declined by 20% while agricultural fields expanded by 16% during the entire period of study. Apparent from the land cover conversion matrices was that the majority of the forest decline was a consequence of agricultural expansion. The model results revealed decreased infiltration amounts by between 6% and 15%. The headwater regions with the vast deforestation were noted to be more vulnerable to the land cover change effects. Despite the haphazard land use patterns and uncertainties related to poor data quality for environmental monitoring and assessment, the study exposed the vast degradation and hence the need for sustainable land use planning for enhanced catchment management purposes.

Timber production assessment of a plantation forest: An integrated framework with field-based inventory, multi-source remote sensing data and forest management history

NASA Astrophysics Data System (ADS)

Gao, Tian; Zhu, Jiaojun; Deng, Songqiu; Zheng, Xiao; Zhang, Jinxin; Shang, Guiduo; Huang, Liyan

2016-10-01

Timber production is the purpose for managing plantation forests, and its spatial and quantitative information is critical for advising management strategies. Previous studies have focused on growing stock volume (GSV), which represents the current potential of timber production, yet few studies have investigated historical process-harvested timber. This resulted in a gap in a synthetical ecosystem service assessment of timber production. In this paper, we established a Management Process-based Timber production (MPT) framework to integrate the current GSV and the harvested timber derived from historical logging regimes, trying to synthetically assess timber production for a historical period. In the MPT framework, age-class and current GSV determine the times of historical thinning and the corresponding harvested timber, by using a ;space-for-time; substitution. The total timber production can be estimated by the historical harvested timber in each thinning and the current GSV. To test this MPT framework, an empirical study on a larch plantation (LP) with area of 43,946 ha was conducted in North China for a period from 1962 to 2010. Field-based inventory data was integrated with ALOS PALSAR (Advanced Land-Observing Satellite Phased Array L-band Synthetic Aperture Radar) and Landsat-8 OLI (Operational Land Imager) data for estimating the age-class and current GSV of LP. The random forest model with PALSAR backscatter intensity channels and OLI bands as input predictive variables yielded an accuracy of 67.9% with a Kappa coefficient of 0.59 for age-class classification. The regression model using PALSAR data produced a root mean square error (RMSE) of 36.5 m3 ha-1. The total timber production of LP was estimated to be 7.27 × 106 m3, with 4.87 × 106 m3 in current GSV and 2.40 × 106 m3 in harvested timber through historical thinning. The historical process-harvested timber accounts to 33.0% of the total timber production, which component has been neglected in the assessments for current status of plantation forests. Synthetically considering the RMSE for predictive GSV and misclassification of age-class, the error in timber production were supposed to range from -55.2 to 56.3 m3 ha-1. The MPT framework can be used to assess timber production of other tree species at a larger spatial scale, providing crucial information for a better understanding of forest ecosystem service.

Quantifying and Characterizing Tonic Thermal Pain Across Subjects From EEG Data Using Random Forest Models.

PubMed

Vijayakumar, Vishal; Case, Michelle; Shirinpour, Sina; He, Bin

2017-12-01

Effective pain assessment and management strategies are needed to better manage pain. In addition to self-report, an objective pain assessment system can provide a more complete picture of the neurophysiological basis for pain. In this study, a robust and accurate machine learning approach is developed to quantify tonic thermal pain across healthy subjects into a maximum of ten distinct classes. A random forest model was trained to predict pain scores using time-frequency wavelet representations of independent components obtained from electroencephalography (EEG) data, and the relative importance of each frequency band to pain quantification is assessed. The mean classification accuracy for predicting pain on an independent test subject for a range of 1-10 is 89.45%, highest among existing state of the art quantification algorithms for EEG. The gamma band is the most important to both intersubject and intrasubject classification accuracy. The robustness and generalizability of the classifier are demonstrated. Our results demonstrate the potential of this tool to be used clinically to help us to improve chronic pain treatment and establish spectral biomarkers for future pain-related studies using EEG.

Detection and Classification of Motor Vehicle Noise in a Forested Landscape

NASA Astrophysics Data System (ADS)

Brown, Casey L.; Reed, Sarah E.; Dietz, Matthew S.; Fristrup, Kurt M.

2013-11-01

Noise emanating from human activity has become a common addition to natural soundscapes and has the potential to harm wildlife and erode human enjoyment of nature. In particular, motor vehicles traveling along roads and trails produce high levels of both chronic and intermittent noise, eliciting varied responses from a wide range of animal species. Anthropogenic noise is especially conspicuous in natural areas where ambient background sound levels are low. In this article, we present an acoustic method to detect and analyze motor vehicle noise. Our approach uses inexpensive consumer products to record sound, sound analysis software to automatically detect sound events within continuous recordings and measure their acoustic properties, and statistical classification methods to categorize sound events. We describe an application of this approach to detect motor vehicle noise on paved, gravel, and natural-surface roads, and off-road vehicle trails in 36 sites distributed throughout a national forest in the Sierra Nevada, CA, USA. These low-cost, unobtrusive methods can be used by scientists and managers to detect anthropogenic noise events for many potential applications, including ecological research, transportation and recreation planning, and natural resource management.

Disturbance dynamics and ecosystem-based forest management

Treesearch

Kalev Jogiste; W. Keith Moser; Malle Mandre

2005-01-01

Ecosystem-based management is intended to balance ecological, social and economic values of sustainable resource management. The desired future state of forest ecosystem is usually defined through productivity, biodiversity, stability or other terms. However, ecosystem-based management may produce an unbalanced emphasis on different components. Although ecosystem-based...

Analyzing landscape changes in the Bafa Lake Nature Park of Turkey using remote sensing and landscape structure metrics.

PubMed

Esbah, Hayriye; Deniz, Bulent; Kara, Baris; Kesgin, Birsen

2010-06-01

Bafa Lake Nature Park is one of Turkey's most important legally protected areas. This study aimed at analyzing spatial change in the park environment by using object-based classification technique and landscape structure metrics. SPOT 2X (1994) and ASTER (2005) images are the primary research materials. Results show that artificial surfaces, low maqui, garrigue, and moderately high maqui covers have increased and coniferous forests, arable lands, permanent crop, and high maqui covers have decreased; coniferous forest, high maqui, grassland, and saline areas are in a disappearance stage of the land transformation; and the landscape pattern is more fragmented outside the park boundaries. The management actions should support ongoing vegetation regeneration, mitigate transformation of vegetation structure to less dense and discontinuous cover, control the dynamics at the agricultural-natural landscape interface, and concentrate on relatively low but steady increase of artificial surfaces.

CURE-SMOTE algorithm and hybrid algorithm for feature selection and parameter optimization based on random forests.

PubMed

Ma, Li; Fan, Suohai

2017-03-14

The random forests algorithm is a type of classifier with prominent universality, a wide application range, and robustness for avoiding overfitting. But there are still some drawbacks to random forests. Therefore, to improve the performance of random forests, this paper seeks to improve imbalanced data processing, feature selection and parameter optimization. We propose the CURE-SMOTE algorithm for the imbalanced data classification problem. Experiments on imbalanced UCI data reveal that the combination of Clustering Using Representatives (CURE) enhances the original synthetic minority oversampling technique (SMOTE) algorithms effectively compared with the classification results on the original data using random sampling, Borderline-SMOTE1, safe-level SMOTE, C-SMOTE, and k-means-SMOTE. Additionally, the hybrid RF (random forests) algorithm has been proposed for feature selection and parameter optimization, which uses the minimum out of bag (OOB) data error as its objective function. Simulation results on binary and higher-dimensional data indicate that the proposed hybrid RF algorithms, hybrid genetic-random forests algorithm, hybrid particle swarm-random forests algorithm and hybrid fish swarm-random forests algorithm can achieve the minimum OOB error and show the best generalization ability. The training set produced from the proposed CURE-SMOTE algorithm is closer to the original data distribution because it contains minimal noise. Thus, better classification results are produced from this feasible and effective algorithm. Moreover, the hybrid algorithm's F-value, G-mean, AUC and OOB scores demonstrate that they surpass the performance of the original RF algorithm. Hence, this hybrid algorithm provides a new way to perform feature selection and parameter optimization.

Object-based random forest classification of Landsat ETM+ and WorldView-2 satellite imagery for mapping lowland native grassland communities in Tasmania, Australia

NASA Astrophysics Data System (ADS)

Melville, Bethany; Lucieer, Arko; Aryal, Jagannath

2018-04-01

This paper presents a random forest classification approach for identifying and mapping three types of lowland native grassland communities found in the Tasmanian Midlands region. Due to the high conservation priority assigned to these communities, there has been an increasing need to identify appropriate datasets that can be used to derive accurate and frequently updateable maps of community extent. Therefore, this paper proposes a method employing repeat classification and statistical significance testing as a means of identifying the most appropriate dataset for mapping these communities. Two datasets were acquired and analysed; a Landsat ETM+ scene, and a WorldView-2 scene, both from 2010. Training and validation data were randomly subset using a k-fold (k = 50) approach from a pre-existing field dataset. Poa labillardierei, Themeda triandra and lowland native grassland complex communities were identified in addition to dry woodland and agriculture. For each subset of randomly allocated points, a random forest model was trained based on each dataset, and then used to classify the corresponding imagery. Validation was performed using the reciprocal points from the independent subset that had not been used to train the model. Final training and classification accuracies were reported as per class means for each satellite dataset. Analysis of Variance (ANOVA) was undertaken to determine whether classification accuracy differed between the two datasets, as well as between classifications. Results showed mean class accuracies between 54% and 87%. Class accuracy only differed significantly between datasets for the dry woodland and Themeda grassland classes, with the WorldView-2 dataset showing higher mean classification accuracies. The results of this study indicate that remote sensing is a viable method for the identification of lowland native grassland communities in the Tasmanian Midlands, and that repeat classification and statistical significant testing can be used to identify optimal datasets for vegetation community mapping.

Designing and Implementation of River Classification Assistant Management System

NASA Astrophysics Data System (ADS)

Zhao, Yinjun; Jiang, Wenyuan; Yang, Rujun; Yang, Nan; Liu, Haiyan

2018-03-01

In an earlier publication, we proposed a new Decision Classifier (DCF) for Chinese river classification based on their structures. To expand, enhance and promote the application of the DCF, we build a computer system to support river classification named River Classification Assistant Management System. Based on ArcEngine and ArcServer platform, this system implements many functions such as data management, extraction of river network, river classification, and results publication under combining Client / Server with Browser / Server framework.

Accuracy of Remotely Sensed Classifications For Stratification of Forest and Nonforest Lands

Treesearch

Raymond L. Czaplewski; Paul L. Patterson

2001-01-01

We specify accuracy standards for remotely sensed classifications used by FIA to stratify landscapes into two categories: forest and nonforest. Accuracy must be highest when forest area approaches 100 percent of the landscape. If forest area is rare in a landscape, then accuracy in the nonforest stratum must be very high, even at the expense of accuracy in the forest...

Sustainability assessment in forest management based on individual preferences.

PubMed

Martín-Fernández, Susana; Martinez-Falero, Eugenio

2018-01-15

This paper presents a methodology to elicit the preferences of any individual in the assessment of sustainable forest management at the stand level. The elicitation procedure was based on the comparison of the sustainability of pairs of forest locations. A sustainability map of the whole territory was obtained according to the individual's preferences. Three forest sustainability indicators were pre-calculated for each point in a study area in a Scots pine forest in the National Park of Sierra de Guadarrama in the Madrid Region in Spain to obtain the best management plan with the sustainability map. We followed a participatory process involving fifty people to assess the sustainability of the forest management and the methodology. The results highlighted the demand for conservative forest management, the usefulness of the methodology for managers, and the importance and necessity of incorporating stakeholders into forestry decision-making processes. Copyright © 2017 Elsevier Ltd. All rights reserved.

Carbon profile of the managed forest sector in Canada in the 20th century: sink or source?

PubMed

Chen, Jiaxin; Colombo, Stephen J; Ter-Mikaelian, Michael T; Heath, Linda S

2014-08-19

Canada contains 10% of global forests and has been one of the world's largest harvested wood products (HWP) producers. Therefore, Canada's managed forest sector, the managed forest area and HWP, has the potential to significantly increase or reduce atmospheric greenhouse gases. Using the most comprehensive carbon balance analysis to date, this study shows Canada's managed forest area and resulting HWP were a sink of 7510 and 849 teragrams carbon (TgC), respectively, in the period 1901-2010, exceeding Canada's fossil fuel-based emissions over this period (7333 TgC). If Canadian HWP were not produced and used for residential construction, and instead more energy intensive materials were used, there would have been an additional 790 TgC fossil fuel-based emissions. Because the forest carbon increases in the 20th century were mainly due to younger growing forests that resulted from disturbances in the 19th century, and future increases in forest carbon stocks appear uncertain, in coming decades most of the mitigation contribution from Canadian forests will likely accrue from wood substitution that reduces fossil fuel-based emissions and stores carbon, so long as those forests are managed sustainably.

Managing Sierra Nevada forests

Treesearch

Malcolm North

2012-01-01

There has been widespread interest in applying new forest practices based on concepts presented in U.S. Forest Service General Technical Report PSW-GTR-220, "An Ecosystem Management Strategy for Sierran Mixed-Conifer Forests." This collection of papers (PSW-GTR-237) summarizes the state of the science in some topics relevant to this forest management approach...

A biomass representative land cover classification for the Democratic Republic of Congo derived from the Forets D'Afrique Central Evaluee par Teledetection (FACET) data set

NASA Astrophysics Data System (ADS)

Molinario, G.; Hansen, M.; Potapov, P.; Altstatt, A. L.; Justice, C. O.

2012-12-01

The FACET forest cover and forest cover loss 2000-2005-2010 data set has been produced by South Dakota State University, the University of Maryland and the Kinshasa-based Observatoire Satellital des Forets D'Afrique Central (OSFAC) with funding from the USAID Central African Regional Program for the Environment (CARPE). The product is now available or being finalized for the DRC, the ROC and Gabon with plans to complete all Congo Basin countries. While FACET provides unprecedented synoptic detail in the extent of Congo Basin forest and the forest cover loss, additional information is required to stratify land cover into types indicative of biomass content. Analysis of the FACET patterns of deforestation, more detailed remote sensing analysis of biophysical attributes within the FACET land cover classes and GIS-derived classes of degradation obtained through variable distance buffers based on relevant literature and ground truth data are combined with the existing FACET classes to produce a ranking of land cover from low biomass to high biomass for the Democratic Republic of Congo. The resulting classification can be used in all Reduced Emissions from Degradation and Deforestation (REDD) pre-inventory phases when baseline forest cover needs to be known and the location and amount of forest biomass inventory plots needs to be designed. FACET cover loss classes were kept in the classification and can provide the Monitoring, Reporting and Verification tools needed for REDD projects. The project will be demonstrated for the Maringa Lopori Wamba Landscape of the DRC where this work was funded by the African Wildlife Foundation to support the design of a REDD pilot project.

Forest Classification Accuracy as Influenced by Multispectral Scanner Spatial Resolution. [Sam Houston National Forest, Texas

NASA Technical Reports Server (NTRS)

Nalepka, R. F. (Principal Investigator); Sadowski, F. E.; Sarno, J. E.

1976-01-01

The author has identified the following significant results. A supervised classification within two separate ground areas of the Sam Houston National Forest was carried out for two sq meters spatial resolution MSS data. Data were progressively coarsened to simulate five additional cases of spatial resolution ranging up to 64 sq meters. Similar processing and analysis of all spatial resolutions enabled evaluations of the effect of spatial resolution on classification accuracy for various levels of detail and the effects on area proportion estimation for very general forest features. For very coarse resolutions, a subset of spectral channels which simulated the proposed thematic mapper channels was used to study classification accuracy.

Object-Based Random Forest Classification of Land Cover from Remotely Sensed Imagery for Industrial and Mining Reclamation

NASA Astrophysics Data System (ADS)

Chen, Y.; Luo, M.; Xu, L.; Zhou, X.; Ren, J.; Zhou, J.

2018-04-01

The RF method based on grid-search parameter optimization could achieve a classification accuracy of 88.16 % in the classification of images with multiple feature variables. This classification accuracy was higher than that of SVM and ANN under the same feature variables. In terms of efficiency, the RF classification method performs better than SVM and ANN, it is more capable of handling multidimensional feature variables. The RF method combined with object-based analysis approach could highlight the classification accuracy further. The multiresolution segmentation approach on the basis of ESP scale parameter optimization was used for obtaining six scales to execute image segmentation, when the segmentation scale was 49, the classification accuracy reached the highest value of 89.58 %. The classification accuracy of object-based RF classification was 1.42 % higher than that of pixel-based classification (88.16 %), and the classification accuracy was further improved. Therefore, the RF classification method combined with object-based analysis approach could achieve relatively high accuracy in the classification and extraction of land use information for industrial and mining reclamation areas. Moreover, the interpretation of remotely sensed imagery using the proposed method could provide technical support and theoretical reference for remotely sensed monitoring land reclamation.

Classification of Snowfall Events and Their Effect on Canopy Interception Efficiency in a Temperate Montane Forest.

NASA Astrophysics Data System (ADS)

Roth, T. R.; Nolin, A. W.

2015-12-01

Forest canopies intercept as much as 60% of snowfall in maritime environments, while processes of sublimation and melt can reduce the amount of snow transferred from the canopy to the ground. This research examines canopy interception efficiency (CIE) as a function of forest and event-scale snowfall characteristics. We use a 4-year dataset of continuous meteorological measurements and monthly snow surveys from the Forest Elevation Snow Transect (ForEST) network that has forested and open sites at three elevations spanning the rain-snow transition zone to the upper seasonal snow zone. Over 150 individual storms were classified by forest and storm type characteristics (e.g. forest density, vegetation type, air temperature, snowfall amount, storm duration, wind speed, and storm direction). The between-site comparisons showed that, as expected, CIE was highest for the lower elevation (warmer) sites with higher forest density compared with the higher elevation sites where storm temperatures were colder, trees were smaller and forests were less dense. Within-site comparisons based on storm type show that this classification system can be used to predict CIE.Our results suggest that the coupling of forest type and storm type information can improve estimates of canopy interception. Understanding the effects of temperature and storm type in temperate montane forests is also valuable for future estimates of canopy interception under a warming climate.

Evolving land cover classification algorithms for multispectral and multitemporal imagery

NASA Astrophysics Data System (ADS)

Brumby, Steven P.; Theiler, James P.; Bloch, Jeffrey J.; Harvey, Neal R.; Perkins, Simon J.; Szymanski, John J.; Young, Aaron C.

2002-01-01

The Cerro Grande/Los Alamos forest fire devastated over 43,000 acres (17,500 ha) of forested land, and destroyed over 200 structures in the town of Los Alamos and the adjoining Los Alamos National Laboratory. The need to measure the continuing impact of the fire on the local environment has led to the application of a number of remote sensing technologies. During and after the fire, remote-sensing data was acquired from a variety of aircraft- and satellite-based sensors, including Landsat 7 Enhanced Thematic Mapper (ETM+). We now report on the application of a machine learning technique to the automated classification of land cover using multi-spectral and multi-temporal imagery. We apply a hybrid genetic programming/supervised classification technique to evolve automatic feature extraction algorithms. We use a software package we have developed at Los Alamos National Laboratory, called GENIE, to carry out this evolution. We use multispectral imagery from the Landsat 7 ETM+ instrument from before, during, and after the wildfire. Using an existing land cover classification based on a 1992 Landsat 5 TM scene for our training data, we evolve algorithms that distinguish a range of land cover categories, and an algorithm to mask out clouds and cloud shadows. We report preliminary results of combining individual classification results using a K-means clustering approach. The details of our evolved classification are compared to the manually produced land-cover classification.

Are community-based forest enterprises in the tropics financially viable? Case studies from the Brazilian Amazon

Treesearch

Shoana Humphries; Thomas P. Holmes; Karen Kainer; Carlos Gabriel Goncalves Koury; Edson Cruz; Rosana de Miranda Rocha

2012-01-01

Community-based forest management is an integral component of sustainable forest management and conservation in the Brazilian Amazon, where it has been heavily subsidized for the last ten years. Yet knowledge of the financial viability and impact of community-based forest enterprises (CFEs) is lacking. This study evaluates the profitability of three CFEs in the...

Wind in the forests of southeast Alaska and guides for reducing damage.

Treesearch

A.S. Harris

1999-01-01

Alaska based on the literature and the author's experience. Storm winds resulting in damage to forest stands are described, and some ecological and management considerations of wind that are of concern to forest managers are reviewed. The author made a general reconnaissance of forest conditions on Prince of Wales Island and adjacent islands based on forest-type...

An analysis of tree mortality using high resolution remotely-sensed data for mixed-conifer forests in San Diego county

NASA Astrophysics Data System (ADS)

Freeman, Mary Pyott

ABSTRACT An Analysis of Tree Mortality Using High Resolution Remotely-Sensed Data for Mixed-Conifer Forests in San Diego County by Mary Pyott Freeman The montane mixed-conifer forests of San Diego County are currently experiencing extensive tree mortality, which is defined as dieback where whole stands are affected. This mortality is likely the result of the complex interaction of many variables, such as altered fire regimes, climatic conditions such as drought, as well as forest pathogens and past management strategies. Conifer tree mortality and its spatial pattern and change over time were examined in three components. In component 1, two remote sensing approaches were compared for their effectiveness in delineating dead trees, a spatial contextual approach and an OBIA (object based image analysis) approach, utilizing various dates and spatial resolutions of airborne image data. For each approach transforms and masking techniques were explored, which were found to improve classifications, and an object-based assessment approach was tested. In component 2, dead tree maps produced by the most effective techniques derived from component 1 were utilized for point pattern and vector analyses to further understand spatio-temporal changes in tree mortality for the years 1997, 2000, 2002, and 2005 for three study areas: Palomar, Volcan and Laguna mountains. Plot-based fieldwork was conducted to further assess mortality patterns. Results indicate that conifer mortality was significantly clustered, increased substantially between 2002 and 2005, and was non-random with respect to tree species and diameter class sizes. In component 3, multiple environmental variables were used in Generalized Linear Model (GLM-logistic regression) and decision tree classifier model development, revealing the importance of climate and topographic factors such as precipitation and elevation, in being able to predict areas of high risk for tree mortality. The results from this study highlight the importance of multi-scale spatial as well as temporal analyses, in order to understand mixed-conifer forest structure, dynamics, and processes of decline, which can lead to more sustainable management of forests with continued natural and anthropogenic disturbance.

Lidar-based multinomial classification algorithms for tropical forest degradation status: Implications for biomass estimation

NASA Astrophysics Data System (ADS)

Duffy, P.; Keller, M.; Longo, M.; Morton, D. C.; dos-Santos, M. N.; Pinagé, E. R.

2017-12-01

There is an urgent need to quantify the effects of land use and land cover change on carbon stocks in tropical forests to support REDD+ policies and improve characterization of global carbon budgets. This need is underscored by the fact that the variability in forest biomass estimates from global forest carbon maps is artificially low relative to estimates generated from forest inventory and high-resolution airborne lidar data. Both deforestation and degradation processes (e.g. logging, fire, and fragmentation) affect carbon fluxes at varying spatial and temporal scales. While the spatial extent and impact of deforestation has been relatively well characterized, the quantification of degradation processes is still poorly constrained. In the Brazilian Amazon, the largest source of uncertainty in CO2 emissions estimates is data on changes in tropical forest carbon stocks through time, followed closely by incomplete information on the carbon losses from forest degradation. In this work, we present a method for classifying the degradation status of tropical forests using higher order moments (skewness and kurtosis) of lidar return distributions aggregated at grids with resolution ranging from 50 m to 250 m. Across multiple spatial resolutions, we quantify the strength of the functional relationship between the lidar returns and the classification based on historical time series of Landsat imagery. Our results show that the higher order moments of the lidar return distributions provide sufficient information to build multinomial models that accurately classify the landscape into intact, logged, and burned forests. Model fit improved with coarser spatial resolution with Kappa statistics of 0.70 at 50 m, and 0.77 at 250 m. In addition, multi-class AUC was estimated as 0.87 at 50 m, and 0.95 at 250 m. This classification provides important information regarding the applicability of the use of lidar data for regional monitoring of recent logging, as well as the trajectory of the carbon budget. Differentiating between the biomass changes associated with deforestation and degradation processes is critical for accurate accounting of disturbance impacts on carbon cycling within the Brazilian Amazon and global tropical forests.

A multitemporal (1979-2009) land-use/land-cover dataset of the binational Santa Cruz Watershed

USGS Publications Warehouse

2011-01-01

Trends derived from multitemporal land-cover data can be used to make informed land management decisions and to help managers model future change scenarios. We developed a multitemporal land-use/land-cover dataset for the binational Santa Cruz watershed of southern Arizona, United States, and northern Sonora, Mexico by creating a series of land-cover maps at decadal intervals (1979, 1989, 1999, and 2009) using Landsat Multispectral Scanner and Thematic Mapper data and a classification and regression tree classifier. The classification model exploited phenological changes of different land-cover spectral signatures through the use of biseasonal imagery collected during the (dry) early summer and (wet) late summer following rains from the North American monsoon. Landsat images were corrected to remove atmospheric influences, and the data were converted from raw digital numbers to surface reflectance values. The 14-class land-cover classification scheme is based on the 2001 National Land Cover Database with a focus on "Developed" land-use classes and riverine "Forest" and "Wetlands" cover classes required for specific watershed models. The classification procedure included the creation of several image-derived and topographic variables, including digital elevation model derivatives, image variance, and multitemporal Kauth-Thomas transformations. The accuracy of the land-cover maps was assessed using a random-stratified sampling design, reference aerial photography, and digital imagery. This showed high accuracy results, with kappa values (the statistical measure of agreement between map and reference data) ranging from 0.80 to 0.85.

Comparing Forest/Nonforest Classifications of Landsat TM Imagery for Stratifying FIA Estimates of Forest Land Area

Treesearch

Mark D. Nelson; Ronald E. McRoberts; Greg C. Liknes; Geoffrey R. Holden

2005-01-01

Landsat Thematic Mapper (TM) satellite imagery and Forest Inventory and Analysis (FIA) plot data were used to construct forest/nonforest maps of Mapping Zone 41, National Land Cover Dataset 2000 (NLCD 2000). Stratification approaches resulting from Maximum Likelihood, Fuzzy Convolution, Logistic Regression, and k-Nearest Neighbors classification/prediction methods were...

Crown-condition classification: a guide to data collection and analysis

Treesearch

Michael E. Schomaker; Stanley J. Zarnoch; William A. Bechtold; David J. Latelle; William G. Burkman; Susan M. Cox

2007-01-01

The Forest Inventory and Analysis (FIA) Program of the Forest Service, U.S. Department of Agriculture, conducts a national inventory of forests across the United States. A systematic subset of permanent inventory plots in 38 States is currently sampled every year for numerous forest health indicators. One of these indicators, crown-condition classification, is designed...

Field sampling and data analysis methods for development of ecological land classifications: an application on the Manistee National Forest.

Treesearch

George E. Host; Carl W. Ramm; Eunice A. Padley; Kurt S. Pregitzer; James B. Hart; David T. Cleland

1992-01-01

Presents technical documentation for development of an Ecological Classification System for the Manistee National Forest in northwest Lower Michigan, and suggests procedures applicable to other ecological land classification projects. Includes discussion of sampling design, field data collection, data summarization and analyses, development of classification units,...

Ponderosa pine forest structure and northern goshawk reproduction: Response to Beier et al

Treesearch

Richard T. Reynolds; Douglas A. Boyce; Russell T. Graham

2012-01-01

Ecosystem-based forest management requires long planning horizons to incorporate forest dynamics - changes resulting from vegetation growth and succession and the periodic resetting of these by natural and anthropogenic disturbances such as fire, wind, insects, and timber harvests. Given these dynamics, ecosystem-based forest management plans should specify desired...

Application of Modis Data to Assess the Latest Forest Cover Changes of Sri Lanka

NASA Astrophysics Data System (ADS)

Perera, K.; Herath, S.; Apan, A.; Tateishi, R.

2012-07-01

Assessing forest cover of Sri Lanka is becoming important to lower the pressure on forest lands as well as man-elephant conflicts. Furthermore, the land access to north-east Sri Lanka after the end of 30 years long civil war has increased the need of regularly updated land cover information for proper planning. This study produced an assessment of the forest cover of Sri Lanka using two satellite data based maps within 23 years of time span. For the old forest cover map, the study used one of the first island-wide digital land cover classification produced by the main author in 1988. The old land cover classification was produced at 80 m spatial resolution, using Landsat MSS data. A previously published another study by the author has investigated the application feasibility of MODIS and Landsat MSS imagery for a selected sub-section of Sri Lanka to identify the forest cover changes. Through the light of these two studies, the assessment was conducted to investigate the application possibility of MODIS 250 m over a small island like Sri Lanka. The relation between the definition of forest in the study and spatial resolution of the used satellite data sets were considered since the 2012 map was based on MODIS data. The forest cover map of 1988 was interpolated into 250 m spatial resolution to integrate with the GIS data base. The results demonstrated the advantages as well as disadvantages of MODIS data in a study at this scale. The successful monitoring of forest is largely depending on the possibility to update the field conditions at regular basis. Freely available MODIS data provides a very valuable set of information of relatively large green patches on the ground at relatively real-time basis. Based on the changes of forest cover from 1988 to 2012, the study recommends the use of MODIS data as a resalable method to forest assessment and to identify hotspots to be re-investigated. It's noteworthy to mention the possibility of uncounted small isolated pockets of forest, or sub-pixel size forest patches when MODIS 250 m x 250 m data used in small regions.

Measuring impacts of community forestry program through repeat photography and satellite remote sensing in the Dolakha district of Nepal.

PubMed

Niraula, Rabin Raj; Gilani, Hammad; Pokharel, Bharat Kumar; Qamer, Faisal Mueen

2013-09-15

During the 1990's community-based forest management gained momentum in Nepal. This study systematically evaluates the impacts that this had on land cover change and other associated aspects during the period 1990-2010 using repeat photography and satellite imagery in combination with interviews with community members. The results of the study clearly reflect the success of community-based forest management in the Dolakha district of the mid-hills of Nepal: during the study period, the rate of conversion of sparse forest into dense forest under community-based management was found to be between 1.13% and 3.39% per year. Similarly, the rate of conversion of non-forest area into forest was found to be between 1.11% and 1.96% per year. Community-based forest management has resulted in more efficient use of forest resources, contributed to a decline in the use of slash-and-burn agricultural practices, reduced the incidence of forest fires, spurred tree plantation, and encouraged the conservation and protection of trees on both public and private land. The resulting reclamation of forest in landside areas and river banks and the overall improvement in forest cover in the area has reduced flash floods and associated landslides. Copyright © 2013 Elsevier Ltd. All rights reserved.

Model for multi-stand management based on structural attributes of individual stands

Treesearch

G.W. Miller; J. Sullivan

1997-01-01

A growing interest in managing forest ecosystems calls for decision models that take into account attribute goals for large forest areas while continuing to recognize the individual stand as a basic unit of forest management. A dynamic, nonlinear forest management model is described that schedules silvicultural treatments for individual stands that are linked by multi-...

Simulation of Sentinel-2A Red Edge Bands with RPAS Based Multispectral Data

NASA Astrophysics Data System (ADS)

Davids, Corine; Storvold, Rune; Haarpaintner, Jorg; Arnason, Kolbeinn

2016-08-01

Very high spatial and spectral resolution multispectral data was collected over the Hallormstađur test site in eastern Iceland using a fixed wing remotely piloted aerial system as part of the EU FP7 project North State (www.northstatefp7.eu). The North State project uses forest variable estimates derived from optical and radar satellite data as either input or validation for carbon flux models. The RPAS data from the Hallormsstađur forest test site in Iceland is here used to simulate Landsat and Sentinel-2A data and to explore the advantages of the new Sentinel-2A red edge bands for forest vegetation mapping. Simple supervised classification shows that the inclusion of the red edge bands improves the tree species classification considerably.

Comparing forests across climates and biomes: qualitative assessments, reference forests and regional intercomparisons.

PubMed

Salk, Carl F; Frey, Ulrich; Rusch, Hannes

2014-01-01

Communities, policy actors and conservationists benefit from understanding what institutions and land management regimes promote ecosystem services like carbon sequestration and biodiversity conservation. However, the definition of success depends on local conditions. Forests' potential carbon stock, biodiversity and rate of recovery following disturbance are known to vary with a broad suite of factors including temperature, precipitation, seasonality, species' traits and land use history. Methods like tracking over-time changes within forests, or comparison with "pristine" reference forests have been proposed as means to compare the structure and biodiversity of forests in the face of underlying differences. However, data from previous visits or reference forests may be unavailable or costly to obtain. Here, we introduce a new metric of locally weighted forest intercomparison to mitigate the above shortcomings. This method is applied to an international database of nearly 300 community forests and compared with previously published techniques. It is particularly suited to large databases where forests may be compared among one another. Further, it avoids problematic comparisons with old-growth forests which may not resemble the goal of forest management. In most cases, the different methods produce broadly congruent results, suggesting that researchers have the flexibility to compare forest conditions using whatever type of data is available. Forest structure and biodiversity are shown to be independently measurable axes of forest condition, although users' and foresters' estimations of seemingly unrelated attributes are highly correlated, perhaps reflecting an underlying sentiment about forest condition. These findings contribute new tools for large-scale analysis of ecosystem condition and natural resource policy assessment. Although applied here to forestry, these techniques have broader applications to classification and evaluation problems using crowdsourced or repurposed data for which baselines or external validations are not available.

Comparing Forests across Climates and Biomes: Qualitative Assessments, Reference Forests and Regional Intercomparisons

PubMed Central

Salk, Carl F.; Frey, Ulrich; Rusch, Hannes

2014-01-01

Communities, policy actors and conservationists benefit from understanding what institutions and land management regimes promote ecosystem services like carbon sequestration and biodiversity conservation. However, the definition of success depends on local conditions. Forests' potential carbon stock, biodiversity and rate of recovery following disturbance are known to vary with a broad suite of factors including temperature, precipitation, seasonality, species' traits and land use history. Methods like tracking over-time changes within forests, or comparison with “pristine” reference forests have been proposed as means to compare the structure and biodiversity of forests in the face of underlying differences. However, data from previous visits or reference forests may be unavailable or costly to obtain. Here, we introduce a new metric of locally weighted forest intercomparison to mitigate the above shortcomings. This method is applied to an international database of nearly 300 community forests and compared with previously published techniques. It is particularly suited to large databases where forests may be compared among one another. Further, it avoids problematic comparisons with old-growth forests which may not resemble the goal of forest management. In most cases, the different methods produce broadly congruent results, suggesting that researchers have the flexibility to compare forest conditions using whatever type of data is available. Forest structure and biodiversity are shown to be independently measurable axes of forest condition, although users' and foresters' estimations of seemingly unrelated attributes are highly correlated, perhaps reflecting an underlying sentiment about forest condition. These findings contribute new tools for large-scale analysis of ecosystem condition and natural resource policy assessment. Although applied here to forestry, these techniques have broader applications to classification and evaluation problems using crowdsourced or repurposed data for which baselines or external validations are not available. PMID:24743325

36 CFR 1237.30 - How do agencies manage records on nitrocellulose-base and cellulose-acetate base film?

Code of Federal Regulations, 2014 CFR

2014-07-01

... 36 Parks, Forests, and Public Property 3 2014-07-01 2014-07-01 false How do agencies manage records on nitrocellulose-base and cellulose-acetate base film? 1237.30 Section 1237.30 Parks, Forests..., CARTOGRAPHIC, AND RELATED RECORDS MANAGEMENT § 1237.30 How do agencies manage records on nitrocellulose-base...

36 CFR 1237.30 - How do agencies manage records on nitrocellulose-base and cellulose-acetate base film?

Code of Federal Regulations, 2011 CFR

2011-07-01

... 36 Parks, Forests, and Public Property 3 2011-07-01 2011-07-01 false How do agencies manage records on nitrocellulose-base and cellulose-acetate base film? 1237.30 Section 1237.30 Parks, Forests..., CARTOGRAPHIC, AND RELATED RECORDS MANAGEMENT § 1237.30 How do agencies manage records on nitrocellulose-base...

36 CFR 1237.30 - How do agencies manage records on nitrocellulose-base and cellulose-acetate base film?

Code of Federal Regulations, 2012 CFR

2012-07-01

... 36 Parks, Forests, and Public Property 3 2012-07-01 2012-07-01 false How do agencies manage records on nitrocellulose-base and cellulose-acetate base film? 1237.30 Section 1237.30 Parks, Forests..., CARTOGRAPHIC, AND RELATED RECORDS MANAGEMENT § 1237.30 How do agencies manage records on nitrocellulose-base...

The role of communities in sustainable land and forest management: The case of Nyanga, Zvimba and Guruve districts of Zimbabwe

PubMed Central

Sagonda, Ruvimbo; Kaundikiza, Munyaradzi

2016-01-01

Forest benefit analysis is vital in ensuring sustainable community-based natural resources management. Forest depletion and degradation are key issues in rural Zimbabwe and strategies to enhance sustainable forest management are continually sought. This study was carried out to assess the impact of forests on communities from Nyanga, Guruve and Zvimba districts of Zimbabwe. It is based on a Big Lottery Fund project implemented by Progressio-UK and Environment Africa. It focuses on identifying replicable community forest and land management strategies and the level of benefits accruing to the community. Analysis of change was based on the Income and Food Security and Forest benefits, which also constitutes the tools used during the research. The study confirms the high rate of deforestation and the increased realisation by communities to initiate practical measures aimed at protecting and sustaining forest and land resources from which they derive economic and social benefits. The results highlight the value of community structures (Farmer Field Schools and Environmental Action Groups) as conduits for natural resource management. The interconnectivity among forests, agricultural systems and the integral role of people are recognised as key to climate change adaptation.

The Zoning of Forest Fire Potential of Gulestan Province Forests Using Granular Computing and MODIS Images

NASA Astrophysics Data System (ADS)

Jalilzadeh Shadlouei, A.; Delavar, M. R.

2013-09-01

There are many vegetation in Iran. This is because of extent of Iran and its width. One of these vegetation is forest vegetation most prevalent in Northern provinces named Guilan, Mazandaran, Gulestan, Ardebil as well as East Azerbaijan. These forests are always threatened by natural forest fires so much so that there have been reports of tens of fires in recent years. Forest fires are one of the major environmental as well as economic, social and security concerns in the world causing much damages. According to climatology, forest fires are one of the important factors in the formation and dispersion of vegetation. Also, regarding the environment, forest fires cause the emission of considerable amounts of greenhouse gases, smoke and dust into the atmosphere which in turn causes the earth temperature to rise up and are unhealthy to humans, animals and vegetation. In agriculture droughts are the usual side effects of these fires. The causes of forest fires could be categorized as either Human or Natural Causes. Naturally, it is impossible to completely contain forest fires; however, areas with high potentials of fire could be designated and analysed to decrease the risk of fires. The zoning of forest fire potential is a multi-criteria problem always accompanied by inherent uncertainty like other multi-criteria problems. So far, various methods and algorithm for zoning hazardous areas via Remote Sensing (RS) and Geospatial Information System (GIS) have been offered. This paper aims at zoning forest fire potential of Gulestan Province of Iran forests utilizing Remote Sensing, Geospatial Information System, meteorological data, MODIS images and granular computing method. Granular computing is part of granular mathematical and one way of solving multi-criteria problems such forest fire potential zoning supervised by one expert or some experts , and it offers rules for classification with the least inconsistencies. On the basis of the experts' opinion, 6 determinative criterias contributing to forest fires have been designated as follows: vegetation (NDVI), slope, aspect, temperature, humidity and proximity to roadways. By applying these variables on several tentatively selected areas and formation information tables and producing granular decision tree and extraction of rules, the zoning rules (for the areas in question) were extracted. According to them the zoning of the entire area has been conducted. The zoned areas have been classified into 5 categories: high hazard, medium hazard (high), medium hazard (low), low hazard (high), low hazard (low). According to the map, the zoning of most of the areas fall into the low hazard (high) class while the least number of areas have been classified as low hazard (low). Comparing the forest fires in these regions in 2010 with the MODIS data base for forest fires, it is concluded that areas with high hazards of forest fire have been classified with a 64 percent precision. In other word 64 percent of pixels that are in high hazard classification are classified according to MODIS data base. Using this method we obtain a good range of Perception. Manager will reduce forest fire concern using precautionary proceeding on hazardous area.

Application of remote sensing and GIS techniques for forest cover monitoring in the southern part of Laos

NASA Astrophysics Data System (ADS)

Keonuchan, Ammala; Liu, Yaolin

2008-12-01

Forest resource is the important material foundation of national sustainable development. And it need to master the status and change of forest resource timely for reasonable exploitation of forest and its renewal. Laos is located in the heart of the Indochinese peninsular, in southeast Asia, latitude 14° to 23 °north and longitude 100°to 108°east, covered a total 236, 800 square kilometers, and country of nearly 6 million people. The forest of Laos dropped from close to two-third in the 1970's to less than half by the 1990's. This deforestation has been attributed to two human activities : a traditional of shifting cultivation or slash and burn farming, and logging without reforestation. Remote sensing and GIS are the most modern technologies which have been widely used in the field of natural resource management and monitoring. These technologies provide very powerful tools to observe and collect information on natural resources and dynamic phenomenon on the earth surface, and ability to integrate different data and present data in different formats. In this study, using forest cover map and Landsat 7 ETM data, we analyze and compare forest cover change from 1997 to 2002. And the maximum likelihood method of supervised classification was used to classify the remote sensing data, we processed Spectral Enhancement, including Normalized Difference Vegetation Index (NDVI) ,and re-classify data again base on Principle Components Analysis (PCA) and NDVI.

Determining successional stage of temperate coniferous forests with Landsat satellite data

NASA Technical Reports Server (NTRS)

Fiorella, Maria; Ripple, William J.

1993-01-01

Thematic Mapper (TM) digital imagery was used to map forest successional stages and to evaluate spectral differences between old-growth and mature forests in the central Cascade Range of Oregon. Relative sun incidence values were incorporated into the successional stage classification to compensate for topographic induced variation. Relative sun incidence improved the classification accuracy of young successional stages, but did not improve the classification accuracy of older, closed canopy forest classes or overall accuracy. TM bands 1, 2, and 4; the normalized difference vegetation index; and TM 4/3, 4/5, and 4/7 band ratio values for o|d-growth forests were found to be significantly lower than the values of mature forests. The Tasseled Cap features of brightness, greenness, and wetness also had significantly lower old-growth values as compared to mature forest values .

A hierarchical approach to forest landscape pattern characterization.

PubMed

Wang, Jialing; Yang, Xiaojun

2012-01-01

Landscape spatial patterns have increasingly been considered to be essential for environmental planning and resources management. In this study, we proposed a hierarchical approach for landscape classification and evaluation by characterizing landscape spatial patterns across different hierarchical levels. The case study site is the Red Hills region of northern Florida and southwestern Georgia, well known for its biodiversity, historic resources, and scenic beauty. We used one Landsat Enhanced Thematic Mapper image to extract land-use/-cover information. Then, we employed principal-component analysis to help identify key class-level landscape metrics for forests at different hierarchical levels, namely, open pine, upland pine, and forest as a whole. We found that the key class-level landscape metrics varied across different hierarchical levels. Compared with forest as a whole, open pine forest is much more fragmented. The landscape metric, such as CONTIG_MN, which measures whether pine patches are contiguous or not, is more important to characterize the spatial pattern of pine forest than to forest as a whole. This suggests that different metric sets should be used to characterize landscape patterns at different hierarchical levels. We further used these key metrics, along with the total class area, to classify and evaluate subwatersheds through cluster analysis. This study demonstrates a promising approach that can be used to integrate spatial patterns and processes for hierarchical forest landscape planning and management.

Using a Forest Health Index as an Outreach Tool for Improving Public Understanding of Ecosystem Dynamics and Research-Based Management

NASA Astrophysics Data System (ADS)

Osenga, E. C.; Cundiff, J.; Arnott, J. C.; Katzenberger, J.; Taylor, J. R.; Jack-Scott, E.

2015-12-01

An interactive tool called the Forest Health Index (FHI) has been developed for the Roaring Fork watershed of Colorado, with the purpose of improving public understanding of local forest management and ecosystem dynamics. The watershed contains large areas of White River National Forest, which plays a significant role in the local economy, particularly for recreation and tourism. Local interest in healthy forests is therefore strong, but public understanding of forest ecosystems is often simplified. This can pose challenges for land managers and researchers seeking a scientifically informed approach to forest restoration, management, and planning. Now in its second iteration, the FHI is a tool designed to help bridge that gap. The FHI uses a suite of indicators to create a numeric rating of forest functionality and change, based on the desired forest state in relation to four categories: Ecological Integrity, Public Health and Safety, Ecosystem Services, and Sustainable Use and Management. The rating is based on data derived from several sources including local weather stations, stream gauge data, SNOTEL sites, and National Forest Service archives. In addition to offering local outreach and education, this project offers broader insight into effective communication methods, as well as into the challenges of using quantitative analysis to rate ecosystem health. Goals of the FHI include its use in schools as a means of using local data and place-based learning to teach basic math and science concepts, improved public understanding of ecological complexity and need for ongoing forest management, and, in the future, its use as a model for outreach tools in other forested communities in the Intermountain West.

Evaluating satellite imagery for estimating mountain pine beetle-caused lodgepole pine mortality: Current status

Treesearch

B. J. Bentz; D. Endreson

2004-01-01

Spatial accuracy in the detection and monitoring of mountain pine beetle populations is an important aspect of both forest research and management. Using ground-collected data, classification models to predict mountain pine beetle-caused lodgepole pine mortality were developed for Landsat TM, ETM+, and IKONOS imagery. Our results suggest that low-resolution imagery...

Wood Use in the U.S. Pallet and Container Industry: 1995

Treesearch

Vijay S. Reddy; Robert J. Bush; Matthew S. Bumgardner; James L. Chamberlain; Philip A. Araman

1997-01-01

This report from the Center for Forest Products Marketing and Management at Virginia Tech provides results of a study ofwood material use in the pallet and container industry (Standard Industrial Classification codes 2441, 2448, and 2449). The report furnishes estimates of industry-wide use ofvarious wood materials (i.e., solid hardwood, solid softwood,oriented strand...

Narrowing Historical Uncertainty: Probabilistic Classification of Ambiguously Identified Tree Species in Historical Forest Survey Data

Treesearch

David J. Mladenoff; Sally E. Dahir; Eric V. Nordheim; Lisa A. Schulte; Glenn G. Gutenspergen

2002-01-01

Historical data have increasingly become appreciated for insight into the past conditions of ecosystems, Uses of such data include assessing the extent of ecosystem change; deriving ecological baselines for management, restoration, and modeling; and assessing the importance of past conditions on the composition and function of current systems. One historical data set...

Preliminary fuel characterization of the chauga ridges region of the Southern Appalachian Mountains

Treesearch

Aaron D. Stottlemyer; Victor B. Shelburne; Thomas A. Waldrop; Sandra Rideout-Hanzak; William C. Bridges

2006-01-01

Many areas of the southern Appalachian Mountains contain large amounts of dead and/or ericaceous fuel. Fuel information critical in modeling fire behavior and its effects is not available to forest managers in the southern Appalachian Mountains, and direct measurement is often impractical due to steep, remote topography. An existing landscape ecosystem classification (...

Identification of an Efficient Gene Expression Panel for Glioblastoma Classification

PubMed Central

Zelaya, Ivette; Laks, Dan R.; Zhao, Yining; Kawaguchi, Riki; Gao, Fuying; Kornblum, Harley I.; Coppola, Giovanni

2016-01-01

We present here a novel genetic algorithm-based random forest (GARF) modeling technique that enables a reduction in the complexity of large gene disease signatures to highly accurate, greatly simplified gene panels. When applied to 803 glioblastoma multiforme samples, this method allowed the 840-gene Verhaak et al. gene panel (the standard in the field) to be reduced to a 48-gene classifier, while retaining 90.91% classification accuracy, and outperforming the best available alternative methods. Additionally, using this approach we produced a 32-gene panel which allows for better consistency between RNA-seq and microarray-based classifications, improving cross-platform classification retention from 69.67% to 86.07%. A webpage producing these classifications is available at http://simplegbm.semel.ucla.edu. PMID:27855170

A preliminary test of estimating forest site quality using species composition in a southern Appalachian watershed

Treesearch

W. Henry McNab; David L. Loftis

2013-01-01

Characteristic arborescent communities of mesophytic or xerophytic species have long been recognized as indicative of forest site quality in the Southern Appalachians, where soil moisture availability is the primary environmental variable affecting productivity. But, a workable quantitative system of site classification based on species composition is not available. We...

Habitat mapping and interpretation in New England

Treesearch

William B. Leak

1982-01-01

Recommendations are given on the classification of forest land in New England on the basis of physiographic region, climate (elevation, latitude), mineralogy, and habitat. A habitat map for the Bartlett Experimental Forest in New Hampshire is presented based on land form, vegetation, and soil materials. For each habitat or group of habitats, data are presented on stand...

The Importance of Temporal and Spatial Vegetation Structure Information in Biotope Mapping Schemes: A Case Study in Helsingborg, Sweden

NASA Astrophysics Data System (ADS)

Gao, Tian; Qiu, Ling; Hammer, Mårten; Gunnarsson, Allan

2012-02-01

Temporal and spatial vegetation structure has impact on biodiversity qualities. Yet, current schemes of biotope mapping do only to a limited extend incorporate these factors in the mapping. The purpose of this study is to evaluate the application of a modified biotope mapping scheme that includes temporal and spatial vegetation structure. A refined scheme was developed based on a biotope classification, and applied to a green structure system in Helsingborg city in southern Sweden. It includes four parameters of vegetation structure: continuity of forest cover, age of dominant trees, horizontal structure, and vertical structure. The major green structure sites were determined by interpretation of panchromatic aerial photographs assisted with a field survey. A set of biotope maps was constructed on the basis of each level of modified classification. An evaluation of the scheme included two aspects in particular: comparison of species richness between long-continuity and short-continuity forests based on identification of woodland continuity using ancient woodland indicators (AWI) species and related historical documents, and spatial distribution of animals in the green space in relation to vegetation structure. The results indicate that (1) the relationship between forest continuity: according to verification of historical documents, the richness of AWI species was higher in long-continuity forests; Simpson's diversity was significantly different between long- and short-continuity forests; the total species richness and Shannon's diversity were much higher in long-continuity forests shown a very significant difference. (2) The spatial vegetation structure and age of stands influence the richness and abundance of the avian fauna and rabbits, and distance to the nearest tree and shrub was a strong determinant of presence for these animal groups. It is concluded that continuity of forest cover, age of dominant trees, horizontal and vertical structures of vegetation should now be included in urban biotope classifications.

Mapping of taiga forest units using AIRSAR data and/or optical data, and retrieval of forest parameters

NASA Technical Reports Server (NTRS)

Rignot, Eric; Williams, Cynthia; Way, Jobea; Viereck, Leslie

1993-01-01

A maximum a posteriori Bayesian classifier for multifrequency polarimetric SAR data is used to perform a supervised classification of forest types in the floodplains of Alaska. The image classes include white spruce, balsam poplar, black spruce, alder, non-forests, and open water. The authors investigate the effect on classification accuracy of changing environmental conditions, and of frequency and polarization of the signal. The highest classification accuracy (86 percent correctly classified forest pixels, and 91 percent overall) is obtained combining L- and C-band frequencies fully polarimetric on a date where the forest is just recovering from flooding. The forest map compares favorably with a vegetation map assembled from digitized aerial photos which took five years for completion, and address the state of the forest in 1978, ignoring subsequent fires, changes in the course of the river, clear-cutting of trees, and tree growth. HV-polarization is the most useful polarization at L- and C-band for classification. C-band VV (ERS-1 mode) and L-band HH (J-ERS-1 mode) alone or combined yield unsatisfactory classification accuracies. Additional data acquired in the winter season during thawed and frozen days yield classification accuracies respectively 20 percent and 30 percent lower due to a greater confusion between conifers and deciduous trees. Data acquired at the peak of flooding in May 1991 also yield classification accuracies 10 percent lower because of dominant trunk-ground interactions which mask out finer differences in radar backscatter between tree species. Combination of several of these dates does not improve classification accuracy. For comparison, panchromatic optical data acquired by SPOT in the summer season of 1991 are used to classify the same area. The classification accuracy (78 percent for the forest types and 90 percent if open water is included) is lower than that obtained with AIRSAR although conifers and deciduous trees are better separated due to the presence of leaves on the deciduous trees. Optical data do not separate black spruce and white spruce as well as SAR data, cannot separate alder from balsam poplar, and are of course limited by the frequent cloud cover in the polar regions. Yet, combining SPOT and AIRSAR offers better chances to identify vegetation types independent of ground truth information using a combination of NDVI indexes from SPOT, biomass numbers from AIRSAR, and a segmentation map from either one.

Effects of national forest-management regimes on unprotected forests of the Himalaya.

PubMed

Brandt, Jodi S; Allendorf, Teri; Radeloff, Volker; Brooks, Jeremy

2017-12-01

Globally, deforestation continues, and although protected areas effectively protect forests, the majority of forests are not in protected areas. Thus, how effective are different management regimes to avoid deforestation in non-protected forests? We sought to assess the effectiveness of different national forest-management regimes to safeguard forests outside protected areas. We compared 2000-2014 deforestation rates across the temperate forests of 5 countries in the Himalaya (Bhutan, Nepal, China, India, and Myanmar) of which 13% are protected. We reviewed the literature to characterize forest management regimes in each country and conducted a quasi-experimental analysis to measure differences in deforestation of unprotected forests among countries and states in India. Countries varied in both overarching forest-management goals and specific tenure arrangements and policies for unprotected forests, from policies emphasizing economic development to those focused on forest conservation. Deforestation rates differed up to 1.4% between countries, even after accounting for local determinants of deforestation, such as human population density, market access, and topography. The highest deforestation rates were associated with forest policies aimed at maximizing profits and unstable tenure regimes. Deforestation in national forest-management regimes that emphasized conservation and community management were relatively low. In India results were consistent with the national-level results. We interpreted our results in the context of the broader literature on decentralized, community-based natural resource management, and our findings emphasize that the type and quality of community-based forestry programs and the degree to which they are oriented toward sustainable use rather than economic development are important for forest protection. Our cross-national results are consistent with results from site- and regional-scale studies that show forest-management regimes that ensure stable land tenure and integrate local-livelihood benefits with forest conservation result in the best forest outcomes. © 2017 Society for Conservation Biology.

Capability of Integrated MODIS Imagery and ALOS for Oil Palm, Rubber and Forest Areas Mapping in Tropical Forest Regions

PubMed Central

Razali, Sheriza Mohd; Marin, Arnaldo; Nuruddin, Ahmad Ainuddin; Shafri, Helmi Zulhaidi Mohd; Hamid, Hazandy Abdul

2014-01-01

Various classification methods have been applied for low resolution of the entire Earth's surface from recorded satellite images, but insufficient study has determined which method, for which satellite data, is economically viable for tropical forest land use mapping. This study employed Iterative Self Organizing Data Analysis Techniques (ISODATA) and K-Means classification techniques to classified Moderate Resolution Imaging Spectroradiometer (MODIS) Surface Reflectance satellite image into forests, oil palm groves, rubber plantations, mixed horticulture, mixed oil palm and rubber and mixed forest and rubber. Even though frequent cloud cover has been a challenge for mapping tropical forests, our MODIS land use classification map found that 2008 ISODATA-1 performed well with overall accuracy of 94%, with the highest Producer's Accuracy of Forest with 86%, and were consistent with MODIS Land Cover 2008 (MOD12Q1), respectively. The MODIS land use classification was able to distinguish young oil palm groves from open areas, rubber and mature oil palm plantations, on the Advanced Land Observing Satellite (ALOS) map, whereas rubber was more easily distinguished from an open area than from mixed rubber and forest. This study provides insight on the potential for integrating regional databases and temporal MODIS data, in order to map land use in tropical forest regions. PMID:24811079

Capability of integrated MODIS imagery and ALOS for oil palm, rubber and forest areas mapping in tropical forest regions.

PubMed

Razali, Sheriza Mohd; Marin, Arnaldo; Nuruddin, Ahmad Ainuddin; Shafri, Helmi Zulhaidi Mohd; Hamid, Hazandy Abdul

2014-05-07

Various classification methods have been applied for low resolution of the entire Earth's surface from recorded satellite images, but insufficient study has determined which method, for which satellite data, is economically viable for tropical forest land use mapping. This study employed Iterative Self Organizing Data Analysis Techniques (ISODATA) and K-Means classification techniques to classified Moderate Resolution Imaging Spectroradiometer (MODIS) Surface Reflectance satellite image into forests, oil palm groves, rubber plantations, mixed horticulture, mixed oil palm and rubber and mixed forest and rubber. Even though frequent cloud cover has been a challenge for mapping tropical forests, our MODIS land use classification map found that 2008 ISODATA-1 performed well with overall accuracy of 94%, with the highest Producer's Accuracy of Forest with 86%, and were consistent with MODIS Land Cover 2008 (MOD12Q1), respectively. The MODIS land use classification was able to distinguish young oil palm groves from open areas, rubber and mature oil palm plantations, on the Advanced Land Observing Satellite (ALOS) map, whereas rubber was more easily distinguished from an open area than from mixed rubber and forest. This study provides insight on the potential for integrating regional databases and temporal MODIS data, in order to map land use in tropical forest regions.

Investigating the limitations of tree species classification using the Combined Cluster and Discriminant Analysis method for low density ALS data from a dense forest region in Aggtelek (Hungary)

NASA Astrophysics Data System (ADS)

Koma, Zsófia; Deák, Márton; Kovács, József; Székely, Balázs; Kelemen, Kristóf; Standovár, Tibor

2016-04-01

Airborne Laser Scanning (ALS) is a widely used technology for forestry classification applications. However, single tree detection and species classification from low density ALS point cloud is limited in a dense forest region. In this study we investigate the division of a forest into homogenous groups at stand level. The study area is located in the Aggtelek karst region (Northeast Hungary) with a complex relief topography. The ALS dataset contained only 4 discrete echoes (at 2-4 pt/m2 density) from the study area during leaf-on season. Ground-truth measurements about canopy closure and proportion of tree species cover are available for every 70 meter in 500 square meter circular plots. In the first step, ALS data were processed and geometrical and intensity based features were calculated into a 5×5 meter raster based grid. The derived features contained: basic statistics of relative height, canopy RMS, echo ratio, openness, pulse penetration ratio, basic statistics of radiometric feature. In the second step the data were investigated using Combined Cluster and Discriminant Analysis (CCDA, Kovács et al., 2014). The CCDA method first determines a basic grouping for the multiple circle shaped sampling locations using hierarchical clustering and then for the arising grouping possibilities a core cycle is executed comparing the goodness of the investigated groupings with random ones. Out of these comparisons difference values arise, yielding information about the optimal grouping out of the investigated ones. If sub-groups are then further investigated, one might even find homogeneous groups. We found that low density ALS data classification into homogeneous groups are highly dependent on canopy closure, and the proportion of the dominant tree species. The presented results show high potential using CCDA for determination of homogenous separable groups in LiDAR based tree species classification. Aggtelek Karst/Slovakian Karst Caves" (HUSK/1101/221/0180, Aggtelek NP), data evaluation: 'Multipurpose assessment serving forest biodiversity conservation in the Carpathian region of Hungary', Swiss-Hungarian Cooperation Programme (SH/4/13 Project). BS contributed as an Alexander von Humboldt Research Fellow. J. Kovács, S. Kovács, N. Magyar, P. Tanos, I. G. Hatvani, and A. Anda (2014), Classification into homogeneous groups using combined cluster and discriminant analysis, Environmental Modelling & Software, 57, 52-59.

Mapping of government land encroachment in Cameron Highlands using multiple remote sensing datasets

NASA Astrophysics Data System (ADS)

Zin, M. H. M.; Ahmad, B.

2014-02-01

The cold and refreshing highland weather is one of the factors that give impact to socio-economic growth in Cameron Highlands. This unique weather of the highland surrounded by tropical rain forest can only be found in a few places in Malaysia. It makes this place a famous tourism attraction and also provides a very suitable temperature for agriculture activities. Thus it makes agriculture such as tea plantation, vegetable, fruits and flowers one of the biggest economic activities in Cameron Highlands. However unauthorized agriculture activities are rampant. The government land, mostly forest area have been encroached by farmers, in many cases indiscriminately cutting down trees and hill slopes. This study is meant to detect and assess this encroachment using multiple remote sensing datasets. The datasets were used together with cadastral parcel data where survey lines describe property boundary, pieces of land are subdivided into lots of government and private. The general maximum likelihood classification method was used on remote sensing image to classify the land-cover in the study area. Ground truth data from field observation were used to assess the accuracy of the classification. Cadastral parcel data was overlaid on the classification map in order to detect the encroachment area. The result of this study shows that there is a land cover change of 93.535 ha in the government land of the study area between years 2001 to 2010, nevertheless almost no encroachment took place in the studied forest reserve area. The result of this study will be useful for the authority in monitoring and managing the forest.

Coast redwood ecological types of southern Monterey County, California

Treesearch

Mark Borchert; Daniel Segotta; Michael D. Purser

1988-01-01

An ecological classification system has been developed for the Pacific Southwest Region of the Forest Service. As part of this classification effort, coast redwood (Sequoia sempervirens) forests of southern Monterey County in the Los Padres National Forest were classified into six ecological types using vegetation, soils and geomorphology taken from...

Applications of satellite remote sensing to forested ecosystems

Treesearch

Louis R. Iverson; Robin Lambert Graham; Elizabeth A. Cook; Elizabeth A. Cook

1989-01-01

Since the launch of the first civilian earth-observing satellite in 1972, satellite remote sensing has provided increasingly sophisticated information on the structure and function of forested ecosystems. Forest classification and mapping, common uses of satellite data, have improved over the years as a result of more discriminating sensors, better classification...

Ensemble Pruning for Glaucoma Detection in an Unbalanced Data Set.

PubMed

Adler, Werner; Gefeller, Olaf; Gul, Asma; Horn, Folkert K; Khan, Zardad; Lausen, Berthold

2016-12-07

Random forests are successful classifier ensemble methods consisting of typically 100 to 1000 classification trees. Ensemble pruning techniques reduce the computational cost, especially the memory demand, of random forests by reducing the number of trees without relevant loss of performance or even with increased performance of the sub-ensemble. The application to the problem of an early detection of glaucoma, a severe eye disease with low prevalence, based on topographical measurements of the eye background faces specific challenges. We examine the performance of ensemble pruning strategies for glaucoma detection in an unbalanced data situation. The data set consists of 102 topographical features of the eye background of 254 healthy controls and 55 glaucoma patients. We compare the area under the receiver operating characteristic curve (AUC), and the Brier score on the total data set, in the majority class, and in the minority class of pruned random forest ensembles obtained with strategies based on the prediction accuracy of greedily grown sub-ensembles, the uncertainty weighted accuracy, and the similarity between single trees. To validate the findings and to examine the influence of the prevalence of glaucoma in the data set, we additionally perform a simulation study with lower prevalences of glaucoma. In glaucoma classification all three pruning strategies lead to improved AUC and smaller Brier scores on the total data set with sub-ensembles as small as 30 to 80 trees compared to the classification results obtained with the full ensemble consisting of 1000 trees. In the simulation study, we were able to show that the prevalence of glaucoma is a critical factor and lower prevalence decreases the performance of our pruning strategies. The memory demand for glaucoma classification in an unbalanced data situation based on random forests could effectively be reduced by the application of pruning strategies without loss of performance in a population with increased risk of glaucoma.

Random forest feature selection, fusion and ensemble strategy: Combining multiple morphological MRI measures to discriminate among healhy elderly, MCI, cMCI and alzheimer's disease patients: From the alzheimer's disease neuroimaging initiative (ADNI) database.

PubMed

Dimitriadis, S I; Liparas, Dimitris; Tsolaki, Magda N

2018-05-15

In the era of computer-assisted diagnostic tools for various brain diseases, Alzheimer's disease (AD) covers a large percentage of neuroimaging research, with the main scope being its use in daily practice. However, there has been no study attempting to simultaneously discriminate among Healthy Controls (HC), early mild cognitive impairment (MCI), late MCI (cMCI) and stable AD, using features derived from a single modality, namely MRI. Based on preprocessed MRI images from the organizers of a neuroimaging challenge, 3 we attempted to quantify the prediction accuracy of multiple morphological MRI features to simultaneously discriminate among HC, MCI, cMCI and AD. We explored the efficacy of a novel scheme that includes multiple feature selections via Random Forest from subsets of the whole set of features (e.g. whole set, left/right hemisphere etc.), Random Forest classification using a fusion approach and ensemble classification via majority voting. From the ADNI database, 60 HC, 60 MCI, 60 cMCI and 60 CE were used as a training set with known labels. An extra dataset of 160 subjects (HC: 40, MCI: 40, cMCI: 40 and AD: 40) was used as an external blind validation dataset to evaluate the proposed machine learning scheme. In the second blind dataset, we succeeded in a four-class classification of 61.9% by combining MRI-based features with a Random Forest-based Ensemble Strategy. We achieved the best classification accuracy of all teams that participated in this neuroimaging competition. The results demonstrate the effectiveness of the proposed scheme to simultaneously discriminate among four groups using morphological MRI features for the very first time in the literature. Hence, the proposed machine learning scheme can be used to define single and multi-modal biomarkers for AD. Copyright © 2017 Elsevier B.V. All rights reserved.

An integrated classifier for computer-aided diagnosis of colorectal polyps based on random forest and location index strategies

NASA Astrophysics Data System (ADS)

Hu, Yifan; Han, Hao; Zhu, Wei; Li, Lihong; Pickhardt, Perry J.; Liang, Zhengrong

2016-03-01

Feature classification plays an important role in differentiation or computer-aided diagnosis (CADx) of suspicious lesions. As a widely used ensemble learning algorithm for classification, random forest (RF) has a distinguished performance for CADx. Our recent study has shown that the location index (LI), which is derived from the well-known kNN (k nearest neighbor) and wkNN (weighted k nearest neighbor) classifier [1], has also a distinguished role in the classification for CADx. Therefore, in this paper, based on the property that the LI will achieve a very high accuracy, we design an algorithm to integrate the LI into RF for improved or higher value of AUC (area under the curve of receiver operating characteristics -- ROC). Experiments were performed by the use of a database of 153 lesions (polyps), including 116 neoplastic lesions and 37 hyperplastic lesions, with comparison to the existing classifiers of RF and wkNN, respectively. A noticeable gain by the proposed integrated classifier was quantified by the AUC measure.

A k-mer-based barcode DNA classification methodology based on spectral representation and a neural gas network.

PubMed

Fiannaca, Antonino; La Rosa, Massimo; Rizzo, Riccardo; Urso, Alfonso

2015-07-01

In this paper, an alignment-free method for DNA barcode classification that is based on both a spectral representation and a neural gas network for unsupervised clustering is proposed. In the proposed methodology, distinctive words are identified from a spectral representation of DNA sequences. A taxonomic classification of the DNA sequence is then performed using the sequence signature, i.e., the smallest set of k-mers that can assign a DNA sequence to its proper taxonomic category. Experiments were then performed to compare our method with other supervised machine learning classification algorithms, such as support vector machine, random forest, ripper, naïve Bayes, ridor, and classification tree, which also consider short DNA sequence fragments of 200 and 300 base pairs (bp). The experimental tests were conducted over 10 real barcode datasets belonging to different animal species, which were provided by the on-line resource "Barcode of Life Database". The experimental results showed that our k-mer-based approach is directly comparable, in terms of accuracy, recall and precision metrics, with the other classifiers when considering full-length sequences. In addition, we demonstrate the robustness of our method when a classification is performed task with a set of short DNA sequences that were randomly extracted from the original data. For example, the proposed method can reach the accuracy of 64.8% at the species level with 200-bp fragments. Under the same conditions, the best other classifier (random forest) reaches the accuracy of 20.9%. Our results indicate that we obtained a clear improvement over the other classifiers for the study of short DNA barcode sequence fragments. Copyright © 2015 Elsevier B.V. All rights reserved.

Habitat typing versus advanced vegetation classification in western forests

Treesearch

Tony Kusbach; John Shaw; James Long; Helga Van Miegroet

2012-01-01

Major habitat and community types in northern Utah were compared with plant alliances and associations that were derived from fidelity- and diagnostic-species classification concepts. Each of these classification approaches was associated with important environmental factors. Within a 20,000-ha watershed, 103 forest ecosystems were described by physiographic features,...

The influence of multispectral scanner spatial resolution on forest feature classification

NASA Technical Reports Server (NTRS)

Sadowski, F. G.; Malila, W. A.; Sarno, J. E.; Nalepka, R. F.

1977-01-01

Inappropriate spatial resolution and corresponding data processing techniques may be major causes for non-optimal forest classification results frequently achieved from multispectral scanner (MSS) data. Procedures and results of empirical investigations are studied to determine the influence of MSS spatial resolution on the classification of forest features into levels of detail or hierarchies of information that might be appropriate for nationwide forest surveys and detailed in-place inventories. Two somewhat different, but related studies are presented. The first consisted of establishing classification accuracies for several hierarchies of features as spatial resolution was progressively coarsened from (2 meters) squared to (64 meters) squared. The second investigated the capabilities for specialized processing techniques to improve upon the results of conventional processing procedures for both coarse and fine resolution data.

Object-Based Classification and Change Detection of Hokkaido, Japan

NASA Astrophysics Data System (ADS)

Park, J. G.; Harada, I.; Kwak, Y.

2016-06-01

Topography and geology are factors to characterize the distribution of natural vegetation. Topographic contour is particularly influential on the living conditions of plants such as soil moisture, sunlight, and windiness. Vegetation associations having similar characteristics are present in locations having similar topographic conditions unless natural disturbances such as landslides and forest fires or artificial disturbances such as deforestation and man-made plantation bring about changes in such conditions. We developed a vegetation map of Japan using an object-based segmentation approach with topographic information (elevation, slope, slope direction) that is closely related to the distribution of vegetation. The results found that the object-based classification is more effective to produce a vegetation map than the pixel-based classification.

SU-D-207B-02: Early Grade Classification in Meningioma Patients Combining Radiomics and Semantics Data

DOE Office of Scientific and Technical Information (OSTI.GOV)

Coroller, T; Bi, W; Abedalthagafi, M

Purpose: The clinical management of meningioma is guided by its grade and biologic behavior. Currently, diagnosis of tumor grade follows surgical resection and histopathologic review. Reliable techniques for pre-operative determination of tumor behavior are needed. We investigated the association between imaging features extracted from preoperative gadolinium-enhanced T1-weighted MRI and meningioma grade. Methods: We retrospectively examined the pre-operative MRI for 139 patients with de novo WHO grade I (63%) and grade II (37%) meningiomas. We investigated the predictive power of ten semantic radiologic features as determined by a neuroradiologist, fifteen radiomic features, and tumor location. Conventional (volume and diameter) imaging featuresmore » were added for comparison. AUC was computed for continuous and χ{sup 2} for discrete variables. Classification was done using random forest. Performance was evaluated using cross validation (1000 iterations, 75% training and 25% validation). All p-values were adjusted for multiple testing. Results: Significant association was observed between meningioma grade and tumor location (p<0.001) and two semantic features including intra-tumoral heterogeneity (p<0.001) and overt hemorrhage (p=0.01). Conventional (AUC 0.61–0.67) and eleven radiomic (AUC 0.60–0.70) features were significant from random (p<0.05, Noether test). Median AUC values for classification of tumor grade were 0.57, 0.71, 0.72 and 0.77 respectively for conventional, radiomic, location, and semantic features after using random forest. By combining all imaging data (semantic, radiomic, and location), the median AUC was 0.81, which offers superior predicting power to that of conventional imaging descriptors for meningioma as well as radiomic features alone (p<0.05, permutation test). Conclusion: We demonstrate a strong association between radiologic features and meningioma grade. Pre-operative prediction of tumor behavior based on imaging features offers promise for guiding personalized medicine and improving patient management.« less

A study of Minnesota forests and lakes using data from earth resources technology satellites

NASA Technical Reports Server (NTRS)

1972-01-01

This project is to foster and develop new applications of remote sensing under an interdisciplinary effort. Seven reports make up the specific projects presently being conducted throughout the State of Minnesota in cooperation with several agencies and municipalities. These are included under the general headings of: (1) applications of aerial photography and ERTS-1 data to agricultural, forest, and water resources management; (2) classification and dynamics of water and wetland resources of Minnesota; (3) studies of Lake Superior Bay; and (4) feasibility of detecting major air pollutants by earth-oriented satellite-borne sensors.

36 CFR § 1237.30 - How do agencies manage records on nitrocellulose-base and cellulose-acetate base film?

Code of Federal Regulations, 2013 CFR

2013-07-01

... 36 Parks, Forests, and Public Property 3 2013-07-01 2012-07-01 true How do agencies manage records on nitrocellulose-base and cellulose-acetate base film? § 1237.30 Section § 1237.30 Parks, Forests..., CARTOGRAPHIC, AND RELATED RECORDS MANAGEMENT § 1237.30 How do agencies manage records on nitrocellulose-base...

Classifying land cover from an object-oriented approach - applied to LANDSAT 8 at the regional scale of the Lake Tana Basin (Ethiopia)

NASA Astrophysics Data System (ADS)

Lemma, Hanibal; Frankl, Amaury; Poesen, Jean; Adgo, Enyew; Nyssen, Jan

2017-04-01

Object-oriented image classification has been gaining prominence in the field of remote sensing and provides a valid alternative to the 'traditional' pixel based methods. Recent studies have proven the superiority of the object-based approach. So far, object-oriented land cover classifications have been applied either at limited spatial coverages (ranging 2 to 1091 km2) or by using very high resolution (0.5-16 m) imageries. The main aim of this study is to drive land cover information for large area from Landsat 8 OLI surface reflectance using the Estimation of Scale Parameter (ESP) tool and the object oriented software eCognition. The available land cover map of Lake Tana Basin (Ethiopia) is about 20 years old with a courser spatial scale (1:250,000) and has limited use for environmental modelling and monitoring studies. Up-to-date and basin wide land cover maps are essential to overcome haphazard natural resources management, land degradation and reduced agricultural production. Indeed, object-oriented approach involves image segmentation prior to classification, i.e. adjacent similar pixels are aggregated into segments as long as the heterogeneity in the spectral and spatial domains is minimized. For each segmented object, different attributes (spectral, textural and shape) were calculated and used for in subsequent classification analysis. Moreover, the commonly used error matrix is employed to determine the quality of the land cover map. As a result, the multiresolution segmentation (with parameters of scale=30, shape=0.3 and Compactness=0.7) produces highly homogeneous image objects as it is observed in different sample locations in google earth. Out of the 15,089 km2 area of the basin, cultivated land is dominant (69%) followed by water bodies (21%), grassland (4.8%), forest (3.7%) and shrubs (1.1%). Wetlands, artificial surfaces and bare land cover only about 1% of the basin. The overall classification accuracy is 80% with a Kappa coefficient of 0.75. With regard to individual classes, the classification show higher Producer's and User's accuracy (above 84%) for cultivated land, water bodies and forest, but lower (less than 70%) for shrubs, bare land and grassland. Key words: accuracy assessment, eCognition, Estimation of Scale Parameter, land cover, Landsat 8, remote sensing

[Construction of information management-based virtual forest landscape and its application].

PubMed

Chen, Chongcheng; Tang, Liyu; Quan, Bing; Li, Jianwei; Shi, Song

2005-11-01

Based on the analysis of the contents and technical characteristics of different scale forest visualization modeling, this paper brought forward the principles and technical systems of constructing an information management-based virtual forest landscape. With the combination of process modeling and tree geometric structure description, a software method of interactively and parameterized tree modeling was developed, and the corresponding renderings and geometrical elements simplification algorithms were delineated to speed up rendering run-timely. As a pilot study, the geometrical model bases associated with the typical tree categories in Zhangpu County of Fujian Province, southeast China were established as template files. A Virtual Forest Management System prototype was developed with GIS component (ArcObject), OpenGL graphics environment, and Visual C++ language, based on forest inventory and remote sensing data. The prototype could be used for roaming between 2D and 3D, information query and analysis, and virtual and interactive forest growth simulation, and its reality and accuracy could meet the needs of forest resource management. Some typical interfaces of the system and the illustrative scene cross-sections of simulated masson pine growth under conditions of competition and thinning were listed.

An AUC-based permutation variable importance measure for random forests

PubMed Central

2013-01-01

Background The random forest (RF) method is a commonly used tool for classification with high dimensional data as well as for ranking candidate predictors based on the so-called random forest variable importance measures (VIMs). However the classification performance of RF is known to be suboptimal in case of strongly unbalanced data, i.e. data where response class sizes differ considerably. Suggestions were made to obtain better classification performance based either on sampling procedures or on cost sensitivity analyses. However to our knowledge the performance of the VIMs has not yet been examined in the case of unbalanced response classes. In this paper we explore the performance of the permutation VIM for unbalanced data settings and introduce an alternative permutation VIM based on the area under the curve (AUC) that is expected to be more robust towards class imbalance. Results We investigated the performance of the standard permutation VIM and of our novel AUC-based permutation VIM for different class imbalance levels using simulated data and real data. The results suggest that the new AUC-based permutation VIM outperforms the standard permutation VIM for unbalanced data settings while both permutation VIMs have equal performance for balanced data settings. Conclusions The standard permutation VIM loses its ability to discriminate between associated predictors and predictors not associated with the response for increasing class imbalance. It is outperformed by our new AUC-based permutation VIM for unbalanced data settings, while the performance of both VIMs is very similar in the case of balanced classes. The new AUC-based VIM is implemented in the R package party for the unbiased RF variant based on conditional inference trees. The codes implementing our study are available from the companion website: http://www.ibe.med.uni-muenchen.de/organisation/mitarbeiter/070_drittmittel/janitza/index.html. PMID:23560875

An AUC-based permutation variable importance measure for random forests.

PubMed

Janitza, Silke; Strobl, Carolin; Boulesteix, Anne-Laure

2013-04-05

The random forest (RF) method is a commonly used tool for classification with high dimensional data as well as for ranking candidate predictors based on the so-called random forest variable importance measures (VIMs). However the classification performance of RF is known to be suboptimal in case of strongly unbalanced data, i.e. data where response class sizes differ considerably. Suggestions were made to obtain better classification performance based either on sampling procedures or on cost sensitivity analyses. However to our knowledge the performance of the VIMs has not yet been examined in the case of unbalanced response classes. In this paper we explore the performance of the permutation VIM for unbalanced data settings and introduce an alternative permutation VIM based on the area under the curve (AUC) that is expected to be more robust towards class imbalance. We investigated the performance of the standard permutation VIM and of our novel AUC-based permutation VIM for different class imbalance levels using simulated data and real data. The results suggest that the new AUC-based permutation VIM outperforms the standard permutation VIM for unbalanced data settings while both permutation VIMs have equal performance for balanced data settings. The standard permutation VIM loses its ability to discriminate between associated predictors and predictors not associated with the response for increasing class imbalance. It is outperformed by our new AUC-based permutation VIM for unbalanced data settings, while the performance of both VIMs is very similar in the case of balanced classes. The new AUC-based VIM is implemented in the R package party for the unbiased RF variant based on conditional inference trees. The codes implementing our study are available from the companion website: http://www.ibe.med.uni-muenchen.de/organisation/mitarbeiter/070_drittmittel/janitza/index.html.

Forest Service Resource Inventories: An Overview

Treesearch

USDA Forest Service

1992-01-01

Forest and related resource inventories are conducted by the US. Forest Service to provide the quantitative base necessary for making sound management, conservation, and stewardship decisions affecting these valuable resources. Inventory information has guided the management of 191 million acres (77.3 million ha) of publicly-owned National Forest land. Forest...

Hydrological modelling in forested systems | Science ...

EPA Pesticide Factsheets

This chapter provides a brief overview of forest hydrology modelling approaches for answering important global research and management questions. Many hundreds of hydrological models have been applied globally across multiple decades to represent and predict forest hydrological processes. The focus of this chapter is on process-based models and approaches, specifically 'forest hydrology models'; that is, physically based simulation tools that quantify compartments of the forest hydrological cycle. Physically based models can be considered those that describe the conservation of mass, momentum and/or energy. The purpose of this chapter is to provide a brief overview of forest hydrology modeling approaches for answering important global research and management questions. The focus of this chapter is on process-based models and approaches, specifically “forest hydrology models”, i.e., physically-based simulation tools that quantify compartments of the forest hydrological cycle.

Forest resource information system

NASA Technical Reports Server (NTRS)

Mroczynski, R. P. (Principal Investigator)

1978-01-01

The author has identified the following significant results. A benchmark classification evaluation framework was implemented. The FRIS preprocessing activities were refined. Potential geo-based referencing systems were identified as components of FRIS.

New classification of natural breeding habitats for Neotropical anophelines in the Yanomami Indian Reserve, Amazon Region, Brazil and a new larval sampling methodology.

PubMed

Sánchez-Ribas, Jordi; Oliveira-Ferreira, Joseli; Rosa-Freitas, Maria Goreti; Trilla, Lluís; Silva-do-Nascimento, Teresa Fernandes

2015-09-01

Here we present the first in a series of articles about the ecology of immature stages of anophelines in the Brazilian Yanomami area. We propose a new larval habitat classification and a new larval sampling methodology. We also report some preliminary results illustrating the applicability of the methodology based on data collected in the Brazilian Amazon rainforest in a longitudinal study of two remote Yanomami communities, Parafuri and Toototobi. In these areas, we mapped and classified 112 natural breeding habitats located in low-order river systems based on their association with river flood pulses, seasonality and exposure to sun. Our classification rendered seven types of larval habitats: lakes associated with the river, which are subdivided into oxbow lakes and nonoxbow lakes, flooded areas associated with the river, flooded areas not associated with the river, rainfall pools, small forest streams, medium forest streams and rivers. The methodology for larval sampling was based on the accurate quantification of the effective breeding area, taking into account the area of the perimeter and subtypes of microenvironments present per larval habitat type using a laser range finder and a small portable inflatable boat. The new classification and new sampling methodology proposed herein may be useful in vector control programs.

New classification of natural breeding habitats for Neotropical anophelines in the Yanomami Indian Reserve, Amazon Region, Brazil and a new larval sampling methodology

PubMed Central

Sánchez-Ribas, Jordi; Oliveira-Ferreira, Joseli; Rosa-Freitas, Maria Goreti; Trilla, Lluís; Silva-do-Nascimento, Teresa Fernandes

2015-01-01

Here we present the first in a series of articles about the ecology of immature stages of anophelines in the Brazilian Yanomami area. We propose a new larval habitat classification and a new larval sampling methodology. We also report some preliminary results illustrating the applicability of the methodology based on data collected in the Brazilian Amazon rainforest in a longitudinal study of two remote Yanomami communities, Parafuri and Toototobi. In these areas, we mapped and classified 112 natural breeding habitats located in low-order river systems based on their association with river flood pulses, seasonality and exposure to sun. Our classification rendered seven types of larval habitats: lakes associated with the river, which are subdivided into oxbow lakes and nonoxbow lakes, flooded areas associated with the river, flooded areas not associated with the river, rainfall pools, small forest streams, medium forest streams and rivers. The methodology for larval sampling was based on the accurate quantification of the effective breeding area, taking into account the area of the perimeter and subtypes of microenvironments present per larval habitat type using a laser range finder and a small portable inflatable boat. The new classification and new sampling methodology proposed herein may be useful in vector control programs. PMID:26517655

Recreation-related perceptions of natural resource managers in the Saranac Lakes wild forest area

Treesearch

Diane Kuehn; Mark Mink; Rudy Schuster

2007-01-01

Public forest managers often work with diverse stakeholder groups as they implement forest management policies. Within the Saranac Lakes Wild Forest area of New York State's Adirondack Park, stakeholder groups such as visitors, business owners, and landowners often have conflicting perceptions about issues related to water-based recreation in the region's...

Site index determination techniques for southern bottomland hardwoods

Treesearch

Brian Roy Lockhart

2013-01-01

Site index is a species-specific indirect measure of forest productivity expressed as the average height of dominant and codominant trees in a stand of a specified base age. It is widely used by forest managers to make informed decisions regarding forest management practices. Unfortunately, forest managers have difficulty in determining site index for southern US...

3-PG simulations of young ponderosa pine plantations under varied management intensity: why do they grow so differently?

Treesearch

Liang Wei; Marshall John; Jianwei Zhang; Hang Zhou; Robert Powers

2014-01-01

Models can be powerful tools for estimating forest productivity and guiding forest management, but their credibility and complexity are often an issue for forest managers. We parameterized a process-based forest growth model, 3-PG (Physiological Principles Predicting Growth), to simulate growth of ponderosa pine (Pinus ponderosa) plantations in...

Investigating the Capability of IRS-P6-LISS IV Satellite Image for Pistachio Forests Density Mapping (case Study: Northeast of Iran)

NASA Astrophysics Data System (ADS)

Hoseini, F.; Darvishsefat, A. A.; Zargham, N.

2012-07-01

In order to investigate the capability of satellite images for Pistachio forests density mapping, IRS-P6-LISS IV data were analyzed in an area of 500 ha in Iran. After geometric correction, suitable training areas were determined based on fieldwork. Suitable spectral transformations like NDVI, PVI and PCA were performed. A ground truth map included of 34 plots (each plot 1 ha) were prepared. Hard and soft supervised classifications were performed with 5 density classes (0-5%, 5-10%, 10-15%, 15-20% and > 20%). Because of low separability of classes, some classes were merged and classifications were repeated with 3 classes. Finally, the highest overall accuracy and kappa coefficient of 70% and 0.44, respectively, were obtained with three classes (0-5%, 5-20%, and > 20%) by fuzzy classifier. Considering the low kappa value obtained, it could be concluded that the result of the classification was not desirable. Therefore, this approach is not appropriate for operational mapping of these valuable Pistachio forests.

Forest statistics for Arkansas' Ouachita counties - 1988

Treesearch

F. Dee Hines

1988-01-01

Tabulated results were derived from data obtained during a recent inventory of 10 counties comprising the Ouachita Unit of Arkansas. Data on forest acreage and timber volume were secured by a three-step process. A forest-nonforest classification using aerial photographs was accomplished for points representing approximately 230 acres. These photo classifications were...

Accuracy assessment of biomass and forested area classification from modis, landstat-tm satellite imagery and forest inventory plot data

Treesearch

Dumitru Salajanu; Dennis M. Jacobs

2007-01-01

The objective of this study was to determine how well forestfnon-forest and biomass classifications obtained from Landsat-TM and MODIS satellite data modeled with FIA plots, compare to each other and with forested area and biomass estimates from the national inventory data, as well as whether there is an increase in overall accuracy when pixel size (spatial resolution...

Cancer Pain: A Critical Review of Mechanism-based Classification and Physical Therapy Management in Palliative Care

PubMed Central

Kumar, Senthil P

2011-01-01

Mechanism-based classification and physical therapy management of pain is essential to effectively manage painful symptoms in patients attending palliative care. The objective of this review is to provide a detailed review of mechanism-based classification and physical therapy management of patients with cancer pain. Cancer pain can be classified based upon pain symptoms, pain mechanisms and pain syndromes. Classification based upon mechanisms not only addresses the underlying pathophysiology but also provides us with an understanding behind patient's symptoms and treatment responses. Existing evidence suggests that the five mechanisms – central sensitization, peripheral sensitization, sympathetically maintained pain, nociceptive and cognitive-affective – operate in patients with cancer pain. Summary of studies showing evidence for physical therapy treatment methods for cancer pain follows with suggested therapeutic implications. Effective palliative physical therapy care using a mechanism-based classification model should be tailored to suit each patient's findings, using a biopsychosocial model of pain. PMID:21976851

Landscape variation in species diversity and succession as related to topography, soils and human disturbance

Treesearch

Jeffery N. Pearcy; David M. Hix; Stacy A. Drury

1995-01-01

Three hundred and thirty-two plots have been sampled on the Wayne National Forest of southeastern Ohio, for the purpose of developing an ecological classification system (ECS). The ECS will be based on the herbaceous and woody vegetation, soils and topography of mature (80-140 year-old), relatively-undisturbed forests. Species diversity changes little across this...

Relating FIA data to habitat classifications via tree-based models of canopy cover

Treesearch

Mark D. Nelson; Brian G. Tavernia; Chris Toney; Brian F. Walters

2012-01-01

Wildlife species-habitat matrices are used to relate lists of species with abundance of their habitats. The Forest Inventory and Analysis Program provides data on forest composition and structure, but these attributes may not correspond directly with definitions of wildlife habitats. We used FIA tree data and tree crown diameter models to estimate canopy cover, from...

Detecting the Upstream Extent of Fish in the Redwood Region of Northern California

Treesearch

Aaron K. Bliesner; E. George Robison

2007-01-01

The point at which fish use ends represents a key ecological and regulatory demarcation on state and private forest land in the Redwood region. Currently, the end of fish use and other key demarcations with stream classification are measured or estimated based on judgments of Registered Professional Foresters and aquatic biologists with little guidance from empirical...

Consistency of forest presence and biomass predictions modeled across overlapping spatial and temporal extents

Treesearch

Mark D. Nelson; Sean Healey; W. Keith Moser; J.G. Masek; Warren Cohen

2011-01-01

We assessed the consistency across space and time of spatially explicit models of forest presence and biomass in southern Missouri, USA, for adjacent, partially overlapping satellite image Path/Rows, and for coincident satellite images from the same Path/Row acquired in different years. Such consistency in satellite image-based classification and estimation is critical...

Random forests for classification in ecology

USGS Publications Warehouse

Cutler, D.R.; Edwards, T.C.; Beard, K.H.; Cutler, A.; Hess, K.T.; Gibson, J.; Lawler, J.J.

2007-01-01

Classification procedures are some of the most widely used statistical methods in ecology. Random forests (RF) is a new and powerful statistical classifier that is well established in other disciplines but is relatively unknown in ecology. Advantages of RF compared to other statistical classifiers include (1) very high classification accuracy; (2) a novel method of determining variable importance; (3) ability to model complex interactions among predictor variables; (4) flexibility to perform several types of statistical data analysis, including regression, classification, survival analysis, and unsupervised learning; and (5) an algorithm for imputing missing values. We compared the accuracies of RF and four other commonly used statistical classifiers using data on invasive plant species presence in Lava Beds National Monument, California, USA, rare lichen species presence in the Pacific Northwest, USA, and nest sites for cavity nesting birds in the Uinta Mountains, Utah, USA. We observed high classification accuracy in all applications as measured by cross-validation and, in the case of the lichen data, by independent test data, when comparing RF to other common classification methods. We also observed that the variables that RF identified as most important for classifying invasive plant species coincided with expectations based on the literature. ?? 2007 by the Ecological Society of America.

Random-Forest Classification of High-Resolution Remote Sensing Images and Ndsm Over Urban Areas

NASA Astrophysics Data System (ADS)

Sun, X. F.; Lin, X. G.

2017-09-01

As an intermediate step between raw remote sensing data and digital urban maps, remote sensing data classification has been a challenging and long-standing research problem in the community of remote sensing. In this work, an effective classification method is proposed for classifying high-resolution remote sensing data over urban areas. Starting from high resolution multi-spectral images and 3D geometry data, our method proceeds in three main stages: feature extraction, classification, and classified result refinement. First, we extract color, vegetation index and texture features from the multi-spectral image and compute the height, elevation texture and differential morphological profile (DMP) features from the 3D geometry data. Then in the classification stage, multiple random forest (RF) classifiers are trained separately, then combined to form a RF ensemble to estimate each sample's category probabilities. Finally the probabilities along with the feature importance indicator outputted by RF ensemble are used to construct a fully connected conditional random field (FCCRF) graph model, by which the classification results are refined through mean-field based statistical inference. Experiments on the ISPRS Semantic Labeling Contest dataset show that our proposed 3-stage method achieves 86.9% overall accuracy on the test data.

An ecological classification system for the central hardwoods region: The Hoosier National Forest

Treesearch

James E. Van Kley; George R. Parker

1993-01-01

This study, a multifactor ecological classification system, using vegetation, soil characteristics, and physiography, was developed for the landscape of the Hoosier National Forest in Southern Indiana. Measurements of ground flora, saplings, and canopy trees from selected stands older than 80 years were subjected to TWINSPAN classification and DECORANA ordination....

Landsat for practical forest type mapping - A test case

NASA Technical Reports Server (NTRS)

Bryant, E.; Dodge, A. G., Jr.; Warren, S. D.

1980-01-01

Computer classified Landsat maps are compared with a recent conventional inventory of forest lands in northern Maine. Over the 196,000 hectare area mapped, estimates of the areas of softwood, mixed wood and hardwood forest obtained by a supervised classification of the Landsat data and a standard inventory based on aerial photointerpretation, probability proportional to prediction, field sampling and a standard forest measurement program are found to agree to within 5%. The cost of the Landsat maps is estimated to be $0.065/hectare. It is concluded that satellite techniques are worth developing for forest inventories, although they are not yet refined enough to be incorporated into current practical inventories.

Historical land-cover classification for conservation and management in Hawaiian subalpine drylands

Treesearch

James R. Kellner; Gregory P. Asner; Susan Cordell; Jarrod M. Thaxton; Kealoha M. Kinney; Ty Kennedy-Bowdoin; David E. Knapp; Erin F. Questad; Stephen Ambagis

2012-01-01

We used aerial photography from 1954 and airborne LiDAR and imaging spectroscopy from 2008 to infer changes in extent and location of tallstature woody vegetation in 127 km2 of subalpine dry forest on the island of Hawaii (Pohakuloa Training Area), and to identify 25.8 km2 of intact woody vegetation for restoration and...

Development of seed zones for the Eastern United States: Request for input and collaboration!

Treesearch

Carrie C. Pike; George Hernandez; Barbara Crane; Paul Berrang

2017-01-01

Artificial regeneration is necessary for meeting a variety of management objectives following timber harvests and other disturbances. While foresters use ecological classification to identify the most appropriate species to plant on a particular site, they generally use seed zones to identify the most suitable seed source of that species to plant. Seed zones have been...

Water, Forests, People: The Swedish Experience in Building Resilient Landscapes.

PubMed

Eriksson, Mats; Samuelson, Lotta; Jägrud, Linnéa; Mattsson, Eskil; Celander, Thorsten; Malmer, Anders; Bengtsson, Klas; Johansson, Olof; Schaaf, Nicolai; Svending, Ola; Tengberg, Anna

2018-07-01

A growing world population and rapid expansion of cities increase the pressure on basic resources such as water, food and energy. To safeguard the provision of these resources, restoration and sustainable management of landscapes is pivotal, including sustainable forest and water management. Sustainable forest management includes forest conservation, restoration, forestry and agroforestry practices. Interlinkages between forests and water are fundamental to moderate water budgets, stabilize runoff, reduce erosion and improve biodiversity and water quality. Sweden has gained substantial experience in sustainable forest management in the past century. Through significant restoration efforts, a largely depleted Swedish forest has transformed into a well-managed production forest within a century, leading to sustainable economic growth through the provision of forest products. More recently, ecosystem services are also included in management decisions. Such a transformation depends on broad stakeholder dialog, combined with an enabling institutional and policy environment. Based on seminars and workshops with a wide range of key stakeholders managing Sweden's forests and waters, this article draws lessons from the history of forest management in Sweden. These lessons are particularly relevant for countries in the Global South that currently experience similar challenges in forest and landscape management. The authors argue that an integrated landscape approach involving a broad array of sectors and stakeholders is needed to achieve sustainable forest and water management. Sustainable landscape management-integrating water, agriculture and forests-is imperative to achieving resilient socio-economic systems and landscapes.

Land cover and land use mapping of the iSimangaliso Wetland Park, South Africa: comparison of oblique and orthogonal random forest algorithms

NASA Astrophysics Data System (ADS)

Bassa, Zaakirah; Bob, Urmilla; Szantoi, Zoltan; Ismail, Riyad

2016-01-01

In recent years, the popularity of tree-based ensemble methods for land cover classification has increased significantly. Using WorldView-2 image data, we evaluate the potential of the oblique random forest algorithm (oRF) to classify a highly heterogeneous protected area. In contrast to the random forest (RF) algorithm, the oRF algorithm builds multivariate trees by learning the optimal split using a supervised model. The oRF binary algorithm is adapted to a multiclass land cover and land use application using both the "one-against-one" and "one-against-all" combination approaches. Results show that the oRF algorithms are capable of achieving high classification accuracies (>80%). However, there was no statistical difference in classification accuracies obtained by the oRF algorithms and the more popular RF algorithm. For all the algorithms, user accuracies (UAs) and producer accuracies (PAs) >80% were recorded for most of the classes. Both the RF and oRF algorithms poorly classified the indigenous forest class as indicated by the low UAs and PAs. Finally, the results from this study advocate and support the utility of the oRF algorithm for land cover and land use mapping of protected areas using WorldView-2 image data.

Balancing trade-offs between ecosystem services in Germany’s forests under climate change

NASA Astrophysics Data System (ADS)

Gutsch, Martin; Lasch-Born, Petra; Kollas, Chris; Suckow, Felicitas; Reyer, Christopher P. O.

2018-04-01

Germany’s forests provide a variety of ecosystem services. Sustainable forest management aims to optimize the provision of these services at regional level. However, climate change will impact forest ecosystems and subsequently ecosystem services. The objective of this study is to quantify the effects of two alternative management scenarios and climate impacts on forest variables indicative of ecosystem services related to timber, habitat, water, and carbon. The ecosystem services are represented through nine model output variables (timber harvest, above and belowground biomass, net ecosystem production, soil carbon, percolation, nitrogen leaching, deadwood, tree dimension, broadleaf tree proportion) from the process-based forest model 4C. We simulated forest growth, carbon and water cycling until 2045 with 4C set-up for the whole German forest area based on National Forest Inventory data and driven by three management strategies (nature protection, biomass production and a baseline management) and an ensemble of regional climate scenarios (RCP2.6, RCP 4.5, RCP 8.5). We provide results as relative changes compared to the baseline management and observed climate. Forest management measures have the strongest effects on ecosystem services inducing positive or negative changes of up to 40% depending on the ecosystem service in question, whereas climate change only slightly alters ecosystem services averaged over the whole forest area. The ecosystem services ‘carbon’ and ‘timber’ benefit from climate change, while ‘water’ and ‘habitat’ lose. We detect clear trade-offs between ‘timber’ and all other ecosystem services, as well as synergies between ‘habitat’ and ‘carbon’. When evaluating all ecosystem services simultaneously, our results reveal certain interrelations between climate and management scenarios. North-eastern and western forest regions are more suitable to provide timber (while minimizing the negative impacts on remaining ecosystem services) whereas southern and central forest regions are more suitable to fulfil ‘habitat’ and ‘carbon’ services. The results provide the base for future forest management optimizations at the regional scale in order to maximize ecosystem services and forest ecosystem sustainability at the national scale.

Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms.

PubMed

Ozcift, Akin; Gulten, Arif

2011-12-01

Improving accuracies of machine learning algorithms is vital in designing high performance computer-aided diagnosis (CADx) systems. Researches have shown that a base classifier performance might be enhanced by ensemble classification strategies. In this study, we construct rotation forest (RF) ensemble classifiers of 30 machine learning algorithms to evaluate their classification performances using Parkinson's, diabetes and heart diseases from literature. While making experiments, first the feature dimension of three datasets is reduced using correlation based feature selection (CFS) algorithm. Second, classification performances of 30 machine learning algorithms are calculated for three datasets. Third, 30 classifier ensembles are constructed based on RF algorithm to assess performances of respective classifiers with the same disease data. All the experiments are carried out with leave-one-out validation strategy and the performances of the 60 algorithms are evaluated using three metrics; classification accuracy (ACC), kappa error (KE) and area under the receiver operating characteristic (ROC) curve (AUC). Base classifiers succeeded 72.15%, 77.52% and 84.43% average accuracies for diabetes, heart and Parkinson's datasets, respectively. As for RF classifier ensembles, they produced average accuracies of 74.47%, 80.49% and 87.13% for respective diseases. RF, a newly proposed classifier ensemble algorithm, might be used to improve accuracy of miscellaneous machine learning algorithms to design advanced CADx systems. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

Classification of the Gabon SAR Mosaic Using a Wavelet Based Rule Classifier

NASA Technical Reports Server (NTRS)

Simard, Marc; Saatchi, Sasan; DeGrandi, Gianfranco

2000-01-01

A method is developed for semi-automated classification of SAR images of the tropical forest. Information is extracted using the wavelet transform (WT). The transform allows for extraction of structural information in the image as a function of scale. In order to classify the SAR image, a Desicion Tree Classifier is used. The method of pruning is used to optimize classification rate versus tree size. The results give explicit insight on the type of information useful for a given class.

Disturbance ecology and forest management: A review of the literature

Treesearch

Paul Rogers

1996-01-01

This review of the disturbance ecology literature, and how it pertains to forest management, is a resource for forest managers and researchers interested in disturbance theory, specific disturbance agents, their interactions, and appropriate methods of inquiry for specific geographic regions. Implications for the future of disturbance ecology-based management are...

Ground-based photographic monitoring.

Treesearch

Frederick C. Hall

2001-01-01

Land management professionals (foresters, wildlife biologists, range managers, and land managers such as ranchers and forest land owners) often have need to evaluate their management activities. Photographic monitoring is a fast, simple, and effective way to determine if changes made to an area have been successful. Ground-based photo monitoring means using photographs...

Application of satellite data and LARS's data processing techniques to mapping vegetation of the Dismal Swamp. M.S. Thesis - Old Dominion Univ.

NASA Technical Reports Server (NTRS)

Messmore, J. A.

1976-01-01

The feasibility of using digital satellite imagery and automatic data processing techniques as a means of mapping swamp forest vegetation was considered, using multispectral scanner data acquired by the LANDSAT-1 satellite. The site for this investigation was the Dismal Swamp, a 210,000 acre swamp forest located south of Suffolk, Va. on the Virginia-North Carolina border. Two basic classification strategies were employed. The initial classification utilized unsupervised techniques which produced a map of the swamp indicating the distribution of thirteen forest spectral classes. These classes were later combined into three informational categories: Atlantic white cedar (Chamaecyparis thyoides), Loblolly pine (Pinus taeda), and deciduous forest. The subsequent classification employed supervised techniques which mapped Atlantic white cedar, Loblolly pine, deciduous forest, water and agriculture within the study site. A classification accuracy of 82.5% was produced by unsupervised techniques compared with 89% accuracy using supervised techniques.

Characterization and classification of vegetation canopy structure and distribution within the Great Smoky Mountains National Park using LiDAR

DOE Office of Scientific and Technical Information (OSTI.GOV)

Kumar, Jitendra; HargroveJr., William Walter; Norman, Steven P

Vegetation canopy structure is a critically important habit characteristic for many threatened and endangered birds and other animal species, and it is key information needed by forest and wildlife managers for monitoring and managing forest resources, conservation planning and fostering biodiversity. Advances in Light Detection and Ranging (LiDAR) technologies have enabled remote sensing-based studies of vegetation canopies by capturing three-dimensional structures, yielding information not available in two-dimensional images of the landscape pro- vided by traditional multi-spectral remote sensing platforms. However, the large volume data sets produced by airborne LiDAR instruments pose a significant computational challenge, requiring algorithms to identify andmore » analyze patterns of interest buried within LiDAR point clouds in a computationally efficient manner, utilizing state-of-art computing infrastructure. We developed and applied a computationally efficient approach to analyze a large volume of LiDAR data and to characterize and map the vegetation canopy structures for 139,859 hectares (540 sq. miles) in the Great Smoky Mountains National Park. This study helps improve our understanding of the distribution of vegetation and animal habitats in this extremely diverse ecosystem.« less

Predictive mapping for tree sizes and densities in southeast Alaska.

Treesearch

John P. Caouette; Eugene J. DeGayner

2005-01-01

The Forest Service has relied on a single forest measure, timber volume, to meet many management and planning information needs in southeast Alaska. This economic-based categorization of forest types tends to mask critical information relevant to other contemporary forest-management issues, such as modeling forest structure, ecosystem diversity, or wildlife habitat. We...

Intervention for the collaborative use of Geographic Information Systems by private forest landowners: a meaning-centered perspective

Treesearch

Kirk D. Sinclair; Barbara A. Knuth

2001-01-01

Private forest landowners support the stewardship objectives that can be achieved through ecosystems-based management. However, ecosystems-based management is a data intensive approach that focuses upon the broad forest landscape. Intervention by forestry agents or agencies could help neighboring landowners to collaborate with an ecosystems-based approach in pursuit of...

Focused sunlight factor of forest fire danger assessment using Web-GIS and RS technologies

NASA Astrophysics Data System (ADS)

Baranovskiy, Nikolay V.; Sherstnyov, Vladislav S.; Yankovich, Elena P.; Engel, Marina V.; Belov, Vladimir V.

2016-08-01

Timiryazevskiy forestry of Tomsk region (Siberia, Russia) is a study area elaborated in current research. Forest fire danger assessment is based on unique technology using probabilistic criterion, statistical data on forest fires, meteorological conditions, forest sites classification and remote sensing data. MODIS products are used for estimating some meteorological conditions and current forest fire situation. Geonformation technologies are used for geospatial analysis of forest fire danger situation on controlled forested territories. GIS-engine provides opportunities to construct electronic maps with different levels of forest fire probability and support raster layer for satellite remote sensing data on current forest fires. Web-interface is used for data loading on specific web-site and for forest fire danger data representation via World Wide Web. Special web-forms provide interface for choosing of relevant input data in order to process the forest fire danger data and assess the forest fire probability.

California's forest resources. Preliminary assessment

DOE Office of Scientific and Technical Information (OSTI.GOV)

Not Available

1979-01-01

This Preliminary Assessment was prepared in response to the California Forest Resources Assessment and Policy Act of 1977 (FRAPA). This Act was passed to improve the information base upon which State resource administrators formulate forest policy. The Act provides for this report and a full assessment by 1987 and at five year intervals thereafter. Information is presented under the following chapter titles: introduction to the forest resources assessment program; the forest area: a general description; classifications of the forest lands; the watersheds; forest lands and the air resource; fish and wildlife resources; the forested rangelands; the wilderness; forest lands asmore » a recreation resource; the timber resource; wood energy; forest lands and the mineral, fossil fuels, and geothermal energy resources; mathematically modeling California's forest lands; vegetation mapping using remote sensing technology; important forest resources legislation; and, State and cooperative State/Federal forestry programs. Twelve indexes, a bibliography, and glossary are included. (JGB)« less

An assessment of the effectiveness of a random forest classifier for land-cover classification

NASA Astrophysics Data System (ADS)

Rodriguez-Galiano, V. F.; Ghimire, B.; Rogan, J.; Chica-Olmo, M.; Rigol-Sanchez, J. P.

2012-01-01

Land cover monitoring using remotely sensed data requires robust classification methods which allow for the accurate mapping of complex land cover and land use categories. Random forest (RF) is a powerful machine learning classifier that is relatively unknown in land remote sensing and has not been evaluated thoroughly by the remote sensing community compared to more conventional pattern recognition techniques. Key advantages of RF include: their non-parametric nature; high classification accuracy; and capability to determine variable importance. However, the split rules for classification are unknown, therefore RF can be considered to be black box type classifier. RF provides an algorithm for estimating missing values; and flexibility to perform several types of data analysis, including regression, classification, survival analysis, and unsupervised learning. In this paper, the performance of the RF classifier for land cover classification of a complex area is explored. Evaluation was based on several criteria: mapping accuracy, sensitivity to data set size and noise. Landsat-5 Thematic Mapper data captured in European spring and summer were used with auxiliary variables derived from a digital terrain model to classify 14 different land categories in the south of Spain. Results show that the RF algorithm yields accurate land cover classifications, with 92% overall accuracy and a Kappa index of 0.92. RF is robust to training data reduction and noise because significant differences in kappa values were only observed for data reduction and noise addition values greater than 50 and 20%, respectively. Additionally, variables that RF identified as most important for classifying land cover coincided with expectations. A McNemar test indicates an overall better performance of the random forest model over a single decision tree at the 0.00001 significance level.

Ecosystem Service Valuation Assessments for Protected Area Management: A Case Study Comparing Methods Using Different Land Cover Classification and Valuation Approaches

PubMed Central

Whitham, Charlotte E. L.

2015-01-01

Accurate and spatially-appropriate ecosystem service valuations are vital for decision-makers and land managers. Many approaches for estimating ecosystem service value (ESV) exist, but their appropriateness under specific conditions or logistical limitations is not uniform. The most accurate techniques are therefore not always adopted. Six different assessment approaches were used to estimate ESV for a National Nature Reserve in southwest China, across different management zones. These approaches incorporated two different land-use land cover (LULC) maps and development of three economic valuation techniques, using globally or locally-derived data. The differences in ESV across management zones for the six approaches were largely influenced by the classifications of forest and farmland and how they corresponded with valuation coefficients. With realistic limits on access to time, data, skills and resources, and using acquired estimates from globally-relevant sources, the Buffer zone was estimated as the most valuable (2.494 million ± 1.371 million CNY yr-1 km-2) and the Non-protected zone as the least valuable (770,000 ± 4,600 CNY yr-1 km-2). However, for both LULC maps, when using the locally-based and more time and skill-intensive valuation approaches, this pattern was generally reversed. This paper provides a detailed practical example of how ESV can differ widely depending on the availability and appropriateness of LULC maps and valuation approaches used, highlighting pitfalls for the managers of protected areas. PMID:26086191

Fuels planning: science synthesis and integration; forest structure and fire hazard fact sheet 03: visualizing forest structure and fuels

Treesearch

Rocky Mountain Research Station USDA Forest Service

2004-01-01

The software described in this fact sheet provides managers with tools for visualizing forest and fuels information. Computer-based landscape simulations can help visualize stand and landscape conditions and the effects of different management treatments and fuel changes over time. These visualizations can assist forest planning by considering a range of management...

Long-term soil productivity: genesis of the concept and principles behind the program

Treesearch

Robert F. Powers

2006-01-01

The capacity of a forest site to capture carbon and convert it into biomass defines fundamental site productivity. In the United States, the National Forest Management Act (NFMA) of 1976 mandates that this capacity must be protected on federally managed lands. Responding to NFMA, the USDA Forest Service began a soil-based monitoring program for its managed forests....

Method: automatic segmentation of mitochondria utilizing patch classification, contour pair classification, and automatically seeded level sets

PubMed Central

2012-01-01

Background While progress has been made to develop automatic segmentation techniques for mitochondria, there remains a need for more accurate and robust techniques to delineate mitochondria in serial blockface scanning electron microscopic data. Previously developed texture based methods are limited for solving this problem because texture alone is often not sufficient to identify mitochondria. This paper presents a new three-step method, the Cytoseg process, for automated segmentation of mitochondria contained in 3D electron microscopic volumes generated through serial block face scanning electron microscopic imaging. The method consists of three steps. The first is a random forest patch classification step operating directly on 2D image patches. The second step consists of contour-pair classification. At the final step, we introduce a method to automatically seed a level set operation with output from previous steps. Results We report accuracy of the Cytoseg process on three types of tissue and compare it to a previous method based on Radon-Like Features. At step 1, we show that the patch classifier identifies mitochondria texture but creates many false positive pixels. At step 2, our contour processing step produces contours and then filters them with a second classification step, helping to improve overall accuracy. We show that our final level set operation, which is automatically seeded with output from previous steps, helps to smooth the results. Overall, our results show that use of contour pair classification and level set operations improve segmentation accuracy beyond patch classification alone. We show that the Cytoseg process performs well compared to another modern technique based on Radon-Like Features. Conclusions We demonstrated that texture based methods for mitochondria segmentation can be enhanced with multiple steps that form an image processing pipeline. While we used a random-forest based patch classifier to recognize texture, it would be possible to replace this with other texture identifiers, and we plan to explore this in future work. PMID:22321695

Adaptive forest management for drinking water protection under climate change

NASA Astrophysics Data System (ADS)

Koeck, R.; Hochbichler, E.

2012-04-01

Drinking water resources drawn from forested catchment areas are prominent for providing water supply on our planet. Despite the fact that source waters stemming from forested watersheds have generally lower water quality problems than those stemming from agriculturally used watersheds, it has to be guaranteed that the forest stands meet high standards regarding their water protection functionality. For fulfilling these, forest management concepts have to be applied, which are adaptive regarding the specific forest site conditions and also regarding climate change scenarios. In the past century forest management in the alpine area of Austria was mainly based on the cultivation of Norway spruce, by the way neglecting specific forest site conditions, what caused in many cases highly vulnerable mono-species forest stands. The GIS based forest hydrotope model (FoHyM) provides a framework for forest management, which defines the most crucial parameters in a spatial explicit form. FoHyM stratifies the spacious drinking water protection catchments into forest hydrotopes, being operational units for forest management. The primary information layer of FoHyM is the potential natural forest community, which reflects the specific forest site conditions regarding geology, soil types, elevation above sea level, exposition and inclination adequately and hence defines the specific forest hydrotopes. For each forest hydrotope, the adequate tree species composition and forest stand structure for drinking water protection functionality was deduced, based on the plant-sociological information base provided by FoHyM. The most important overall purpose for the related elaboration of adaptive forest management concepts and measures was the improvement of forest stand stability, which can be seen as the crucial parameter for drinking water protection. Only stable forest stands can protect the fragile soil and humus layers and hence prevent erosion process which could endanger the water resources. Forest stands which are formed by a tree species set which conforms to the potential natural forest community are more stable than the currently wide-spread mono-species Norway spruce plantations, especially in times of climate change, where e.g. bark beetle infestations threat spruce with increased intensity. FoHyM also provides the relevant ecological boundary conditions for any estimation of climate change adaptations. The adaptation of the tree species distribution within each forest hydrotope to climate change conditions was fulfilled by the integration of climate change scenarios and the estimation of the eco-physiological characteristics of related tree species. Hence it was possible to define the tree species distribution related to a specific climate change scenario for each forest hydrotope. The silvicultural concepts and measures to accomplish the defined tree species distribution and forest stand structure for each forest hydrotope were defined and elaborated by taking the specific requirements of drinking water protection areas into account, what e.g. comprised the prohibition of the clear cut technique and the application of continuous cover forest management concepts. The overall purpose of these adaptive silvicultural concepts and techniques which were based on the application of FoHyM was the improvement of the water protection functionality of forest stands within drinking water protection zones.

Forest land cover change (1975-2000) in the Greater Border Lakes region

Treesearch

Peter T. Wolter; Brian R. Sturtevant; Brian R. Miranda; Sue M. Lietz; Phillip A. Townsend; John Pastor

2012-01-01

This document and accompanying maps describe land cover classifications and change detection for a 13.8 million ha landscape straddling the border between Minnesota, and Ontario, Canada (greater Border Lakes Region). Land cover classifications focus on discerning Anderson Level II forest and nonforest cover to track spatiotemporal changes in forest cover. Multi-...

Blue oak plant communities of southern San Luis Obispo and northern Santa Barbara Counties, California

Treesearch

Mark I. Borchert; Nancy D. Cunha; Patricia C. Krosse; Marcee L. Lawrence

1993-01-01

An ecological classification system has been developed for the Pacific Southwest Region of the Forest Service. As part of that classification effort, blue oak (Quercus douglasii) woodlands and forests of southern San Luis Obispo and northern Santa Barbara Counties in Los Padres National Forest were classified into I3 plant communities using...

An integrated remote sensing and GIS approach for monitoring areas affected by selective logging: A case study in northern Mato Grosso, Brazilian Amazon

NASA Astrophysics Data System (ADS)

Grecchi, Rosana Cristina; Beuchle, René; Shimabukuro, Yosio Edemir; Aragão, Luiz E. O. C.; Arai, Egidio; Simonetti, Dario; Achard, Frédéric

2017-09-01

Forest cover disturbances due to processes such as logging and forest fires are a widespread issue especially in the tropics, and have heavily affected forest biomass and functioning in the Brazilian Amazon in the past decades. Satellite remote sensing has played a key role for assessing logging activities in this region; however, there are still remaining challenges regarding the quantification and monitoring of these processes affecting forested lands. In this study, we propose a new method for monitoring areas affected by selective logging in one of the hotspots of Mato Grosso state in the Brazilian Amazon, based on a combination of object-based and pixel-based classification approaches applied on remote sensing data. Logging intensity and changes over time are assessed within grid cells of 300 m × 300 m spatial resolution. Our method encompassed three main steps: (1) mapping forest/non-forest areas through an object-based classification approach applied to a temporal series of Landsat images during the period 2000-2015, (2) mapping yearly logging activities from soil fraction images on the same Landsat data series, and (3) integrating information from previous steps within a regular grid-cell of 300 m × 300 m in order to monitor disturbance intensities over this 15-years period. The overall accuracy of the baseline forest/non-forest mask (year 2000) and of the undisturbed vs disturbed forest (for selected years) were 93% and 84% respectively. Our results indicate that annual forest disturbance rates, mainly due to logging activities, were higher than annual deforestation rates during the whole period of study. The deforested areas correspond to circa 25% of the areas affected by forest disturbances. Deforestation rates were highest from 2001 to 2005 and then decreased considerably after 2006. In contrast, the annual forest disturbance rates show high temporal variability with a slow decrease over the 15-year period, resulting in a significant increase of the ratio between disturbed and deforested areas. Although the majority of the areas, which have been affected by selective logging during the period 2000-2014, were not deforested by 2015, more than 70% of the deforested areas in 2015 had been at least once identified as disturbed forest during that period.

An integrated remote sensing and GIS approach for monitoring areas affected by selective logging: A case study in northern Mato Grosso, Brazilian Amazon.

PubMed

Grecchi, Rosana Cristina; Beuchle, René; Shimabukuro, Yosio Edemir; Aragão, Luiz E O C; Arai, Egidio; Simonetti, Dario; Achard, Frédéric

2017-09-01

Forest cover disturbances due to processes such as logging and forest fires are a widespread issue especially in the tropics, and have heavily affected forest biomass and functioning in the Brazilian Amazon in the past decades. Satellite remote sensing has played a key role for assessing logging activities in this region; however, there are still remaining challenges regarding the quantification and monitoring of these processes affecting forested lands. In this study, we propose a new method for monitoring areas affected by selective logging in one of the hotspots of Mato Grosso state in the Brazilian Amazon, based on a combination of object-based and pixel-based classification approaches applied on remote sensing data. Logging intensity and changes over time are assessed within grid cells of 300 m × 300 m spatial resolution. Our method encompassed three main steps: (1) mapping forest/non-forest areas through an object-based classification approach applied to a temporal series of Landsat images during the period 2000-2015, (2) mapping yearly logging activities from soil fraction images on the same Landsat data series, and (3) integrating information from previous steps within a regular grid-cell of 300 m × 300 m in order to monitor disturbance intensities over this 15-years period. The overall accuracy of the baseline forest/non-forest mask (year 2000) and of the undisturbed vs disturbed forest (for selected years) were 93% and 84% respectively. Our results indicate that annual forest disturbance rates, mainly due to logging activities, were higher than annual deforestation rates during the whole period of study. The deforested areas correspond to circa 25% of the areas affected by forest disturbances. Deforestation rates were highest from 2001 to 2005 and then decreased considerably after 2006. In contrast, the annual forest disturbance rates show high temporal variability with a slow decrease over the 15-year period, resulting in a significant increase of the ratio between disturbed and deforested areas. Although the majority of the areas, which have been affected by selective logging during the period 2000-2014, were not deforested by 2015, more than 70% of the deforested areas in 2015 had been at least once identified as disturbed forest during that period.

Development of an ecological classification system for the Wayne National Forest

Treesearch

David M. Hix; Andrea M. Chech

1993-01-01

In 1991, a collaborative research project was initiated to create an ecological classification system for the Wayne National Forest of southeastern Ohio. The work focuses on the ecological land type (ELT) level of ecosystem classification. The most common ELTs are being identified and described using information from intensive field sampling and multivariate data...

Effects of climate, land management, and sulfur deposition on soil base cation supply in national forests of the southern Appalachian mountains

Treesearch

T.C. McDonnell; T.J. Sullivan; B.J. Cosby; W.A. Jackson; K.J. Elliott

2013-01-01

Forest soils having low exchangeable calcium (Ca) and other nutrient base cation (BC) reserves may induce nutrient deficiencies in acid-sensitive plants and impact commercially important tree species. Past and future depletion of soil BC in response to acidic sulfur (S) deposition, forest management, and climate change alter the health and productivity of forest trees...

SVM feature selection based rotation forest ensemble classifiers to improve computer-aided diagnosis of Parkinson disease.

PubMed

Ozcift, Akin

2012-08-01

Parkinson disease (PD) is an age-related deterioration of certain nerve systems, which affects movement, balance, and muscle control of clients. PD is one of the common diseases which affect 1% of people older than 60 years. A new classification scheme based on support vector machine (SVM) selected features to train rotation forest (RF) ensemble classifiers is presented for improving diagnosis of PD. The dataset contains records of voice measurements from 31 people, 23 with PD and each record in the dataset is defined with 22 features. The diagnosis model first makes use of a linear SVM to select ten most relevant features from 22. As a second step of the classification model, six different classifiers are trained with the subset of features. Subsequently, at the third step, the accuracies of classifiers are improved by the utilization of RF ensemble classification strategy. The results of the experiments are evaluated using three metrics; classification accuracy (ACC), Kappa Error (KE) and Area under the Receiver Operating Characteristic (ROC) Curve (AUC). Performance measures of two base classifiers, i.e. KStar and IBk, demonstrated an apparent increase in PD diagnosis accuracy compared to similar studies in literature. After all, application of RF ensemble classification scheme improved PD diagnosis in 5 of 6 classifiers significantly. We, numerically, obtained about 97% accuracy in RF ensemble of IBk (a K-Nearest Neighbor variant) algorithm, which is a quite high performance for Parkinson disease diagnosis.

Modeling impacts of management on carbon sequestration and trace gas emissions in forested wetland ecosystems

Treesearch

Changsheng Li; Jianbo Cui

2004-01-01

A process- based model, Wetland-DNDC, was modified to enhance its capacity to predict the impacts of management practices on carbon sequestration in and trace gas emissions from forested wetland ecosystems. The modifications included parameterization of management practices fe.g., forest harvest, chopping, burning, water management, fertilization, and tree planting),...

Adaptations to climate change: Colville and Okanogan-Wenatchee National Forests

Treesearch

William L. Gaines; David W. Peterson; Cameron A. Thomas; Richy J. Harrod

2012-01-01

Forest managers are seeking practical guidance on how to adapt their current practices and, if necessary, their management goals, in response to climate change. Science-management collaboration was initiated on national forests in eastern Washington where resource managers showed a keen interest in science-based options for adapting to climate change at a 2-day...

Inventory-based landscape-scale simulation of management effectiveness and economic feasibility with BioSum

Treesearch

Jeremy S. Fried; Larry D. Potts; Sara M. Loreno; Glenn A. Christensen; R. Jamie Barbour

2017-01-01

The Forest Inventory and Analysis (FIA)-based BioSum (Bioregional Inventory Originated Simulation Under Management) is a free policy analysis framework and workflow management software solution. It addresses complex management questions concerning forest health and vulnerability for large, multimillion acre, multiowner landscapes using FIA plot data as the initial...

Treatment-Based Classification versus Usual Care for Management of Low Back Pain

DTIC Science & Technology

2017-10-01

AWARD NUMBER: W81XWH-11-1-0657 TITLE: Treatment-Based Classification versus Usual Care for Management of Low Back Pain PRINCIPAL INVESTIGATOR...Treatment-Based Classification versus Usual Care for Management of Low Back Pain 5b. GRANT NUMBER W81XWH-11-1-0657 5c. PROGRAM ELEMENT NUMBER 6...AUTHOR(S) MAJ Daniel Rhon – daniel_rhon@baylor.edu 5d. PROJECT NUMBER 5e. TASK NUMBER 5f. WORK UNIT NUMBER 7. PERFORMING ORGANIZATION NAME(S

Bat activity in selection harvests and intact forest canopy gaps at Indiana state forests

Treesearch

Scott Haulton; Kathryn L. DeCosta

2014-01-01

Forest managers often prescribe silvicultural methods based on how effectively they mimic the natural disturbance agents that have historically shaped the forests they manage. On Indiana state forests, selection systems are used on most harvested acreage and appear to structurally mimic the effects of naturally occurring, gap-forming disturbances affecting individual...

Forest inventory and management-based visual preference models of southern pine stands

Treesearch

Victor A. Rudis; James H. Gramann; Edward J. Ruddell; Joanne M. Westphal

1988-01-01

Statistical models explaining students' ratings of photographs of within stand forest scenes were constructed for 99 forest inventory plots in east Texas pine and oak-pine forest types. Models with parameters that are sensitive to visual preference yet compatible with forest management and timber inventories are presented. The models suggest that the density of...

Comparative genetic responses to climate for the varieties of Pinus ponderosa and Pseudotsuga menziesii: realized climate niches

Treesearch

Gerald E. Rehfeldt; Barry C. Jaquish; Javier Lopez-Upton; Cuauhtemoc Saenz-Romero; J. Bradley St Clair; Laura P. Leites; Dennis G. Joyce

2014-01-01

The Random Forests classification algorithm was used to predict the occurrence of the realized climate niche for two sub-specific varieties of Pinus ponderosa and three varieties of Pseudotsuga menziesii from presence-absence data in forest inventory ground plots. Analyses were based on ca. 271,000 observations for P. ponderosa and ca. 426,000 observations for P....

Mapping trees outside forests using high-resolution aerial imagery: a comparison of pixel- and object based classification approaches

Treesearch

Dacia M. Meneguzzo; Greg C. Liknes; Mark D. Nelson

2013-01-01

Discrete trees and small groups of trees in nonforest settings are considered an essential resource around the world and are collectively referred to as trees outside forests (ToF). ToF provide important functions across the landscape, such as protecting soil and water resources, providing wildlife habitat, and improving farmstead energy efficiency and aesthetics....

Monitoring mangrove forests after aquaculture abandonment using time series of very high spatial resolution satellite images: A case study from the Perancak estuary, Bali, Indonesia.

PubMed

Proisy, Christophe; Viennois, Gaëlle; Sidik, Frida; Andayani, Ariani; Enright, James Anthony; Guitet, Stéphane; Gusmawati, Niken; Lemonnier, Hugues; Muthusankar, Gowrappan; Olagoke, Adewole; Prosperi, Juliana; Rahmania, Rinny; Ricout, Anaïs; Soulard, Benoit; Suhardjono

2018-06-01

Revegetation of abandoned aquaculture regions should be a priority for any integrated coastal zone management (ICZM). This paper examines the potential of a matchless time series of 20 very high spatial resolution (VHSR) optical satellite images acquired for mapping trends in the evolution of mangrove forests from 2001 to 2015 in an estuary fragmented into aquaculture ponds. Evolution of mangrove extent was quantified through robust multitemporal analysis based on supervised image classification. Results indicated that mangroves are expanding inside and outside ponds and over pond dykes. However, the yearly expansion rate of vegetation cover greatly varied between replanted ponds. Ground truthing showed that only Rhizophora species had been planted, whereas natural mangroves consist of Avicennia and Sonneratia species. In addition, the dense Rhizophora plantations present very low regeneration capabilities compared with natural mangroves. Time series of VHSR images provide comprehensive and intuitive level of information for the support of ICZM. Copyright © 2017 Elsevier Ltd. All rights reserved.

Application of a distributed process-based hydrologic model to estimate the effects of forest road density on stormflows in the Southern Appalachians

Treesearch

Salli F. Dymond; W. Michael Aust; Stephen P. Prisley; Mark H. Eisenbies; James M. Vose

2014-01-01

Managed forests have historically been linked to watershed protection and flood mitigation. Research indicates that forests can potentially minimize peak flows during storm events, yet the relationship between forests and flooding is complex. Forest roads, usually found in managed systems, can potentially magnify the effects of forest harvesting on water yields. The...

25 CFR 163.36 - Tribal forestry program financial support.

Code of Federal Regulations, 2010 CFR

2010-04-01

... services to carry out forest land management activities and shall be based on levels of funding assistance... carrying out forest land management activities. Such financial support shall be made available through the... of carrying out forest land management activities may apply and qualify for tribal forestry program...

25 CFR 163.36 - Tribal forestry program financial support.

Code of Federal Regulations, 2011 CFR

2011-04-01

... services to carry out forest land management activities and shall be based on levels of funding assistance... carrying out forest land management activities. Such financial support shall be made available through the... of carrying out forest land management activities may apply and qualify for tribal forestry program...

Potential of forest management to reduce French carbon emissions - regional modelling of the French forest carbon balance from the forest to the wood.

NASA Astrophysics Data System (ADS)

Valade, A.; Luyssaert, S.; Bellassen, V.; Vallet, P.

2015-12-01

In France the low levels of forest harvest (40 Mm3 per year over a volume increment of 89Mm3) is frequently cited to push for a more intensive management of the forest that would help reducing CO2 emissions. This reasoning overlooks the medium-to-long-term effects on the carbon uptake at the national scale that result from changes in the forest's structure and delayed emissions from products decay and bioenergy burning, both determinant for the overall C fluxes between the biosphere and the atmosphere. To address the impacts of an increase in harvest removal on biosphere-atmosphere carbon fluxes at national scale, we build a consistent regional modeling framework to integrate the forest-carbon system from photosynthesis to wood uses. We aim at bridging the gap between regional ecosystem modeling and land managers' considerations, to assess the synergistic and antagonistic effects of management strategies over C-based forest services: C-sequestration, energy and material provision, fossil fuel substitution. For this, we built on inventory data to develop a spatial forest growth simulator and design a novel method for diagnosing the current level of management based on stand characteristics (density, quadratic mean diameter or exploitability). The growth and harvest simulated are then processed with a life cycle analysis to account for wood transformation and uses. Three scenarii describe increases in biomass removals either driven by energy production target (set based on national prospective with a lock on minimum harvest diameters) or by changes in management practices (shorter or longer rotations, management of currently unmanaged forests) to be compared with business as usual simulations. Our management levels' diagnostics quantifies undermanagement at national scale and evidences the large weight of ownership-based undermanagement with an average of 26% of the national forest (between 10% and 40% per species) and thus represents a huge potential wood resource. We examine the effects of a mobilization of this resource versus an intensification of the current harvest on the age structure, the productivity and the stocking volume of the French forest and derive the related impacts on C emissions and C-related services provided by forests.

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

NASA Astrophysics Data System (ADS)

Nitze, Ingmar; Barrett, Brian; Cawkwell, Fiona

2015-02-01

The analysis and classification of land cover is one of the principal applications in terrestrial remote sensing. Due to the seasonal variability of different vegetation types and land surface characteristics, the ability to discriminate land cover types changes over time. Multi-temporal classification can help to improve the classification accuracies, but different constraints, such as financial restrictions or atmospheric conditions, may impede their application. The optimisation of image acquisition timing and frequencies can help to increase the effectiveness of the classification process. For this purpose, the Feature Importance (FI) measure of the state-of-the art machine learning method Random Forest was used to determine the optimal image acquisition periods for a general (Grassland, Forest, Water, Settlement, Peatland) and Grassland specific (Improved Grassland, Semi-Improved Grassland) land cover classification in central Ireland based on a 9-year time-series of MODIS Terra 16 day composite data (MOD13Q1). Feature Importances for each acquisition period of the Enhanced Vegetation Index (EVI) and Normalised Difference Vegetation Index (NDVI) were calculated for both classification scenarios. In the general land cover classification, the months December and January showed the highest, and July and August the lowest separability for both VIs over the entire nine-year period. This temporal separability was reflected in the classification accuracies, where the optimal choice of image dates outperformed the worst image date by 13% using NDVI and 5% using EVI on a mono-temporal analysis. With the addition of the next best image periods to the data input the classification accuracies converged quickly to their limit at around 8-10 images. The binary classification schemes, using two classes only, showed a stronger seasonal dependency with a higher intra-annual, but lower inter-annual variation. Nonetheless anomalous weather conditions, such as the cold winter of 2009/2010 can alter the temporal separability pattern significantly. Due to the extensive use of the NDVI for land cover discrimination, the findings of this study should be transferrable to data from other optical sensors with a higher spatial resolution. However, the high impact of outliers from the general climatic pattern highlights the limitation of spatial transferability to locations with different climatic and land cover conditions. The use of high-temporal, moderate resolution data such as MODIS in conjunction with machine-learning techniques proved to be a good base for the prediction of image acquisition timing for optimal land cover classification results.

Atmospheric circulation classification comparison based on wildfires in Portugal

NASA Astrophysics Data System (ADS)

Pereira, M. G.; Trigo, R. M.

2009-04-01

Atmospheric circulation classifications are not a simple description of atmospheric states but a tool to understand and interpret the atmospheric processes and to model the relation between atmospheric circulation and surface climate and other related variables (Radan Huth et al., 2008). Classifications were initially developed with weather forecasting purposes, however with the progress in computer processing capability, new and more robust objective methods were developed and applied to large datasets prompting atmospheric circulation classification methods to one of the most important fields in synoptic and statistical climatology. Classification studies have been extensively used in climate change studies (e.g. reconstructed past climates, recent observed changes and future climates), in bioclimatological research (e.g. relating human mortality to climatic factors) and in a wide variety of synoptic climatological applications (e.g. comparison between datasets, air pollution, snow avalanches, wine quality, fish captures and forest fires). Likewise, atmospheric circulation classifications are important for the study of the role of weather in wildfire occurrence in Portugal because the daily synoptic variability is the most important driver of local weather conditions (Pereira et al., 2005). In particular, the objective classification scheme developed by Trigo and DaCamara (2000) to classify the atmospheric circulation affecting Portugal have proved to be quite useful in discriminating the occurrence and development of wildfires as well as the distribution over Portugal of surface climatic variables with impact in wildfire activity such as maximum and minimum temperature and precipitation. This work aims to present: (i) an overview the existing circulation classification for the Iberian Peninsula, and (ii) the results of a comparison study between these atmospheric circulation classifications based on its relation with wildfires and relevant meteorological variables. To achieve these objectives we consider the main classifications for Iberia developed within the framework of COST action 733 (Radan Huth et al., 2008). This European project aims to provide a wide range of atmospheric circulation classifications for Europe and sub-regions (http://www.cost733.org/) with an ambitious objective of assessing, comparing and classifying all relevant weather situations in Europe. Pereira et al. (2005) "Synoptic patterns associated with large summer forest fires in Portugal". Agricultural and Forest Meteorology,129, 11-25. Radan Huth et al. (2008) "Classifications of Atmospheric circulation patterns. Recent advances and applications". Trends and Directions in Climate Research: Ann. N.Y. Acad. Sci. 1146: 105-152. doi: 10.1196/annals.1446.019. Trigo R.M., DaCamara C. (2000) "Circulation Weather Types and their impact on the precipitation regime in Portugal". Int J of Climatology, 20, 1559-1581.

Value of the Morgan-Monroe-Yellowwood State Forest Complex

Treesearch

William L. Hoover

2013-01-01

As publicly owned forest land, the Morgan-Monroe and Yellowwood State Forests (Indiana), referred to herein as the Morgan-Monroe Yellowwood Complex (MMYC), have many stakeholders with differing management expectations. The Hardwood Ecosystem Experiment (HEE) within the MMYC will significantly increase the science-based information available for forest management...

Examining the Role of Voluntary Associations in Environmental Management: The Case of the Sam Houston National Forest

NASA Astrophysics Data System (ADS)

Lu, Jiaying; Schuett, Michael A.

2012-02-01

The purpose of this study was to gain a better understanding of voluntary associations involved in forest management. The specific areas examined in this study include organizational attributes, membership profile, attitudes toward forest-management priorities, and concerns about forest-management issues. To achieve this purpose, data were collected using a case study approach with mixed-methods (document reviews, personal interviews, and a Web survey) at a national forest in Texas, USA. Overall, the voluntary associations in this study can be described as place-based, small to moderate in scale, activity-oriented, and active groups that are adaptive to sociopolitical and environmental changes. General group members placed high importance on aesthetic, ecological, and recreation management of the national forest. In addition, this study showed five key forest management issues: (1) limited recreation access; (2) financial challenges for forest management; (3) conflict among recreation user groups; (4) inadequate communication by the United States Forest Service to the general public, and (5) sustainability of the forest. Theoretical and managerial implications of the results are discussed.

Adopting public values and climate change adaptation strategies in urban forest management: A review and analysis of the relevant literature.

PubMed

Ordóñez Barona, Camilo

2015-12-01

Urban trees are a dominant natural element in cities; they provide important ecosystem services to urban citizens and help urban areas adapt to climate change. Many rationales have been proposed to provide a purpose for urban forest management, some of which have been ineffective in addressing important ecological and social management themes. Among these rationales we find a values-based perspective, which sees management as a process where the desires of urban dwellers are met. Another perspective is climate change adaptation, which sees management as a process where urban forest vulnerability to climate change is reduced and resilience enhanced. Both these rationales have the advantage of complementing, enhancing, and broadening urban forest management objectives. A critical analysis of the literature on public values related to urban forests and climate change adaptation in the context of urban forests is undertaken to discuss what it means to adopt these two issues in urban forest management. The analysis suggests that by seeing urban forest management as a process by which public values are satisfied and urban-forest vulnerabilities to climate change are reduced, we can place issues such as naturalization, adaptive management, and engaging people in management at the centre of urban forest management. Focusing urban forest management on these issues may help ensure the success of programs focused on planting more trees and increasing citizen participation in urban forest management. Copyright © 2015 Elsevier Ltd. All rights reserved.

Black bear habitat use in relation to food availability in the Interior Highlands of Arkansas

USGS Publications Warehouse

Clark, Joseph D.; Clapp, Daniel L.; Smith, Kimberly G.; Ederington, Belinda

1994-01-01

A black bear (Ursus americanus) food value index (FVI) was developed and calculated for forest cover type classifications on Ozark Mountain (White Rock) and Ouachita Mountain (Dry Creek) study areas in western Arkansas. FVIs are estimates of bear food production capabilities of the major forest cover types and were calculated using percent cover, mean fruit production scorings, and the dietary percentage of each major plant food species as variables. Goodness-of-fit analyses were used to determine use of forest cover types by 23 radio-collared female bears. Habitat selection by forest cover type was not detected on White Rock but was detected on Dry Creek. Use of habitats on Dry Creek appeared to be related to food production with the exception of regeneration areas, which were used less than expected but had a high FVI ranking. In general, pine cover types had low FVI rankings and were used less than expected by bears. Forest management implications are discussed. 

Deep canyon and subalpine riparian and wetland plant associations of the Malheur, Umatilla, and Wallowa-Whitman National Forests.

Treesearch

Aaron F. Wells

2006-01-01

This guide presents a classification of the deep canyon and subalpine riparian and wetland vegetation types of the Malheur, Umatilla, and Wallowa-Whitman National Forests. A primary goal of the deep canyon and subalpine riparian and wetland classification was a seamless linkage with the midmontane northeastern Oregon riparian and wetland classification provided by...

[Land cover classification of Four Lakes Region in Hubei Province based on MODIS and ENVISAT data].

PubMed

Xue, Lian; Jin, Wei-Bin; Xiong, Qin-Xue; Liu, Zhang-Yong

2010-03-01

Based on the differences of back scattering coefficient in ENVISAT ASAR data, a classification was made on the towns, waters, and vegetation-covered areas in the Four Lakes Region of Hubei Province. According to the local cropping systems and phenological characteristics in the region, and by using the discrepancies of the MODIS-NDVI index from late April to early May, the vegetation-covered areas were classified into croplands and non-croplands. The classification results based on the above-mentioned procedure was verified by the classification results based on the ETM data with high spatial resolution. Based on the DEM data, the non-croplands were categorized into forest land and bottomland; and based on the discrepancies of mean NDVI index per month, the crops were identified as mid rice, late rice, and cotton, and the croplands were identified as paddy field and upland field. The land cover classification based on the MODIS data with low spatial resolution was basically consistent with that based on the ETM data with high spatial resolution, and the total error rate was about 13.15% when the classification results based on ETM data were taken as the standard. The utilization of the above-mentioned procedures for large scale land cover classification and mapping could make the fast tracking of regional land cover classification.

Estimation of Trees Outside Forests using IRS High Resolution data by Object Based Image Analysis

NASA Astrophysics Data System (ADS)

Pujar, G. S.; Reddy, P. M.; Reddy, C. S.; Jha, C. S.; Dadhwal, V. K.

2014-11-01

Assessment of Trees outside forests (TOF) is widely being recognized as a pivotal theme, in sustainable natural resource management, due to their role in offering variety of goods, such as timber, fruits and fodder as well as services like water, carbon, biodiversity. Forest Conservation efforts involving reduction of deforestation and degradation may have to increasingly rely on alternatives provided by TOF in catering to economic demands in forest edges. Spatial information systems involving imaging, analysis and monitoring to achieve objectives under protocols like REDD+, require incorporation of information content from areas under forest as well as trees outside forests, to aid holistic decisions. In this perspective, automation in retrieving information on area under trees, growing outside forests, using high resolution imaging is essential so that measuring and verification of extant carbon pools, are strengthened. Retrieval of this tree cover is demonstrated herewith, using object based image analysis in a forest edge of dry deciduous forests of Eastern Ghats, in Khammam district of Telangana state of India. IRS high resolution panchromatic 2.5 m data (Cartosat-1 Orthorectified) used in tandem with 5.8 m multispectral LISS IV data, discerns tree crowns and clusters at a detailed scale and hence semi-automated approach is attempted to classify TOF from a pair of image from relatively crop and cloud free season. Object based image analysis(OBIA) approach as implemented in commercial suite of e-Cognition (Ver 8.9) consists of segmentation at user defined scale followed by application of wide range of spectral, textural and object geometry based parameters for classification. Software offers innovative blend of raster and vector features that can be juxtaposed flexibly, across scales horizontally or vertically. Segmentation was carried out at multiple scales to discern first the major land covers, such as forest, water, agriculture followed by that at a finer scale, within cultivated landscape. Latter scale aimed to segregate TOF in configurations such as individual or scattered crowns, linear formations and patch TOF. As per the adopted norms in India for defining tree cover, units up to 1 ha area were considered as candidate TOF. Classification of fine scale (at 10) segments was accomplished using size, shape and texture. A customised parameter involving ratio of area of segment to its main skeleton length discerned linear formations consistently. Texture of Cartosat-1 2.5 m data was also used segregate tree cover from smoother crop patches in patch TOF category. In view of the specificity of the landscape character, continuum of cultivated area (b) and pockets of cultivation within forest (c) as well as the entire study area (a) were considered as three envelopes for evaluating the accuracy of the method. Accuracies not less than 75.1 per cent were reported in all the envelopes with a kappa accuracy of not less than 0.58. Overall accuracy of entire study area was 75.9 per cent with Kappa of 0.59 followed by 75.1 per cent ( Kappa: 0.58 ) of agricultural landscape (b). In pockets of cultivation context(c) accuracy was higher at 79.2 per cent ( Kappa: 0.64 ) possibly due to smaller population. Assessment showed that 1,791 ha of 24,140 ha studied (7.42 %) was under tree cover as per the definitions adopted. Strength of accuracy demonstrated obviously points to the potential of IRS high resolution data combination in setting up procedures to monitor the TOF in Indian context using OBIA approach so as to cater to the evolving demands of resource assessment and monitoring.

Three Global Land Cover and Use Stage considering Environmental Condition and Economic Development

NASA Astrophysics Data System (ADS)

Lee, W. K.; Song, C.; Moon, J.; Ryu, D.

2016-12-01

The Mid-Latitude zone can be broadly defined as part of the hemisphere between around 30° - 60° latitude. This zone is a home to over more than 50% of the world population and encompasses about 36 countries throughout the principal regions which host most of the global problems related to development and poverty. Mid-Latitude region and its ecotone demands in-depth analysis, however, latitudinal approach has not been widely recognized, considering that many of natural resources and environment indicators, as well as social and economic indicators are based on administrative basis or by country and regional boundaries. This study sets the land cover change and use stage based on environmental condition and economic development. Because various land cover and use among the regions, form vegetated parts of East Asia and Mediterranean to deserted parts of Central Asia, the forest area was varied between countries. In addition, some nations such as North Korea, Afghanistan, Pakistan showed decreasing trends in forest area whereas some nations showed increasing trends in forest area. The economic capacity for environmental activities and policies for restoration were different among countries. By adopting the standard from IMF or World Bank, developing and developed counties were classified. Based on the classification, this study suggested the land cover and use stages as degradation, restoration, and sustainability. As the degradation stage, the nations which had decreasing forest area with less environmental restoration capacity based on economic size were selected. As the restoration stage, the nation which had increasing forest area or restoration capacity were selected. In the case of the sustainability, the nation which had enough restoration capacity with increasing forest area or small ratio in forest area decreasing were selected. In reviewing some of the past and current major environmental challenges that regions of Mid-Latitudes are facing, grouping by land cover and use stage provides environmental rationale of research, which enables better understanding on the function and interaction of ecosystem from various perspectives with preparing global climate change and sustainable management of natural resources. Keywords: Global land stage, Degradation, Restoration, Sustainability, Mid-Latitude

Toward extending terrestrial laser scanning applications in forestry: a case study of broad- and needle-leaf tree classification

NASA Astrophysics Data System (ADS)

Lin, Yi; Jiang, Miao

2017-01-01

Tree species information is essential for forest research and management purposes, which in turn require approaches for accurate and precise classification of tree species. One such remote sensing technology, terrestrial laser scanning (TLS), has proved to be capable of characterizing detailed tree structures, such as tree stem geometry. Can TLS further differentiate between broad- and needle-leaves? If the answer is positive, TLS data can be used for classification of taxonomic tree groups by directly examining their differences in leaf morphology. An analysis was proposed to assess TLS-represented broad- and needle-leaf structures, followed by a Bayes classifier to perform the classification. Tests indicated that the proposed method can basically implement the task, with an overall accuracy of 77.78%. This study indicates a way of implementing the classification of the two major broad- and needle-leaf taxonomies measured by TLS in accordance to their literal definitions, and manifests the potential of extending TLS applications in forestry.

Investigation of forestry resources and other remote sensing data. 1: LANDSAT. 2: Remote sensing of volcanic emissions

NASA Technical Reports Server (NTRS)

Birnie, R. W.; Stoiber, R. E. (Principal Investigator)

1983-01-01

Computer classification of LANDSAT data was used for forest type mapping in New England. The ability to classify areas of hardwood, softwood, and mixed tree types was assessed along with determining clearcut regions and gypsy moth defoliation. Applications of the information to forest management and locating potential deer yards were investigated. The principal activities concerned with remote sensing of volcanic emissions centered around the development of remote sensors for SO2 and HCl gas, and their use at appropriate volcanic sites. Two major areas were investigated (Masaya, Nicaragua, and St. Helens, Washington) along with several minor ones.

Regulating the sustainability of forest management in the Americas: Cross-country comparisons of forest legislation

Treesearch

Kathleen McGinley; Raquel Alvarado; Frederick Cubbage; Diana Diaz; Pablo J. Donoso; Laercio Antonio Jacovine Goncalves; Fabiano Luiz de Silva; Charles MacIntyre; Elizabeth Monges Zalazar

2012-01-01

Based on theoretical underpinnings and an empirical review of forest laws and regulations of selected countries throughout the Americas, we examine key components of natural forest management and how they are addressed in the legal frameworks of Argentina, Brazil, Chile, Costa Rica, Guatemala, Nicaragua, Paraguay, Uruguay, and the U.S. We consider forest policy...

Use of LIDAR for forest inventory and forest management application

Treesearch

Birgit Peterson; Ralph Dubayah; Peter Hyde; Michelle Hofton; J. Bryan Blair; JoAnn Fites-Kaufman

2007-01-01

A significant impediment to forest managers has been the difficulty in obtaining large-area forest structure and fuel characteristics at useful resolutions and accuracies. This paper demonstrates how LIDAR data were used to predict canopy bulk density (CBD) and canopy base height (CBH) for an area in the Sierra National Forest. The LIDAR data were used to generate maps...

Coronado National Forest Draft Land and Resource Management Plan: Cochise, Graham, Pima, Pinal, and Santa Cruz Counties, Arizona, and Hidalgo County, New Mexico

Treesearch

Terry Austin; Yolynda Begay; Sharon Biedenbender; Rachael Biggs; Erin Boyle; Eli Curiel; Sarah Davis; Sara Dechter; Tami Emmett; Mary Farrell; Richard Gerhart; William Gillespie; Polly Haessig; Ed Holloway; Melissa Jenkins; Larry Jones; Debby Kriegel; Robert Lefevre; Mark Stamer; Mindi Lehew; Ann Lynch; George McKay; Linda Peery; Albert Peralta; Jennifer Ruyle; Jeremy Sautter; Kenna Schoenle; Salek Shafiqullah; Christopher Stetson; Mindi Sue Vogel; Laura White; Craig Wilcox; Judy York

2013-01-01

The Coronado National Forest is an administrative component of the National Forest System. It administers 1,783,639 acres of National Forest System lands. National forests across the United States were established to provide natural resource-based goods and services to American citizens, and to protect timber and watershed resources. Management of national forests is...

Development of a statewide Landsat digital data base for forest insect damage assessment

NASA Technical Reports Server (NTRS)

Williams, D. L.; Dottavio, C. L.; Nelson, R. F.

1983-01-01

A Joint Research Project (JRP) invlving NASA/Goddard Space Flight Center and the Pennsylvania Bureau of Forestry/Division of Forest Pest Management demonstrates the utility of Landsat data for assessing forest insect damage. A major effort within the project has been the creation of map-registered, statewide Landsat digital data base for Pennsylvania. The data base, developed and stored on computers at the Pennsylvania State University Computation Center, contains Landsat imagery, a Landsat-derived forest resource map, and digitized data layers depicting Forest Pest Management District boundaries and county boundaries. A data management front-end system was also developed to provide an interface between the various layers of information within the data base and image analysis software. This front-end system insures than an automated assessment of defoliation damage can be conducted and summarized by geographic area or jurisdiction of interest.

Managing an established tree invader: developing control methods for Chinese tallow (Triadica sebifera) in maritime forests

Treesearch

Lauren S. Pile; G. Geoff Wang; Thomas A. Waldrop; Joan L. Walker; William C. Bridges; Patricia A. Layton

2017-01-01

Biological invasions by woody species in forested ecosystems can have significant impacts on forest management and conservation. We designed and tested several management options based on the physiology of Chinese tallow (Triadica sebifera [L.] Small). Specifically, we tested four treatments, including mastication, foliar herbicide, and fire (MH...

Alberta Biodiversity Monitoring Program - monitoring effectiveness of sustainable forest management planning

Treesearch

J. John Stadt; Jim Schieck; Harry Stelfox

2006-01-01

The Alberta Biodiversity Monitoring Program is a rigorous science-based initiative that is being developed to monitor and report on biodiversity status and trends throughout the province of Alberta, Canada. Forest management plans in Alberta are required to monitor and report on the achievement of stated sustainable forest management objectives; however, the...

Public acceptance of disturbance-based forest management: factors influencing support

Treesearch

Christine S. Olsen; Angela L. Mallon; Bruce A. Shindler

2012-01-01

Growing emphasis on ecosystem and landscape-level forest management across North America has spurred an examination of alternative management strategies which focus on emulating dynamic natural disturbance processes, particularly those associated with forest fire regimes. This topic is the cornerstone of research in the Blue River Landscape Study (BRLS) on the...

Spectroscopic diagnosis of laryngeal carcinoma using near-infrared Raman spectroscopy and random recursive partitioning ensemble techniques.

PubMed

Teh, Seng Khoon; Zheng, Wei; Lau, David P; Huang, Zhiwei

2009-06-01

In this work, we evaluated the diagnostic ability of near-infrared (NIR) Raman spectroscopy associated with the ensemble recursive partitioning algorithm based on random forests for identifying cancer from normal tissue in the larynx. A rapid-acquisition NIR Raman system was utilized for tissue Raman measurements at 785 nm excitation, and 50 human laryngeal tissue specimens (20 normal; 30 malignant tumors) were used for NIR Raman studies. The random forests method was introduced to develop effective diagnostic algorithms for classification of Raman spectra of different laryngeal tissues. High-quality Raman spectra in the range of 800-1800 cm(-1) can be acquired from laryngeal tissue within 5 seconds. Raman spectra differed significantly between normal and malignant laryngeal tissues. Classification results obtained from the random forests algorithm on tissue Raman spectra yielded a diagnostic sensitivity of 88.0% and specificity of 91.4% for laryngeal malignancy identification. The random forests technique also provided variables importance that facilitates correlation of significant Raman spectral features with cancer transformation. This study shows that NIR Raman spectroscopy in conjunction with random forests algorithm has a great potential for the rapid diagnosis and detection of malignant tumors in the larynx.

Use and applicability of the vegetation component of the national site classification system. [Sumter National Forest, South Carolina

NASA Technical Reports Server (NTRS)

Clark, C. A. (Principal Investigator)

1981-01-01

Existing vegetation on a site in Sumter National Forest, South Carolina was classified using high altitude aerial optical bar color infrared photography in an effort to determine if the National Site Classification (NSC) system could be used in the heterogeneously forested southeastern United States where it had not previously been used. Results show that the revised UNESCO international classification and mapping of vegetation system, as incorporated into the NSCS, is general enough at the higher levels and specific enough at the lower levels to adequately accommodate densely forested, heterogeneous areas as well as the larger, more homogeneous regions of the Pacific Northwest. The major problem is of existing vegetation versus natural vegetation.

A GIS-based protocol for the simulation and evaluation of realistic 3-D thinning scenarios in recreational forest management.

PubMed

Lin, Chinsu; Thomson, Gavin; Hung, Shih-Hsiang; Lin, Yu-Dung

2012-12-30

This study introduces a GIS-based protocol for the simulation and evaluation of thinning treatments in recreational forest management. The protocol was implemented in a research study based on an area of recreational forest in Alishan National Scenic Area, Taiwan. Ground survey data were mapped to a GIS database, to create a precise, yet flexible, GIS-based digital forest. The digital forest model was used to generate 18 different thinning scenario images and one image of the existing unthinned forest. A questionnaire was completed by 456 participants while simultaneously viewing the scenario images. The questionnaire was used to determine the scenic beauty preferences of the respondents. Statistical analysis of the data revealed that the respondents preferred low density, upper-storey thinning treatments and a dispersed retention pattern of the remaining trees. High density upper-storey treatments evoked a strongly negative reaction in the observers. The experiment demonstrated that the proposed protocol is suitable for selecting an appropriate thinning strategy for recreational forest and that the protocol has practical value in recreational forest management. Copyright © 2012 Elsevier Ltd. All rights reserved.

Vegetation survey in Amazonia using LANDSAT data. [Brazil

NASA Technical Reports Server (NTRS)

Parada, N. D. J. (Principal Investigator); Shimabukuro, Y. E.; Dossantos, J. R.; Deaquino, L. C. S.

1982-01-01

Automatic Image-100 analysis of LANDSAT data was performed using the MAXVER classification algorithm. In the pilot area, four vegetation units were mapped automatically in addition to the areas occupied for agricultural activities. The Image-100 classified results together with a soil map and information from RADAR images, permitted the establishment of the final legend with six classes: semi-deciduous tropical forest; low land evergreen tropical forest; secondary vegetation; tropical forest of humid areas, predominant pastureland and flood plains. Two water types were identified based on their sediments indicating different geological and geomorphological aspects.

An ecological aesthetic for forest landscape management

Treesearch

Paul H. Gobster

1999-01-01

Although aesthetics and ecological sustainability are two highly regared values of forest landscapes, practices developed to manage forests for these values can sometimes conflict with one another. In this paper I argue that such conflicts are rooted in our conception of forest aesthetics as scenery, and propose that a normative, "ecological aesthetic" based...

Managing ecosystems for forest health: An approach and the effects on uses and values

Treesearch

Chadwick D. Oliver; Dennis E. Ferguson; Alan E. Harvey; Herbert S. Malany; John M. Mandzak; Robert W. Mutch

1994-01-01

Forest health is most appropriately based on the scientific paradigm of dynamic, constantly changing forest ecosystems. Many forests in the Inland West now support high levels of insect infestations, disease epidemics, fire susceptibilities, and imbalances in stand structures and habitats because of natural processes and past management practices. Impending,...

Forest Interpreter's Primer on Fire Management.

ERIC Educational Resources Information Center

Zelker, Thomas M.

Specifically prepared for the use of Forest Service field-based interpreters of the management, protection, and use of forest and range resources and the associated human, cultural, and natural history found on these lands, this book is the second in a series of six primers on the multiple use of forest and range resources. Following an…

Base-age invariance and inventory projections

Treesearch

C. J. Cieszewski; R. L. Bailey; B. E. Borders; G. H. Brister; B. D. Shiver

2000-01-01

One of the most important functions of forest inventory is to facilitate management decisions towards forest sustainability based on inventory projections into the future. Therefore, most forest inventories are used for predicting future states of the forests, in modern forestry the most common methods used in inventory projections are based on implicit functions...

Phase I Forest Area Estimation Using Landsat TM and Iterative Guided Spectral Class Rejection: Assessment of Possible Training Data Protocols

Treesearch

John A. Scrivani; Randolph H. Wynne; Christine E. Blinn; Rebecca F. Musy

2001-01-01

Two methods of training data collection for automated image classification were tested in Virginia as part of a larger effort to develop an objective, repeatable, and low-cost method to provide forest area classification from satellite imagery. The derived forest area estimates were compared to estimates derived from a traditional photo-interpreted, double sample. One...

Uncertainties and Solutions Related to Use of WRB (2007) in the Boreo-nemoral zone, Case of Latvia

NASA Astrophysics Data System (ADS)

Kasparinskis, Raimonds; Nikodemus, Olgerts; Rolavs, Nauris

2014-05-01

Relatively high diversity of soils groups according to the WRB (2007) classification is observed in forest ecosystems in the boreo-nemoral zone in Latvia. This is due to the geological genesis of area and environmental conditions (Kasparinskis, Nikodemus, 2012), as well as historical land use and management (Nikodemus et al., 2013). Due to the relatively young soils, Albic, Spodic and Cambic horizons are relatively weakly expressed in many cases. Relatively well developed Albic horizons occur in sandy forest soils, but unusually well expressed Spodic features are observed. In some cases there is a Cambic horizon, however location of Cambisols in the WRB (2007) soil classification sequence does not provide an opportunity to classify these soils as Cambisols, but they are classified as Arenosols. This sequence does not reflect the logical sheme of soil development, and therefore raises the question about location of Podzols, Arenosols and Cambisols in the sequence of WRB (2007) soil classification. Soils with two parent materials (abrupt textural change) are relatively common in Latvia, where conceptually on the small scale mapping results in classification as the soil group Planosols, but in many cases there is occurrence of Fluvic materials, as parent material in the upper part of the soil profile is formed by Baltic Ice lake sandy sediments - this leads to question about the location of Fluvisols and Planosols in the sequence of the WRB (2007) soil classification. Soil research has found cases, where a relatively well developed Spodic horizon was established as the result of ground water table depth in areas of abrupt textural change. In this case the profile corresponds to the soil group of Podzols, however in some cases - Gleysols not Planosols due to a high ground water table. Therefore there is a need for discussion also about the location of Podzols and Planosols in the sequence of the WRB (2007) soil classification. The above mentioned questions raise problems related to unambiguous determination of soil groups. Soil classification must be very precise by reflecting relationships of soil forming processes. In the development of international soil classification it is advisable to pay more attention on ecological processes. This study was supported by the European Social Fund No. 2013/0020/1DP/1.1.1.2.0/13/APIA/VIAA/066. References: IUSS Working Group, 2007. World Reference Base for Soil Resources 2006, first update 2007. World Soil Resources Reports 103. FAO, Rome. 103-116. Kasparinskis R., Nikodemus O. 2012. Influence of environmental factors on the spatial distribution and diversity of forest soil in Latvia. Estonian Journal of Earth Sciences. 61(1): 48-64. Nikodemus O., Kasparinskis R., Kukuls I. 2013. Influence of Afforestation on Soil Genesis, Morphology and Properties in Glacial Till Deposits. Archives of Agronomy and Soil Science. 59(3): 449-465.

Comparison of Hyperspectral and Multispectral Satellites for Forest Alliance Classification in the San Francisco Bay Area

NASA Astrophysics Data System (ADS)

Clark, M. L.

2016-12-01

The goal of this study was to assess multi-temporal, Hyperspectral Infrared Imager (HyspIRI) satellite imagery for improved forest class mapping relative to multispectral satellites. The study area was the western San Francisco Bay Area, California and forest alliances (e.g., forest communities defined by dominant or co-dominant trees) were defined using the U.S. National Vegetation Classification System. Simulated 30-m HyspIRI, Landsat 8 and Sentinel-2 imagery were processed from image data acquired by NASA's AVIRIS airborne sensor in year 2015, with summer and multi-temporal (spring, summer, fall) data analyzed separately. HyspIRI reflectance was used to generate a suite of hyperspectral metrics that targeted key spectral features related to chemical and structural properties. The Random Forests classifier was applied to the simulated images and overall accuracies (OA) were compared to those from real Landsat 8 images. For each image group, broad land cover (e.g., Needle-leaf Trees, Broad-leaf Trees, Annual agriculture, Herbaceous, Built-up) was classified first, followed by a finer-detail forest alliance classification for pixels mapped as closed-canopy forest. There were 5 needle-leaf tree alliances and 16 broad-leaf tree alliances, including 7 Quercus (oak) alliance types. No forest alliance classification exceeded 50% OA, indicating that there was broad spectral similarity among alliances, most of which were not spectrally pure but rather a mix of tree species. In general, needle-leaf (Pine, Redwood, Douglas Fir) alliances had better class accuracies than broad-leaf alliances (Oaks, Madrone, Bay Laurel, Buckeye, etc). Multi-temporal data classifications all had 5-6% greater OA than with comparable summer data. For simulated data, HyspIRI metrics had 4-5% greater OA than Landsat 8 and Sentinel-2 multispectral imagery and 3-4% greater OA than HyspIRI reflectance. Finally, HyspIRI metrics had 8% greater OA than real Landsat 8 imagery. In conclusion, forest alliance classification was found to be a difficult remote sensing application with moderate resolution (30 m) satellite imagery; however, of the data tested, HyspIRI spectral metrics had the best performance relative to multispectral satellites.

Land cover mapping of North and Central America—Global Land Cover 2000

USGS Publications Warehouse

Latifovic, Rasim; Zhu, Zhi-Liang

2004-01-01

The Land Cover Map of North and Central America for the year 2000 (GLC 2000-NCA), prepared by NRCan/CCRS and USGS/EROS Data Centre (EDC) as a regional component of the Global Land Cover 2000 project, is the subject of this paper. A new mapping approach for transforming satellite observations acquired by the SPOT4/VGTETATION (VGT) sensor into land cover information is outlined. The procedure includes: (1) conversion of daily data into 10-day composite; (2) post-seasonal correction and refinement of apparent surface reflectance in 10-day composite images; and (3) extraction of land cover information from the composite images. The pre-processing and mosaicking techniques developed and used in this study proved to be very effective in removing cloud contamination, BRDF effects, and noise in Short Wave Infra-Red (SWIR). The GLC 2000-NCA land cover map is provided as a regional product with 28 land cover classes based on modified Federal Geographic Data Committee/Vegetation Classification Standard (FGDC NVCS) classification system, and as part of a global product with 22 land cover classes based on Land Cover Classification System (LCCS) of the Food and Agriculture Organisation. The map was compared on both areal and per-pixel bases over North and Central America to the International Geosphere–Biosphere Programme (IGBP) global land cover classification, the University of Maryland global land cover classification (UMd) and the Moderate Resolution Imaging Spectroradiometer (MODIS) Global land cover classification produced by Boston University (BU). There was good agreement (79%) on the spatial distribution and areal extent of forest between GLC 2000-NCA and the other maps, however, GLC 2000-NCA provides additional information on the spatial distribution of forest types. The GLC 2000-NCA map was produced at the continental level incorporating specific needs of the region.

Updating beliefs and combining evidence in adaptive forest management under climate change: a case study of Norway spruce (Picea abies L. Karst) in the Black Forest, Germany.

PubMed

Yousefpour, Rasoul; Temperli, Christian; Bugmann, Harald; Elkin, Che; Hanewinkel, Marc; Meilby, Henrik; Jacobsen, Jette Bredahl; Thorsen, Bo Jellesmark

2013-06-15

We study climate uncertainty and how managers' beliefs about climate change develop and influence their decisions. We develop an approach for updating knowledge and beliefs based on the observation of forest and climate variables and illustrate its application for the adaptive management of an even-aged Norway spruce (Picea abies L. Karst) forest in the Black Forest, Germany. We simulated forest development under a range of climate change scenarios and forest management alternatives. Our analysis used Bayesian updating and Dempster's rule of combination to simulate how observations of climate and forest variables may influence a decision maker's beliefs about climate development and thereby management decisions. While forest managers may be inclined to rely on observed forest variables to infer climate change and impacts, we found that observation of climate state, e.g. temperature or precipitation is superior for updating beliefs and supporting decision-making. However, with little conflict among information sources, the strongest evidence would be offered by a combination of at least two informative variables, e.g., temperature and precipitation. The success of adaptive forest management depends on when managers switch to forward-looking management schemes. Thus, robust climate adaptation policies may depend crucially on a better understanding of what factors influence managers' belief in climate change. Copyright © 2013 Elsevier Ltd. All rights reserved.

Ensemble of random forests One vs. Rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares.

PubMed

Ramírez, J; Górriz, J M; Ortiz, A; Martínez-Murcia, F J; Segovia, F; Salas-Gonzalez, D; Castillo-Barnes, D; Illán, I A; Puntonet, C G

2018-05-15

Alzheimer's disease (AD) is the most common cause of dementia in the elderly and affects approximately 30 million individuals worldwide. Mild cognitive impairment (MCI) is very frequently a prodromal phase of AD, and existing studies have suggested that people with MCI tend to progress to AD at a rate of about 10-15% per year. However, the ability of clinicians and machine learning systems to predict AD based on MRI biomarkers at an early stage is still a challenging problem that can have a great impact in improving treatments. The proposed system, developed by the SiPBA-UGR team for this challenge, is based on feature standardization, ANOVA feature selection, partial least squares feature dimension reduction and an ensemble of One vs. Rest random forest classifiers. With the aim of improving its performance when discriminating healthy controls (HC) from MCI, a second binary classification level was introduced that reconsiders the HC and MCI predictions of the first level. The system was trained and evaluated on an ADNI datasets that consist of T1-weighted MRI morphological measurements from HC, stable MCI, converter MCI and AD subjects. The proposed system yields a 56.25% classification score on the test subset which consists of 160 real subjects. The classifier yielded the best performance when compared to: (i) One vs. One (OvO), One vs. Rest (OvR) and error correcting output codes (ECOC) as strategies for reducing the multiclass classification task to multiple binary classification problems, (ii) support vector machines, gradient boosting classifier and random forest as base binary classifiers, and (iii) bagging ensemble learning. A robust method has been proposed for the international challenge on MCI prediction based on MRI data. The system yielded the second best performance during the competition with an accuracy rate of 56.25% when evaluated on the real subjects of the test set. Copyright © 2017 Elsevier B.V. All rights reserved.

Working with knowledge at the science/policy interface: a unique example from developing the Tongass Land Management Plan.

Treesearch

Charles G. Shaw; Fred H. Everest; Douglas N. Swanston

2000-01-01

An innovative, knowledge-based partnership between research scientists and resource managers in the U.S. Forest Service provided the foundation upon which the Forest Plan was developed that will guide management on the Tongass National Forest for the next 10-15 years. Criteria developed by the scientists to evaluate if management decisions were consistent with the...

An Initial Analysis of LANDSAT-4 Thematic Mapper Data for the Discrimination of Agricultural, Forested Wetland, and Urban Land Covers

NASA Technical Reports Server (NTRS)

Quattrochi, D. A.

1984-01-01

An initial analysis of LANDSAT 4 Thematic Mapper (TM) data for the discrimination of agricultural, forested wetland, and urban land covers is conducted using a scene of data collected over Arkansas and Tennessee. A classification of agricultural lands derived from multitemporal LANDSAT Multispectral Scanner (MSS) data is compared with a classification of TM data for the same area. Results from this comparative analysis show that the multitemporal MSS classification produced an overall accuracy of 80.91% while the TM classification yields an overall classification accuracy of 97.06% correct.

ForestCrowns: a transparency estimation tool for digital photographs of forest canopies

Treesearch

Matthew Winn; Jeff Palmer; S.-M. Lee; Philip Araman

2016-01-01

ForestCrowns is a Windows®-based computer program that calculates forest canopy transparency (light transmittance) using ground-based digital photographs taken with standard or hemispherical camera lenses. The software can be used by forest managers and researchers to monitor growth/decline of forest canopies; provide input for leaf area index estimation; measure light...

Reconciling salvage logging of boreal forests with a tural-disturbance management model.

PubMed

Schmiegelow, Fiona K A; Stepnisky, David P; Stambaugh, Curtis A; Koivula, Matti

2006-08-01

In North American boreal forests, wildfire is the dominant agent of natural disturbance. A natural-disturbance model has therefore been promoted as an ecologically based approach to forest harvesting in these systems. Given accelerating resource demands, fire competes with harvest for timber and there is increasing pressure to salvage naturally burned areas. This creates a management paradox: simultaneous promotion of natural disturbance as a guide to sustainability while salvaging forests that have been naturally disturbed. The major drivers of postfire salvage in Canadian boreal forests are societal perceptions, overallocation of forest resources, and economic and policy incentives, and postfire salvage compromisesforest sustainability by diminishing the role of fire as a critical, natural process. These factors might be reconciled through consideration of fire in resource allocations and application of active adaptive management. We provide novel treatment of the role of burn severity in mediating biotic response by examining its influence on the amount, type, and distribution of live, postfire residual material, and we highlight the role of fire in shaping spatial and temporal patterns in forest biodiversity. Maintenance of natural postfire forests is a critical component of an ecosystem-based approach to forest management in boreal systems. Nevertheless, presentpracticesfocus heavily on expediting removal of timber from burned forests, despite increasing evidence that postfire communities differ markedly from postharvest systems, and there is a mismatch between emerging management models and past management practices. Policies that recognize the critical role of fire in these systems and facilitate enhanced understanding of natural system dynamics in support of development of sustainable management practices are urgently needed.

Monitoring the effects of extreme climate disturbances on forest health in the northeast U.S.

Treesearch

Allan N.D. Auclair; Warren E. Heilman; Peter Busalacchi

2002-01-01

No methodology has been developed to date to predict when a forest population is at risk to specific climate and air pollution stressors. Yet, this information is important to natural resource managers who need frequent, updated assessments of forest health upon which to base management decisions and respond to public concerns on forest health. The USDA Forest Service...

Forest cover loss and urban area expansion in the Conterminous Unites States in the first decade of the third millennium

NASA Astrophysics Data System (ADS)

Huo, L. Z.; Boschetti, L.

2016-12-01

Remote sensing has been successfully used for global mapping of changes in forest cover, but further analysis is needed to characterize those changes - and in particular to classify the total loss of forest loss (Gross Forest Cover Loss, GFCL) based on the cause (natural/human) and on the outcome of the change (regeneration to forest/transition to non-forest) (Kurtz et al., 2010). While natural forest disturbances (fires, insect outbreaks) and timber harvest generally involve a temporary change of land cover (vegetated to non-vegetated), they generally do not involve a change in land use, and it is expected that the forest cover loss is followed by recovery. Change of land use, such as the conversion of forest to agricultural or urban areas, is instead generally irreversible. The proper classification of forest cover loss is therefore necessary to properly model the long term effects of the disturbances on the carbon budget. The present study presents a spatial and temporal analysis of the forest cover loss due to urban expansion in the Conterminous United States. The Landsat-derived University of Maryland Global Forest Change product (Hansen et al, 2013) is used to identify all the areas of gross forest cover loss, which are subsequently classified into disturbance type (deforestation, stand-replacing natural disturbances, industrial forest clearcuts) using an object-oriented time series analysis (Huo and Boschetti, 2015). A further refinement of the classification is conducted to identify the areas of transition from forest land use to urban land use based on ancillary datasets such as the National Land Cover Database (Homer et al., 2015) and contextual image analysis techniques (analysis of object proximity, and detection of shapes). Results showed that over 4000 km2of forest were lost to urban area expansion in CONUS over the 2001 to 2010 period (1.8% of the gross forest cover loss). Most of the urban growth was concentrated in large urban areas: Atlanta, GA ranked first, followed by Houston, TX; Charlotte, NC; Jacksonville, FL; and Raleigh, NC. At the state level, the top 10 states with urban growth due to forest loss were GA, FL, TX, NC, SC, AL, LA, MS, VA and WA, which cumulatively accounted for 76 % of the total forest cover loss due to urban growth.

Criterion 6, indicator 34 : value of capital investment and annual expenditure in forest management, wood and non-wood product industries, forest-based environmental services, recreation, and tourism

Treesearch

Ken Skog; John Bergstrom; Elizabeth Hill; Ken Cordell

2010-01-01

USDA Forest Service capital investment in management infrastructure was $501 and $390 million (2005$) for 2005 and 2007, respectively. National forest programs expenditures decreased from $3.0 to $2.7 billion between 2004 and 2007 and wildfire management expenditures increased from $1.7 to $2.1 billion (2005$). State forestry program expenditures for 1998, 2002, and...

Determining successional stage of temperate coniferous forests with Landsat satellite data

NASA Technical Reports Server (NTRS)

Fiorella, Maria; Ripple, William J.

1995-01-01

Thematic Mapper (TM) digital imagery was used to map forest successional stages and to evaluate spectral differences between old-growth and mature forests in the central Cascade Range of Oregon. Relative sun incidence values were incorporated into the successional stage classification to compensate for topographic induced variation. Relative sun incidence improved the classification accuracy of young successional stages, but did not improve the classification accuracy of older, closed canopy forest classes or overall accuracy. TM bands 1, 2, and 4; the normalized difference vegetation index (NDVI); and TM 4/3, 4/5, and 4/7 band ratio values for old-growth forests were found to be significantly lower than the values of mature forests (P less than or equal to 0.010). Wetness and the TM 4/5 and 4/7 band ratios all had low correlations to relative sun incidence (r(exp 2) less than or equal to 0.16). The TM 4/5 band ratio was named the 'structural index' (SI) because of its ability to distinguish between mature and old-growth forests and its simplicity.

Using the Viability Theory to Assess the Flexibility of Forest Managers Under Ecological Intensification

NASA Astrophysics Data System (ADS)

Mathias, Jean-Denis; Bonté, Bruno; Cordonnier, Thomas; de Morogues, Francis

2015-11-01

Greater demand for wood material has converged with greater demand for biodiversity conservation to make balancing forest ecosystem services a key societal issue. Forest managers, owners, or policymakers need new approaches and methods to evaluate their ability to adapt to this dual objective. We analyze the ability of forest owners to define sustainable forest management options based on viability theory and a new flexibility index. This new indicator gauges the adaptive capacity of forest owners based on the number of sustainable actions available to them at a given time. Here we study a public forest owner who regulates harvest intensity and frequency in order to meet demand for timber wood at forest scale and to meet a biodiversity recommendation via a minimum permanently maintained volume of deadwood per hectare at stand scale. Dynamical systems theory was used to model uneven-aged forest dynamics—including deadwood dynamics—and the dynamics of timber wood demand and tree removals. Uneven-aged silver fir forest management in the "Quatre Montagnes region" (Vercors, France) is used as an illustrative example. The results explain situations where a joint increase in wood production and deadwood retention does not reduce the flexibility index more than increasing either one dimension alone, thus opening up ecological intensification options. To conclude, we discuss the value of the new flexibility index for addressing environmental management and ecological intensification issues.

Chemical ecology and management of bark beetles in western coniferous forests

Treesearch

Christopher J. Fettig

2013-01-01

The future looks bright for the development and use of semiochemical-based tools in forests, particularly in remote and sensitive areas where other management techniques (e.g., the use of insecticides) may not be appropriate. This editorial provides an concise overview of chemical ecology and management of bark beetles in western coniferous forests.

Evidence supporting the need for a common soil monitoring protocol

Treesearch

Derrick A. Reeves; Mark D. Coleman; Deborah S. Page-Dumroese

2013-01-01

Many public land management agencies monitor forest soils for levels of disturbance related to management activities. Although several soil disturbance monitoring protocols based on visual observation have been developed to assess the amount and types of disturbance caused by forest management, no common method is currently used on National Forest lands in the United...

Coastal change analysis program implemented in Louisiana

USGS Publications Warehouse

Ramsey, Elijah W.; Nelson, G.A.; Sapkota, S.K.

2001-01-01

Landsat Thematic Mapper images from 1990 to 1996 and collateral data sources were used to classify the land cover of the Mermentau River Basin (MRB) within the Chenier Plain of coastal Louisiana. Landcover classes followed the definition of the National Oceanic and Atmospheric Administration's Coastal Change Analysis Program; however, classification methods had to be developed as part of this study for attainment of these national classification standards. Classification method developments were especially important when classes were spectrally inseparable, when classes were part of spatial and spectral continuums, when the spatial resolution of the sensor included more than one landcover type, and when human activities caused abnormal transitions in the landscape. Most classification problems were overcome by using one or a combination of techniques, such as separating the MRB into subregions of commonality, applying masks to specific land mixtures, and highlighting class transitions between years that were highly unlikely. Overall, 1990, 1993, and 1996 classification accuracy percentages (associated kappa statistics) were 80% (0.79), 78% (0.76), and 86% (0.84), respectively. Most classification errors were associated with confusion between managed (cultivated land) and unmanaged grassland classes; scrub shrub, grasslands and forest classes; water, unconsolidated shore and bare land classes; and especially in 1993, between water and floating vegetation classes. Combining cultivated land and grassland classes and water and floating vegetation classes into single classes accuracies for 1990, 1993, and 1996 increased to 82%, 83%, and 90%, respectively. To improve the interpretation of landcover change, three indicators of landcover class stability were formulated. Location stability was defined as the percentage of a landcover class that remained as the same class in the same location at the beginning and the end of the monitoring period. Residence stability was defined as the percent change in each class within the entire MRB during the monitoring period. Turnover was defined as the addition of other landcover classes to the target landcover class during the defined monitoring period. These indicators allowed quick assessment of the dynamic nature of landcover classes, both in reference to a spatial location and to retaining their presence throughout the MRB. Examining the landcover changes between 1990 to 1993 and 1993 to 1996, led us to five principal findings: (1) Landcover turnover is maintaining a near stable logging cycle, although the locations of grassland, scrub shrub, and forest areas involved in the cycle appeared to change. (2) Planting of seedlings is critical to maintaining cycle stability. (3) Logging activities tend to replace woody land mixed forests with woody land evergreen forests. (4) Wetland estuarine marshes are expanding slightly. (5) Wetland palustrine marshes and mature forested wetlands in the MRB are relatively stable.

Carbon Legacy of Forest Degradation Foregone: can Europe's Forests Contribute to Deep Decarbonization?

NASA Astrophysics Data System (ADS)

Kauppi, P.; Nabuurs, G. J.

2016-12-01

Contemporary European forests, comprising 161 Mha, play a large role in mitigation of the EU carbon emissions. These intensively managed forests, roughly compensate 10% of EU emissions in forest carbon, in synchrony with the harvest for lumber, fibre and bioenergy, . But this has not always been the case; European forests are recovering since roughly 1850 from thousands of years of human induced degradation. The impact of more recent management is profound and has stimulated a worldwide unique and unprecedented recovery of this forest biome, partly in terms of area, but mainly in forest density that is, biomass per hectare increases. Based on what we know of the recent historic development, can these forests further contribute to deep decarbonization and how? We outline historic development of European forests since roughly 0 AD. We sketch evidence on degradation and deforestation, and on the impact of forest management on restoring the forest growth thus feeding on biomass recovery. We estimate the historical trajectory of the recovery from forest degradation. We discuss the future pathways of European forest resources, and the prospects for the European-model recovery to occur in degraded forests of the other continents. Based on this evidence from the past, we outline what Climate Smart Forestry could mean in the European circumstances aiming to further strengthen this role of European forests. Big scientific challenges remain to understand and project the future development of these forests under climate change and natural disturbances closely entangled with forest management and new demands of industry in the bio-economy.

Analysis of Radarsat-2 Full Polarimetric Data for Forest Mapping

NASA Astrophysics Data System (ADS)

Maghsoudi, Yasser

Forests are a major natural resource of the Earth and control a wide range of environmental processes. Forests comprise a major part of the planet's plant biodiversity and have an important role in the global hydrological and biochemical cycles. Among the numerous potential applications of remote sensing in forestry, forest mapping plays a vital role for characterization of the forest in terms of species. Particularly, in Canada where forests occupy 45% of the territory, representing more than 400 million hectares of the total Canadian continental area. In this thesis, the potential of polarimetric SAR (PolSAR) Radarsat-2 data for forest mapping is investigated. This thesis has two principle objectives. First is to propose algorithms for analyzing the PolSAR image data for forest mapping. There are a wide range of SAR parameters that can be derived from PolSAR data. In order to make full use of the discriminative power offered by all these parameters, two categories of methods are proposed. The methods are based on the concept of feature selection and classifier ensemble. First, a nonparametric definition of the evaluation function is proposed and hence the methods NFS and CBFS. Second, a fast wrapper algorithm is proposed for the evaluation function in feature selection and hence the methods FWFS and FWCBFS. Finally, to incorporate the neighboring pixels information in classification an extension of the FWCBFS method i.e. CCBFS is proposed. The second objective of this thesis is to provide a comparison between leaf-on (summer) and leaf-off (fall) season images for forest mapping. Two Radarsat-2 images acquired in fine quad-polarized mode were chosen for this study. The images were collected in leaf-on and leaf-off seasons. We also test the hypothesis whether combining the SAR parameters obtained from both images can provide better results than either individual datasets. The rationale for this combination is that every dataset has some parameters which may be useful for forest mapping. To assess the potential of the proposed methods their performance have been compared with each other and with the baseline classifiers. The baseline methods include the Wishart classifier, which is a commonly used classification method in PolSAR community, as well as an SVM classifier with the full set of parameters. Experimental results showed a better performance of the leaf-off image compared to that of leaf-on image for forest mapping. It is also shown that combining leaf-off parameters with leaf-on parameters can significantly improve the classification accuracy. Also, the classification results (in terms of the overall accuracy) compared to the baseline classifiers demonstrate the effectiveness of the proposed nonparametric scheme for forest mapping.

Plant landscape design simulating natural community by using AHP method based on TWINSPAN classification

NASA Astrophysics Data System (ADS)

Wang, Li Han

2018-06-01

Taking the forest vegetation in Zijin Mountain (Purple Mountain) Area of Nanjing as the research object, based on the simulation natural and semi natural plant communities, the systematic research on the construction of Nanjing regional plant landscape is carried out by the method such as literature and theory, investigation and evaluation, discussion and reference. On the basis of TWINSPAN classification, the species composition (flora and geographical composition), community structure, species diversity, interspecific relationship and ecological niche of Zijin Mountain natural vegetation are studied and analyzed as a basis for simulation design and planting. Then, from the three levels of ornamental value, resource development and utilization potential and biological characteristics, a comprehensive evaluation system used for wild ornamental plant resources in Zijin Mountain is built. Finally, some suggestions on the planting species of deep forest vegetation in Zijin Mountain are put forward.

Developing Land Surface Type Map with Biome Classification Scheme Using Suomi NPP/JPSS VIIRS Data

NASA Astrophysics Data System (ADS)

Zhang, Rui; Huang, Chengquan; Zhan, Xiwu; Jin, Huiran

2016-08-01

Accurate representation of actual terrestrial surface types at regional to global scales is an important element for a wide range of applications, such as land surface parameterization, modeling of biogeochemical cycles, and carbon cycle studies. In this study, in order to meet the requirement of the retrieval of global leaf area index (LAI) and fraction of photosynthetically active radiation absorbed by the vegetation (fPAR) and other studies, a global map generated from Suomi National Polar- orbiting Partnership (S-NPP) Visible Infrared Imaging Radiometer Suite (VIIRS) surface reflectance data in six major biome classes based on their canopy structures, which include: Grass/Cereal Crops, Shrubs, Broadleaf Crops, Savannas, Broadleaf Forests, and Needleleaf Forests, was created. The primary biome classes were converted from an International Geosphere-Biosphere Program (IGBP) legend global surface type data that was created in previous study, and the separation of two crop types are based on a secondary classification.

[Quantitative classification-based occupational health management for electroplating enterprises in Baoan District of Shenzhen, China].

PubMed

Zhang, Sheng; Huang, Jinsheng; Yang, Baigbing; Lin, Binjie; Xu, Xinyun; Chen, Jinru; Zhao, Zhuandi; Tu, Xiaozhi; Bin, Haihua

2014-04-01

To improve the occupational health management levels in electroplating enterprises with quantitative classification measures and to provide a scientific basis for the prevention and control of occupational hazards in electroplating enterprises and the protection of workers' health. A quantitative classification table was created for the occupational health management in electroplating enterprises. The evaluation indicators included 6 items and 27 sub-items, with a total score of 100 points. Forty electroplating enterprises were selected and scored according to the quantitative classification table. These electroplating enterprises were classified into grades A, B, and C based on the scores. Among 40 electroplating enterprises, 11 (27.5%) had scores of >85 points (grade A), 23 (57.5%) had scores of 60∼85 points (grade B), and 6 (15.0%) had scores of <60 points (grade C). Quantitative classification management for electroplating enterprises is a valuable attempt, which is helpful for the supervision and management by the health department and provides an effective method for the self-management of enterprises.

Comparing ensemble learning methods based on decision tree classifiers for protein fold recognition.

PubMed

Bardsiri, Mahshid Khatibi; Eftekhari, Mahdi

2014-01-01

In this paper, some methods for ensemble learning of protein fold recognition based on a decision tree (DT) are compared and contrasted against each other over three datasets taken from the literature. According to previously reported studies, the features of the datasets are divided into some groups. Then, for each of these groups, three ensemble classifiers, namely, random forest, rotation forest and AdaBoost.M1 are employed. Also, some fusion methods are introduced for combining the ensemble classifiers obtained in the previous step. After this step, three classifiers are produced based on the combination of classifiers of types random forest, rotation forest and AdaBoost.M1. Finally, the three different classifiers achieved are combined to make an overall classifier. Experimental results show that the overall classifier obtained by the genetic algorithm (GA) weighting fusion method, is the best one in comparison to previously applied methods in terms of classification accuracy.

An attribute-based approach to contingent valuation of forest protection programs

Treesearch

Christopher C. Moore; Thomas P. Holmes; Kathleen P. Bell

2011-01-01

The hemlock woolly adelgid is an invasive insect that is damaging hemlock forests in the eastern United States. Several control methods are available but forest managers are constrained by cost, availability, and environmental concerns. As a result forest managers must decide how to allocate limited conservation resources over heterogeneous landscapes. We develop an...

The use of recreation planning tools in U.S. Forest Service NEPA assessments

Treesearch

Lee K. Cerveny; Dale J. Blahna; Marc J. Stern; Michael J. Mortimer; S. Andrew Predmore; James Freeman

2011-01-01

U.S. Forest Service managers are required to incorporate social and biophysical science information in planning and environmental analysis. The use of science is mandated by the National Environmental Policy Act (NEPA), the National Forest Management Act, and U.S. Forest Service planning rules. Despite the agency's emphasis on "science-based"...

Development of a data management front end for use with a LANDSAT based information system. [assessing gypsy moth defoliation damage in Pennsylvania

NASA Technical Reports Server (NTRS)

Turner, B. J. (Principal Investigator)

1982-01-01

A user friendly front end was constructed to facilitate access to the LANDSAT mosaic data base supplied by JPL and to process both LANDSAT and ancillary data. Archieval and retrieval techniques were developed to efficiently handle this data base and make it compatible with requirements of the Pennsylvania Bureau of Forestry. Procedures are ready for: (1) forming the forest/nonforest mask in ORSER compressed map format using GSFC-supplied classification procedures; (2) registering data from a new scene (defoliated) to the mask (which may involve mosaicking if the area encompasses two LANDSAT scenes; (3) producing a masked new data set using the MASK program; (4) analyzing this data set to produce a map showing degrees of defoliation, output on the Versatec plotter; and (5) producing color composite maps by a diazo-type process.

36 CFR 219.11 - Timber requirements based on the NFMA.

Code of Federal Regulations, 2012 CFR

2012-07-01

... 36 Parks, Forests, and Public Property 2 2012-07-01 2012-07-01 false Timber requirements based on the NFMA. 219.11 Section 219.11 Parks, Forests, and Public Property FOREST SERVICE, DEPARTMENT OF AGRICULTURE PLANNING National Forest System Land Management Planning § 219.11 Timber requirements based on the...

36 CFR 219.11 - Timber requirements based on the NFMA.

Code of Federal Regulations, 2014 CFR

2014-07-01

... 36 Parks, Forests, and Public Property 2 2014-07-01 2014-07-01 false Timber requirements based on the NFMA. 219.11 Section 219.11 Parks, Forests, and Public Property FOREST SERVICE, DEPARTMENT OF AGRICULTURE PLANNING National Forest System Land Management Planning § 219.11 Timber requirements based on the...

36 CFR 219.11 - Timber requirements based on the NFMA.

Code of Federal Regulations, 2013 CFR

2013-07-01

... 36 Parks, Forests, and Public Property 2 2013-07-01 2013-07-01 false Timber requirements based on the NFMA. 219.11 Section 219.11 Parks, Forests, and Public Property FOREST SERVICE, DEPARTMENT OF AGRICULTURE PLANNING National Forest System Land Management Planning § 219.11 Timber requirements based on the...

Assessing the effects of management on forest growth across France: insights from a new functional-structural model.

PubMed

Guillemot, Joannès; Delpierre, Nicolas; Vallet, Patrick; François, Christophe; Martin-StPaul, Nicolas K; Soudani, Kamel; Nicolas, Manuel; Badeau, Vincent; Dufrêne, Eric

2014-09-01

The structure of a forest stand, i.e. the distribution of tree size features, has strong effects on its functioning. The management of the structure is therefore an important tool in mitigating the impact of predicted changes in climate on forests, especially with respect to drought. Here, a new functional-structural model is presented and is used to assess the effects of management on forest functioning at a national scale. The stand process-based model (PBM) CASTANEA was coupled to a stand structure module (SSM) based on empirical tree-to-tree competition rules. The calibration of the SSM was based on a thorough analysis of intersite and interannual variability of competition asymmetry. The coupled CASTANEA-SSM model was evaluated across France using forest inventory data, and used to compare the effect of contrasted silvicultural practices on simulated stand carbon fluxes and growth. The asymmetry of competition varied consistently with stand productivity at both spatial and temporal scales. The modelling of the competition rules enabled efficient prediction of changes in stand structure within the CASTANEA PBM. The coupled model predicted an increase in net primary productivity (NPP) with management intensity, resulting in higher growth. This positive effect of management was found to vary at a national scale across France: the highest increases in NPP were attained in forests facing moderate to high water stress; however, the absolute effect of management on simulated stand growth remained moderate to low because stand thinning involved changes in carbon allocation at the tree scale. This modelling approach helps to identify the areas where management efforts should be concentrated in order to mitigate near-future drought impact on national forest productivity. Around a quarter of the French temperate oak and beech forests are currently in zones of high vulnerability, where management could thus mitigate the influence of climate change on forest yield.

[An object-based information extraction technology for dominant tree species group types].

PubMed

Tian, Tian; Fan, Wen-yi; Lu, Wei; Xiao, Xiang

2015-06-01

Information extraction for dominant tree group types is difficult in remote sensing image classification, howevers, the object-oriented classification method using high spatial resolution remote sensing data is a new method to realize the accurate type information extraction. In this paper, taking the Jiangle Forest Farm in Fujian Province as the research area, based on the Quickbird image data in 2013, the object-oriented method was adopted to identify the farmland, shrub-herbaceous plant, young afforested land, Pinus massoniana, Cunninghamia lanceolata and broad-leave tree types. Three types of classification factors including spectral, texture, and different vegetation indices were used to establish a class hierarchy. According to the different levels, membership functions and the decision tree classification rules were adopted. The results showed that the method based on the object-oriented method by using texture, spectrum and the vegetation indices achieved the classification accuracy of 91.3%, which was increased by 5.7% compared with that by only using the texture and spectrum.

Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods

PubMed Central

Burlina, Philippe; Billings, Seth; Joshi, Neil

2017-01-01

Objective To evaluate the use of ultrasound coupled with machine learning (ML) and deep learning (DL) techniques for automated or semi-automated classification of myositis. Methods Eighty subjects comprised of 19 with inclusion body myositis (IBM), 14 with polymyositis (PM), 14 with dermatomyositis (DM), and 33 normal (N) subjects were included in this study, where 3214 muscle ultrasound images of 7 muscles (observed bilaterally) were acquired. We considered three problems of classification including (A) normal vs. affected (DM, PM, IBM); (B) normal vs. IBM patients; and (C) IBM vs. other types of myositis (DM or PM). We studied the use of an automated DL method using deep convolutional neural networks (DL-DCNNs) for diagnostic classification and compared it with a semi-automated conventional ML method based on random forests (ML-RF) and “engineered” features. We used the known clinical diagnosis as the gold standard for evaluating performance of muscle classification. Results The performance of the DL-DCNN method resulted in accuracies ± standard deviation of 76.2% ± 3.1% for problem (A), 86.6% ± 2.4% for (B) and 74.8% ± 3.9% for (C), while the ML-RF method led to accuracies of 72.3% ± 3.3% for problem (A), 84.3% ± 2.3% for (B) and 68.9% ± 2.5% for (C). Conclusions This study demonstrates the application of machine learning methods for automatically or semi-automatically classifying inflammatory muscle disease using muscle ultrasound. Compared to the conventional random forest machine learning method used here, which has the drawback of requiring manual delineation of muscle/fat boundaries, DCNN-based classification by and large improved the accuracies in all classification problems while providing a fully automated approach to classification. PMID:28854220

Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods.

PubMed

Burlina, Philippe; Billings, Seth; Joshi, Neil; Albayda, Jemima

2017-01-01

To evaluate the use of ultrasound coupled with machine learning (ML) and deep learning (DL) techniques for automated or semi-automated classification of myositis. Eighty subjects comprised of 19 with inclusion body myositis (IBM), 14 with polymyositis (PM), 14 with dermatomyositis (DM), and 33 normal (N) subjects were included in this study, where 3214 muscle ultrasound images of 7 muscles (observed bilaterally) were acquired. We considered three problems of classification including (A) normal vs. affected (DM, PM, IBM); (B) normal vs. IBM patients; and (C) IBM vs. other types of myositis (DM or PM). We studied the use of an automated DL method using deep convolutional neural networks (DL-DCNNs) for diagnostic classification and compared it with a semi-automated conventional ML method based on random forests (ML-RF) and "engineered" features. We used the known clinical diagnosis as the gold standard for evaluating performance of muscle classification. The performance of the DL-DCNN method resulted in accuracies ± standard deviation of 76.2% ± 3.1% for problem (A), 86.6% ± 2.4% for (B) and 74.8% ± 3.9% for (C), while the ML-RF method led to accuracies of 72.3% ± 3.3% for problem (A), 84.3% ± 2.3% for (B) and 68.9% ± 2.5% for (C). This study demonstrates the application of machine learning methods for automatically or semi-automatically classifying inflammatory muscle disease using muscle ultrasound. Compared to the conventional random forest machine learning method used here, which has the drawback of requiring manual delineation of muscle/fat boundaries, DCNN-based classification by and large improved the accuracies in all classification problems while providing a fully automated approach to classification.

Application of AIS Technology to Forest Mapping

NASA Technical Reports Server (NTRS)

Yool, S. R.; Star, J. L.

1985-01-01

Concerns about environmental effects of large scale deforestation have prompted efforts to map forests over large areas using various remote sensing data and image processing techniques. Basic research on the spectral characteristics of forest vegetation are required to form a basis for development of new techniques, and for image interpretation. Examination of LANDSAT data and image processing algorithms over a portion of boreal forest have demonstrated the complexity of relations between the various expressions of forest canopies, environmental variability, and the relative capacities of different image processing algorithms to achieve high classification accuracies under these conditions. Airborne Imaging Spectrometer (AIS) data may in part provide the means to interpret the responses of standard data and techniques to the vegetation based on its relatively high spectral resolution.

Classification of large-scale fundus image data sets: a cloud-computing framework.

PubMed

Roychowdhury, Sohini

2016-08-01

Large medical image data sets with high dimensionality require substantial amount of computation time for data creation and data processing. This paper presents a novel generalized method that finds optimal image-based feature sets that reduce computational time complexity while maximizing overall classification accuracy for detection of diabetic retinopathy (DR). First, region-based and pixel-based features are extracted from fundus images for classification of DR lesions and vessel-like structures. Next, feature ranking strategies are used to distinguish the optimal classification feature sets. DR lesion and vessel classification accuracies are computed using the boosted decision tree and decision forest classifiers in the Microsoft Azure Machine Learning Studio platform, respectively. For images from the DIARETDB1 data set, 40 of its highest-ranked features are used to classify four DR lesion types with an average classification accuracy of 90.1% in 792 seconds. Also, for classification of red lesion regions and hemorrhages from microaneurysms, accuracies of 85% and 72% are observed, respectively. For images from STARE data set, 40 high-ranked features can classify minor blood vessels with an accuracy of 83.5% in 326 seconds. Such cloud-based fundus image analysis systems can significantly enhance the borderline classification performances in automated screening systems.

Analyzing the cost effectiveness of Santiago, Chile's policy of using urban forests to improve air quality.

PubMed

Escobedo, Francisco J; Wagner, John E; Nowak, David J; De la Maza, Carmen Luz; Rodriguez, Manuel; Crane, Daniel E

2008-01-01

Santiago, Chile has the distinction of having among the worst urban air pollution problems in Latin America. As part of an atmospheric pollution reduction plan, the Santiago Regional Metropolitan government defined an environmental policy goal of using urban forests to remove particulate matter less than 10 microm (PM(10)) in the Gran Santiago area. We used cost effectiveness, or the process of establishing costs and selecting least cost alternatives for obtaining a defined policy goal of PM(10) removal, to analyze this policy goal. For this study, we quantified PM(10) removal by Santiago's urban forests based on socioeconomic strata and using field and real-time pollution and climate data via a dry deposition urban forest effects model. Municipal urban forest management costs were estimated using management cost surveys and Chilean Ministry of Planning and Cooperation documents. Results indicate that managing municipal urban forests (trees, shrubs, and grass whose management is under the jurisdiction of Santiago's 36 municipalities) to remove PM(10) was a cost-effective policy for abating PM(10) based on criteria set by the World Bank. In addition, we compared the cost effectiveness of managing municipal urban forests and street trees to other control policies (e.g. alternative fuels) to abate PM(10) in Santiago and determined that municipal urban forest management efficiency was similar to these other air quality improvement measures.

Ensemble Feature Learning of Genomic Data Using Support Vector Machine

PubMed Central

Anaissi, Ali; Goyal, Madhu; Catchpoole, Daniel R.; Braytee, Ali; Kennedy, Paul J.

2016-01-01

The identification of a subset of genes having the ability to capture the necessary information to distinguish classes of patients is crucial in bioinformatics applications. Ensemble and bagging methods have been shown to work effectively in the process of gene selection and classification. Testament to that is random forest which combines random decision trees with bagging to improve overall feature selection and classification accuracy. Surprisingly, the adoption of these methods in support vector machines has only recently received attention but mostly on classification not gene selection. This paper introduces an ensemble SVM-Recursive Feature Elimination (ESVM-RFE) for gene selection that follows the concepts of ensemble and bagging used in random forest but adopts the backward elimination strategy which is the rationale of RFE algorithm. The rationale behind this is, building ensemble SVM models using randomly drawn bootstrap samples from the training set, will produce different feature rankings which will be subsequently aggregated as one feature ranking. As a result, the decision for elimination of features is based upon the ranking of multiple SVM models instead of choosing one particular model. Moreover, this approach will address the problem of imbalanced datasets by constructing a nearly balanced bootstrap sample. Our experiments show that ESVM-RFE for gene selection substantially increased the classification performance on five microarray datasets compared to state-of-the-art methods. Experiments on the childhood leukaemia dataset show that an average 9% better accuracy is achieved by ESVM-RFE over SVM-RFE, and 5% over random forest based approach. The selected genes by the ESVM-RFE algorithm were further explored with Singular Value Decomposition (SVD) which reveals significant clusters with the selected data. PMID:27304923

Factors affecting collective action for forest fire management: a comparative study of community forest user groups in central Siwalik, Nepal.

PubMed

Sapkota, Lok Mani; Shrestha, Rajendra Prasad; Jourdain, Damien; Shivakoti, Ganesh P

2015-01-01

The attributes of social ecological systems affect the management of commons. Strengthening and enhancing social capital and the enforcement of rules and sanctions aid in the collective action of communities in forest fire management. Using a set of variables drawn from previous studies on the management of commons, we conducted a study across 20 community forest user groups in Central Siwalik, Nepal, by dividing the groups into two categories based on the type and level of their forest fire management response. Our study shows that the collective action in forest fire management is consistent with the collective actions in other community development activities. However, the effectiveness of collective action is primarily dependent on the complex interaction of various variables. We found that strong social capital, strong enforcement of rules and sanctions, and users' participation in crafting the rules were the major variables that strengthen collective action in forest fire management. Conversely, users' dependency on a daily wage and a lack of transparency were the variables that weaken collective action. In fire-prone forests such as the Siwalik, our results indicate that strengthening social capital and forming and enforcing forest fire management rules are important variables that encourage people to engage in collective action in fire management.

Life on the Edge - Improved Forest Cover Mapping in Mixed-Use Tropical Regions

NASA Astrophysics Data System (ADS)

Anderson, C.; Mendenhall, C. D.; Daily, G.

2016-12-01

Tropical ecosystems and biodiversity are experiencing rapid change, primarily due to conversion of forest habitat to agriculture. Protected areas, while effective for conservation, only manage 15% of terrestrial area, whereas approximately 58% is privately owned. To incentivize private forest management and slow the loss of biodiversity, payments for ecosystem services (PES) programs were established in Costa Rica that pay landowners who maintain trees on their property. While this program is effective in improving livelihoods and preventing forest conversion, it is only managing payments to landowners on 1% of eligible, non-protected forested land.A major bottleneck for this program is access to accurate, national-scale tree cover maps. While the remote sensing community has made great progress in global-scale tree cover mapping, these maps are not sufficient to guide investments for PES programs. The major limitations of current global-scale tree-cover maps are that they a) do not distinguish between forest and agriculture and b) overestimate tree cover in mixed land-use areas (e.g. Global Forest Change overestimates by 20% on average in this region). This is especially problematic in biodiversity-rich Costa Rica, where small patches of forest intermix with agricultural production, and where the conservation value of tree-cover is high. To address this problem, we are developing a new forest cover mapping method that a) performs a least-squares spectral mixture analysis (SMA) using repeat Landsat imagery and canopy radiative transfer modeling: b) combines Landsat data, SMA results, and radar backscatter data using multi-sensor fusion techniques and: c) trains tree-cover classification models using high resolution data sets along a land use-intensity gradient. Our method predicted tree cover with 85% accuracy when compared to a fine-scale map of tree cover in a tropical, agricultural landscape, whereas the next-best method, the Global Forest Change map, predicted tree cover with 72% accuracy. Next steps will aim to test, improve, and apply this method globally to guide investments in nature in agricultural landscapes where forest stewardship will sustain biodiversity.

Red-edge vegetation indices for detecting and assessing disturbances in Norway spruce dominated mountain forests

NASA Astrophysics Data System (ADS)

Adamczyk, Joanna; Osberger, Antonia

2015-05-01

Here we propose an approach to enhance the detection and assessment of forest disturbances in mountain areas based on red-edge reflectance. The research addresses the need for improved monitoring of areas included in the European Natura 2000 network. Thirty-eight vegetation indices (VI) are assessed for sensitivity to topographic variations. A separability analysis is performed for the resulting set of ten VI whereby two VI (PSSRc2, SR 800/550) are found most suitable for threshold-based OBIA classification. With a correlation analysis (SRCC) between VI and the training samples we identify Datt4 as suitable to represent the magnitude of forest disturbance. The provided information layers illustrate two combined phenomena that were derived by (1) an OBIA delineation and (2) continuous representation of the magnitude of forest disturbance. The satisfactory accuracy assessment results confirm that the approach is useful for operational tasks in the long-term monitoring of Norway spruce dominated forests in mountainous areas, with regard to forest disturbance.

Automatic Derivation of Forest Cover and Forest Cover Change Using Dense Multi-Temporal Time Series Data from Landsat and SPOT 5 Take5

NASA Astrophysics Data System (ADS)

Storch, Cornelia; Wagner, Thomas; Ramminger, Gernot; Pape, Marlon; Ott, Hannes; Hausler, Thomas; Gomez, Sharon

2016-08-01

The paper presents a description of the methods development for an automated processing chain for the classification of Forest Cover and Change based on high resolution multi-temporal time series Landsat and SPOT5Take5 data with focus on the dry forest ecosystems of Africa. The method has been developed within the European Space Agency (ESA) funded Global monitoring for Environment and Security Service Element for Forest Monitoring (GSE FM) project on dry forest areas; the demonstration site selected was in Malawi. The methods are based on the principles of a robust, but still flexible monitoring system, to cope with most complex Earth Observation (EO) data scenarios, varying in terms of data quality, source, accuracy, information content, completeness etc. The method allows automated tracking of change dates, data gap filling and takes into account phenology, seasonality of tree species with respect to leaf fall and heavy cloud cover during the rainy season.

Multiple Spectral-Spatial Classification Approach for Hyperspectral Data

NASA Technical Reports Server (NTRS)

Tarabalka, Yuliya; Benediktsson, Jon Atli; Chanussot, Jocelyn; Tilton, James C.

2010-01-01

A .new multiple classifier approach for spectral-spatial classification of hyperspectral images is proposed. Several classifiers are used independently to classify an image. For every pixel, if all the classifiers have assigned this pixel to the same class, the pixel is kept as a marker, i.e., a seed of the spatial region, with the corresponding class label. We propose to use spectral-spatial classifiers at the preliminary step of the marker selection procedure, each of them combining the results of a pixel-wise classification and a segmentation map. Different segmentation methods based on dissimilar principles lead to different classification results. Furthermore, a minimum spanning forest is built, where each tree is rooted on a classification -driven marker and forms a region in the spectral -spatial classification: map. Experimental results are presented for two hyperspectral airborne images. The proposed method significantly improves classification accuracies, when compared to previously proposed classification techniques.

Object-based class modelling for multi-scale riparian forest habitat mapping

NASA Astrophysics Data System (ADS)

Strasser, Thomas; Lang, Stefan

2015-05-01

Object-based class modelling allows for mapping complex, hierarchical habitat systems. The riparian zone, including forests, represents such a complex ecosystem. Forests within riparian zones are biologically high productive and characterized by a rich biodiversity; thus considered of high community interest with an imperative to be protected and regularly monitored. Satellite earth observation (EO) provides tools for capturing the current state of forest habitats such as forest composition including intermixture of non-native tree species. Here we present a semi-automated object based image analysis (OBIA) approach for the mapping of riparian forests by applying class modelling of habitats based on the European Nature Information System (EUNIS) habitat classifications and the European Habitats Directive (HabDir) Annex 1. A very high resolution (VHR) WorldView-2 satellite image provided the required spatial and spectral details for a multi-scale image segmentation and rule-base composition to generate a six-level hierarchical representation of riparian forest habitats. Thereby habitats were hierarchically represented within an image object hierarchy as forest stands, stands of homogenous tree species and single trees represented by sunlit tree crowns. 522 EUNIS level 3 (EUNIS-3) habitat patches with a mean patch size (MPS) of 12,349.64 m2 were modelled from 938 forest stand patches (MPS = 6868.20 m2) and 43,742 tree stand patches (MPS = 140.79 m2). The delineation quality of the modelled EUNIS-3 habitats (focal level) was quantitatively assessed to an expert-based visual interpretation showing a mean deviation of 11.71%.

Field evaluation of a random forest activity classifier for wrist-worn accelerometer data.

PubMed

Pavey, Toby G; Gilson, Nicholas D; Gomersall, Sjaan R; Clark, Bronwyn; Trost, Stewart G

2017-01-01

Wrist-worn accelerometers are convenient to wear and associated with greater wear-time compliance. Previous work has generally relied on choreographed activity trials to train and test classification models. However, validity in free-living contexts is starting to emerge. Study aims were: (1) train and test a random forest activity classifier for wrist accelerometer data; and (2) determine if models trained on laboratory data perform well under free-living conditions. Twenty-one participants (mean age=27.6±6.2) completed seven lab-based activity trials and a 24h free-living trial (N=16). Participants wore a GENEActiv monitor on the non-dominant wrist. Classification models recognising four activity classes (sedentary, stationary+, walking, and running) were trained using time and frequency domain features extracted from 10-s non-overlapping windows. Model performance was evaluated using leave-one-out-cross-validation. Models were implemented using the randomForest package within R. Classifier accuracy during the 24h free living trial was evaluated by calculating agreement with concurrently worn activPAL monitors. Overall classification accuracy for the random forest algorithm was 92.7%. Recognition accuracy for sedentary, stationary+, walking, and running was 80.1%, 95.7%, 91.7%, and 93.7%, respectively for the laboratory protocol. Agreement with the activPAL data (stepping vs. non-stepping) during the 24h free-living trial was excellent and, on average, exceeded 90%. The ICC for stepping time was 0.92 (95% CI=0.75-0.97). However, sensitivity and positive predictive values were modest. Mean bias was 10.3min/d (95% LOA=-46.0 to 25.4min/d). The random forest classifier for wrist accelerometer data yielded accurate group-level predictions under controlled conditions, but was less accurate at identifying stepping verse non-stepping behaviour in free living conditions Future studies should conduct more rigorous field-based evaluations using observation as a criterion measure. Copyright © 2016 Sports Medicine Australia. Published by Elsevier Ltd. All rights reserved.

Ash, the emerald ash borer, and private forest land management

Treesearch

Tom Crowe

2010-01-01

Forest management through emerald ash borer (EAB) will be a dynamic process that will change based on the best information available at the time. Management decisions will depend on the anticipated time of EAB arrival; the diameter and number of ash present in the forest stand; the diameter and number of other desirable and undesirable species present in the stand (...

Unsupported inferences of high-severity fire in historical dry forests of the western United States: Response to Williams and Baker

USGS Publications Warehouse

Fulé, Peter Z.; Swetnam, Thomas W.; Brown, Peter M.; Falk, Donald A.; Peterson, David L.; Allen, Craig D.; Aplet, Gregory H.; Battaglia, Mike A.; Binkley, Dan; Farris, Calvin; Keane, Robert E.; Margolis, Ellis Q.; Grissino-Mayer, Henri; Miller, Carol; Sieg, Carolyn Hull; Skinner, Carl; Stephens, Scott L.; Taylor, Alan

2014-01-01

Reconstructions of dry western US forests in the late 19th century in Arizona, Colorado and Oregon based on General Land Office records were used by Williams & Baker (2012; Global Ecology and Biogeography, 21, 1042–1052; hereafter W&B) to infer past fire regimes with substantial moderate and high-severity burning. The authors concluded that present-day large, high-severity fires are not distinguishable from historical patterns. We present evidence of important errors in their study. First, the use of tree size distributions to reconstruct past fire severity and extent is not supported by empirical age–size relationships nor by studies that directly quantified disturbance history in these forests. Second, the fire severity classification of W&B is qualitatively different from most modern classification schemes, and is based on different types of data, leading to an inappropriate comparison. Third, we note that while W&B asserted ‘surprising’ heterogeneity in their reconstructions of stand density and species composition, their data are not substantially different from many previous studies which reached very different conclusions about subsequent forest and fire behaviour changes. Contrary to the conclusions of W&B, the preponderance of scientific evidence indicates that conservation of dry forest ecosystems in the western United States and their ecological, social and economic value is not consistent with a present-day disturbance regime of large, high-severity fires, especially under changing climate

Current Status and Problems in Certification of Sustainable Forest Management in China

NASA Astrophysics Data System (ADS)

Zhao, Jingzhu; Xie, Dongming; Wang, Danyin; Deng, Hongbing

2011-12-01

Forest certification is a mechanism involving the regulation of trade of forest products in order to protect forest resources and improve forest management. Although China had a late start in adopting this process, the country has made good progress in recent years. As of July 31, 2009, 17 forest management enterprises and more than one million hectares of forests in China have been certified by the Forest Stewardship Council (FSC). Several major factors affect forest certification in China. The first set is institutional in nature. Forest management in China is based on centralized national plans and therefore lacks flexibility. A second factor is public awareness. The importance and value of forest certification are not widely understood and thus consumers do not make informed choices regarding certified forest products. The third major factor is the cost of certification. Together these factors have constrained the development of China's forest certification efforts. However, the process does have great potential. According to preliminary calculations, if 50% of China's commercial forests were certified, the economic cost of forest certification would range from US0.66-86.63 million while the economic benefits for the forestry business sector could exceed US150 million. With continuing progress in forest management practices and the development of international trade in forest products, it becomes important to improve the forest certification process in China. This can be achieved by improving the forest management system, constructing and perfecting market access mechanisms for certificated forest products, and increasing public awareness of environmental protection, forest certification, and their interrelationship.

Current status and problems in certification of sustainable forest management in China.

PubMed

Zhao, Jingzhu; Xie, Dongming; Wang, Danyin; Deng, Hongbing

2011-12-01

Forest certification is a mechanism involving the regulation of trade of forest products in order to protect forest resources and improve forest management. Although China had a late start in adopting this process, the country has made good progress in recent years. As of July 31, 2009, 17 forest management enterprises and more than one million hectares of forests in China have been certified by the Forest Stewardship Council (FSC). Several major factors affect forest certification in China. The first set is institutional in nature. Forest management in China is based on centralized national plans and therefore lacks flexibility. A second factor is public awareness. The importance and value of forest certification are not widely understood and thus consumers do not make informed choices regarding certified forest products. The third major factor is the cost of certification. Together these factors have constrained the development of China's forest certification efforts. However, the process does have great potential. According to preliminary calculations, if 50% of China's commercial forests were certified, the economic cost of forest certification would range from US$0.66-86.63 million while the economic benefits for the forestry business sector could exceed US$150 million. With continuing progress in forest management practices and the development of international trade in forest products, it becomes important to improve the forest certification process in China. This can be achieved by improving the forest management system, constructing and perfecting market access mechanisms for certificated forest products, and increasing public awareness of environmental protection, forest certification, and their interrelationship.

Using cluster analysis and a classification and regression tree model to developed cover types in the Sky Islands of southeastern Arizona

Treesearch

Jose M. Iniguez; Joseph L. Ganey; Peter J. Daughtery; John D. Bailey

2005-01-01

The objective of this study was to develop a rule based cover type classification system for the forest and woodland vegetation in the Sky Islands of southeastern Arizona. In order to develop such a system we qualitatively and quantitatively compared a hierarchical (Ward’s) and a non-hierarchical (k-means) clustering method. Ecologically, unique groups represented by...

Using cluster analysis and a classification and regression tree model to developed cover types in the Sky Islands of southeastern Arizona [Abstract

Treesearch

Jose M. Iniguez; Joseph L. Ganey; Peter J. Daugherty; John D. Bailey

2005-01-01

The objective of this study was to develop a rule based cover type classification system for the forest and woodland vegetation in the Sky Islands of southeastern Arizona. In order to develop such system we qualitatively and quantitatively compared a hierarchical (Ward’s) and a non-hierarchical (k-means) clustering method. Ecologically, unique groups and plots...

Mapping Sub-Antarctic Cushion Plants Using Random Forests to Combine Very High Resolution Satellite Imagery and Terrain Modelling

PubMed Central

Bricher, Phillippa K.; Lucieer, Arko; Shaw, Justine; Terauds, Aleks; Bergstrom, Dana M.

2013-01-01

Monitoring changes in the distribution and density of plant species often requires accurate and high-resolution baseline maps of those species. Detecting such change at the landscape scale is often problematic, particularly in remote areas. We examine a new technique to improve accuracy and objectivity in mapping vegetation, combining species distribution modelling and satellite image classification on a remote sub-Antarctic island. In this study, we combine spectral data from very high resolution WorldView-2 satellite imagery and terrain variables from a high resolution digital elevation model to improve mapping accuracy, in both pixel- and object-based classifications. Random forest classification was used to explore the effectiveness of these approaches on mapping the distribution of the critically endangered cushion plant Azorella macquariensis Orchard (Apiaceae) on sub-Antarctic Macquarie Island. Both pixel- and object-based classifications of the distribution of Azorella achieved very high overall validation accuracies (91.6–96.3%, κ = 0.849–0.924). Both two-class and three-class classifications were able to accurately and consistently identify the areas where Azorella was absent, indicating that these maps provide a suitable baseline for monitoring expected change in the distribution of the cushion plants. Detecting such change is critical given the threats this species is currently facing under altering environmental conditions. The method presented here has applications to monitoring a range of species, particularly in remote and isolated environments. PMID:23940805

A heuristic expert system for forest fire guidance in Greece.

PubMed

Iliadis, Lazaros S; Papastavrou, Anastasios K; Lefakis, Panagiotis D

2002-07-01

Forests and forestlands are common inheritance for all Greeks and a piece of the national wealth that must be handed over to the next generations in the best possible condition. After 1974, Greece faces a severe forest fire problem and forest fire forecasting is the process that will enable the Greek ministry of Agriculture to reduce the destruction. This paper describes the basic design principles of an Expert System that performs forest fire forecasting (for the following fire season) and classification of the prefectures of Greece into forest fire risk zones. The Expert system handles uncertainty and uses heuristics in order to produce scenarios based on the presence or absence of various qualitative factors. The initial research focused on the construction of a mathematical model which attempted to describe the annual number of forest fires and burnt area in Greece based on historical data. However this has proven to be impossible using regression analysis and time series. A closer analysis of the fire data revealed that two qualitative factors dramatically affect the number of forest fires and the hectares of burnt areas annually. The first is political stability and national elections and the other is drought cycles. Heuristics were constructed that use political stability and drought cycles, to provide forest fire guidance. Fuzzy logic was applied to produce a fuzzy expected interval for each prefecture of Greece. A fuzzy expected interval is a narrow interval of values that best describes the situation in the country or a part of the country for a certain time period. A successful classification of the prefectures of Greece in forest fire risk zones was done by the system, by comparing the fuzzy expected intervals to each other. The system was tested for the years 1994 and 1995. The testing has clearly shown that the system can predict accurately, the number of forest fires for each prefecture for the following year. The average accuracy was as high as 85.25% for 1995 and 80.89% for 1994. This makes the Expert System a very important tool for forest fire prevention planning.

Role of the U.S. Forest Service: Helping forests, grasslands, and wildlife adapt to shifts in climate

Treesearch

Monica S. Tomosy; Frank R. Thompson; Douglas Boyce

2011-01-01

This fall, the U.S. Forest Service (USFS) will release a comprehensive new guidebook designed to help managers develop climate adaptation options for National Forests (Peterson et al. 2011, in press). The adaptation process is based on partnerships between local resource managers and scientists working collaboratively to understand potential climate change effects,...

Invasive Species as Ecological Threat: Is Restoration an Alternative to Fear-based Resource Management?

Treesearch

Paul H. Gobster

2005-01-01

Invasive species is a hot topic in the USDA Forest Service these days. Along with wildfire, land conversion and unmanaged recreation, Chief Dale Bosworth has called invasive species one of the `Four Threats` needing the attention of Forest Service land managers and researchers (USDA Forest Service 2004). My unit of the Forest Service, the North Central Research...

Managed wildfire effects on forest resilience and water in the Sierra Nevada

Treesearch

Gabrielle Boisramé; Sally Thompson; Brandon Collins; Scott Stephens

2017-01-01

Fire suppression in many dry forest types has left a legacy of dense, homogeneous forests. Such landscapes have high water demands and fuel loads, and when burned can result in catastrophically large fires. These characteristics are undesirable in the face of projected warming and drying in the western US. Alternative forest and fire treatments based on managed...

Stability and change in forest-based communities: a selected bibliography.

Treesearch

Catherine Woods Richardson

1996-01-01

This bibliography lists literature dealing with the concept of community stability, the condition of forest-based communities, and the relations between forest management and local community conditions. Most citations are from the 1970s to the mid 1990s, though some particularly pertinent earlier works also appear. The emphasis is on forest-based communities in the...

The vegetation of the Grand River/Cedar River, Sioux, and Ashland Districts of the Custer National Forest: a habitat type classification.

Treesearch

Paul L. Hansen; George R. Hoffman

1988-01-01

A vegetation classification was developed, using the methods and concepts of Daubenmire, on the Ashland, Sioux, and Grand River/Cedar River Districts of the Custer National Forest. Of the 26 habitat types delimited and described, eight were steppe, nine shrub-steppe, four woodland, and five forest. Two community types also were described. A key to the habitat types and...

Annual Forest Monitoring as part of Indonesia's National Carbon Accounting System

NASA Astrophysics Data System (ADS)

Kustiyo, K.; Roswintiarti, O.; Tjahjaningsih, A.; Dewanti, R.; Furby, S.; Wallace, J.

2015-04-01

Land use and forest change, in particular deforestation, have contributed the largest proportion of Indonesia's estimated greenhouse gas emissions. Indonesia's remaining forests store globally significant carbon stocks, as well as biodiversity values. In 2010, the Government of Indonesia entered into a REDD+ partnership. A spatially detailed monitoring and reporting system for forest change which is national and operating in Indonesia is required for participation in such programs, as well as for national policy reasons including Monitoring, Reporting, and Verification (MRV), carbon accounting, and land-use and policy information. Indonesia's National Carbon Accounting System (INCAS) has been designed to meet national and international policy requirements. The INCAS remote sensing program is producing spatially-detailed annual wall-to-wall monitoring of forest cover changes from time-series Landsat imagery for the whole of Indonesia from 2000 to the present day. Work on the program commenced in 2009, under the Indonesia-Australia Forest Carbon Partnership. A principal objective was to build an operational system in Indonesia through transfer of knowledge and experience, from Australia's National Carbon Accounting System, and adaptation of this experience to Indonesia's requirements and conditions. A semi-automated system of image pre-processing (ortho-rectification, calibration, cloud masking and mosaicing) and forest extent and change mapping (supervised classification of a 'base' year, semi-automated single-year classifications and classification within a multi-temporal probabilistic framework) was developed for Landsat 5 TM and Landsat 7 ETM+. Particular attention is paid to the accuracy of each step in the processing. With the advent of Landsat 8 data and parallel development of processing capability, capacity and international collaborations within the LAPAN Data Centre this processing is being increasingly automated. Research is continuing into improved processing methodology and integration of information from other data sources. This paper presents technical elements of the INCAS remote sensing program and some results of the 2000 - 2012 mapping.

Medical and Endoscopic Management of Gastric Varices

PubMed Central

Al-Osaimi, Abdullah M. S.; Caldwell, Stephen H.

2011-01-01

In the past 20 years, our understanding of the pathophysiology and management options among patients with gastric varices (GV) has changed significantly. GV are the most common cause of upper gastrointestinal bleeding in patients with portal hypertension after esophageal varices (EV) and generally have more severe bleeding than EV. In the United States, the majority of GV patients have underlying portal hypertension rather than splenic vein thrombosis. The widely used classifications are the Sarin Endoscopic Classification and the Japanese Vascular Classifications. The former is based on the endoscopic appearance and location of the varices, while the Japanese classification is based on the underlying vascular anatomy. In this article, the authors address the current concepts of classification, epidemiology, pathophysiology, and emerging management options of gastric varices. They describe the stepwise approach to patients with gastric varices, including the different available modalities, and the pearls, pitfalls, and stop-gap measures useful in managing patients with gastric variceal bleed. PMID:22942544

Can we reliably estimate managed forest carbon dynamics using remotely sensed data?

NASA Astrophysics Data System (ADS)

Smallman, Thomas Luke; Exbrayat, Jean-Francois; Bloom, A. Anthony; Williams, Mathew

2015-04-01

Forests are an important part of the global carbon cycle, serving as both a large store of carbon and currently as a net sink of CO2. Forest biomass varies significantly in time and space, linked to climate, soils, natural disturbance and human impacts. This variation means that the global distribution of forest biomass and their dynamics are poorly quantified. Terrestrial ecosystem models (TEMs) are rarely evaluated for their predictions of forest carbon stocks and dynamics, due to a lack of knowledge on site specific factors such as disturbance dates and / or managed interventions. In this regard, managed forests present a valuable opportunity for model calibration and improvement. Spatially explicit datasets of planting dates, species and yield classification, in combination with remote sensing data and an appropriate data assimilation (DA) framework can reduce prediction uncertainty and error. We use a Baysian approach to calibrate the data assimilation linked ecosystem carbon (DALEC) model using a Metropolis Hastings-Markov Chain Monte Carlo (MH-MCMC) framework. Forest management information is incorporated into the data assimilation framework as part of ecological and dynamic constraints (EDCs). The key advantage here is that DALEC simulates a full carbon balance, not just the living biomass, and that both parameter and prediction uncertainties are estimated as part of the DA analysis. DALEC has been calibrated at two managed forests, in the USA (Pinus taeda; Duke Forest) and UK (Picea sitchensis; Griffin Forest). At each site DALEC is calibrated twice (exp1 & exp2). Both calibrations (exp1 & exp2) assimilated MODIS LAI and HWSD estimates of soil carbon stored in soil organic matter, in addition to common management information and prior knowledge included in parameter priors and the EDCs. Calibration exp1 also utilises multiple site level estimates of carbon storage in multiple pools. By comparing simulations we determine the impact of site-level observations on uncertainty and error on predictions, and which observations are key to constraining ecosystem processes. Preliminary simulations indicate that DALEC calibration exp1 accurately simulated the assimilated observations for forest and soil carbon stock estimates including, critically for forestry, standing wood stocks (R2 = 0.92, bias = -4.46 MgC ha-1, RMSE = 5.80 MgC ha-1). The results from exp1 indicate the model is able to find parameters that are both consistent with EDC and observations. In the absence of site-level stock observations (exp2) DALEC accurately estimates foliage and fine root pools, while the median estimate of above ground litter and wood stocks (R2 = 0.92, bias = -48.30 MgC ha-1, RMSE = 50.30 MgC ha-1) are over- and underestimated respectively, site-level observations are within model uncertainty. These results indicate that we can estimate managed forests dynamics using remotely sensed data, particularly as remotely sensed above ground biomass maps become available to provide constraint to correct biases in woody accumulation.

Mediterranean Land Use and Land Cover Classification Assessment Using High Spatial Resolution Data

NASA Astrophysics Data System (ADS)

Elhag, Mohamed; Boteva, Silvena

2016-10-01

Landscape fragmentation is noticeably practiced in Mediterranean regions and imposes substantial complications in several satellite image classification methods. To some extent, high spatial resolution data were able to overcome such complications. For better classification performances in Land Use Land Cover (LULC) mapping, the current research adopts different classification methods comparison for LULC mapping using Sentinel-2 satellite as a source of high spatial resolution. Both of pixel-based and an object-based classification algorithms were assessed; the pixel-based approach employs Maximum Likelihood (ML), Artificial Neural Network (ANN) algorithms, Support Vector Machine (SVM), and, the object-based classification uses the Nearest Neighbour (NN) classifier. Stratified Masking Process (SMP) that integrates a ranking process within the classes based on spectral fluctuation of the sum of the training and testing sites was implemented. An analysis of the overall and individual accuracy of the classification results of all four methods reveals that the SVM classifier was the most efficient overall by distinguishing most of the classes with the highest accuracy. NN succeeded to deal with artificial surface classes in general while agriculture area classes, and forest and semi-natural area classes were segregated successfully with SVM. Furthermore, a comparative analysis indicates that the conventional classification method yielded better accuracy results than the SMP method overall with both classifiers used, ML and SVM.

Forest succession on four habitat types in western Montana

Treesearch

Stephen F. Arno; Dennis G. Simmerman; Robert E. Keane

1985-01-01

Presents classifications of successional community types on four major forest habitat types in western Montana. Classifications show the sequences of seral community types developing after stand-replacing wildfire and clearcutting with broadcast burning, mechanical scarification, or no followup treatment. Information is provided for associating vegetational response to...

Site classification for northern forest species

Treesearch

Willard H. Carmean

1977-01-01

Summarizes the extensive literature for northern forest species covering site index curves, site index species comparisons, growth intercepts, soil-site studies, plant indicators, physiographic site classifications, and soil survey studies. The advantages and disadvantages of each are discussed, and suggestions are made for future research using each of these methods....

Assessing Land Management Changes and Population Dynamics in Central Burkina Faso in Response to Climate Change.

NASA Astrophysics Data System (ADS)

Kabore Bontogho, P. E.; Boubacar, I.; Afouda, A.; Joerg, H.

2015-12-01

Assessing landscape and population's dynamics at watershed level contribute to address anthropogenic aspect of climate change issue owing to the close link between LULC and climate changes. The objective of this study is to explore the dependencies of population to land management changes in Massili basin (2612 km²) located in central Burkina Faso. A set of three satellite scenes was acquired for the years 1990 (Landsat 7 ETM), 2002 (Landsat 7 ETM+) and 2013 (Landsat 8 OLI/TIRS) from the Global Land Cover Facility's (GLCF) website. Census data were provided by the National institute of statistics and demographic (INSD). The satellites images were classified using object-oriented classification method which was supported by historic maps and field data. Those were collected in order to allow for class definition, verification and accuracy assessments. Based on the developed land use maps, change analysis was carried out using post classification comparison in GIS. Finally, derived land use changes were compared with census data in order to explore links between population dynamics and the land use changes. It was found in 1990 that Massili watershed LULC was dominated by Tree/shrub savannah (69%, 1802.28 km2 ), Farm/Fallow was representing 22%, Gallery forest (4%), Settlement (3%), Barre soil (1%), Water bodies (1%). In 2002, the major landscape was Farm (54%). Tree/Shrub savannas were reduced to 36% while the Gallery Forest was decreased to1% of the basin area. The situation has also slightly changed in 2013 with an increase of the area devoted to farm/fallow and settlement at a rate of 3% and Gallery forest has increased to 4%. The changes in land use are in agreement with a notable increase in population. The analysis of census data showed that the number of inhabitants increased from 338 inhabitants per km2 in 1990 to 1150 inhabitants per km2 in 2013. As shown by statistical analysis (Kendall correlation tau=0.9), there is a close relation between both dynamics.

Quantification of forest carbon degradation in Nicaragua using RapidEye remote sensing data: El Cuá and Wiwili case studies

NASA Astrophysics Data System (ADS)

Argoty, F. N.; Cifuentes, M.; Imbach, P. A.; Vilchez, S.; Casanoves, F.; Ibrahim, M.; Vierling, L. A.

2012-12-01

Forest degradation and deforestation affect ecosystem function and climate regulation services such as carbon storage. Historically, Central America has been a deforestation and forest degradation hotspot. Wiwili and El Cuá municipalities in northern Nicaragua are no exception, where subsistence agriculture and cattle ranch expansion have driven deforestation and other wood extraction activities, leading to various levels of forest degradation. Reduction of Emissions from forest Degradation and Deforestation (REDD) projects are proposed as a tool to slow the degradation and loss of carbon stocks by restoring carbon to its natural levels in order to mitigate carbon dioxide emissions that cause global warming. REDD projects require baseline estimations of current carbon stocks and forest degradation status. We estimated carbon stocks across a forest degradation gradient based on common biophysical variables and commercially available (RapidEye) remote sensing data. We measured 80 temporary forest plots (50x20m) for aboveground biomass to sample a gradient of forest degradation at two municipalities (El Cuá and Wiwili) in northern Nicaragua. We measured biomass in trees (≥10 cm DBH), saplings (5-9.9 cm DBH), other growth forms (ferns, palms and woody vines), and large detritus (snags and downed wood). Biomass was estimated by a range of allometric models and a constant conversion factor (0.47) was applied to calculate aboveground carbon stocks. Remote sensing data from a RapidEye scene for 02/2010 provided data for 5 spectral bands and 19 vegetation indexes at 6 m spatial resolution. Precipitation, temperature, altitude, slope, canopy cover, and aspect were also used as input variables for carbon modeling. We tested linear mixed models, generalized additive mixed models and regression tree approaches to explain carbon stocks based on vegetation indexes and biophysical variables. Additionally, we grouped plots into low (17-168 Mg C ha-1), medium (168-302 Mg C ha-1) and high (302-418 Mg C ha-1) carbon stocks (with conglomerate analysis) to test for a categorical classification approach based on discriminant analysis. Results show a gradient of total aboveground carbon between 17.78 - 379.2 Mg C ha-1. Models predicting carbon stock had an R2 that ranged between 0.32-0.52 (p<0.0001) across the three methods evaluated. Linear mixed models using the MCARI-MTVI2 vegetation index, based on the red-edge band (690-730 nm), showed the best performance. Categorical classification showed improved performance, with a 17% mean classification error, using 20 predictors (MCARI-MTVI2 was the most important). Our results show the importance of the red-edge band and the potential of multi-spectral high-resolution imagery to quantify tropical forest degradation. Although model performance for prediction of continuous biomass values is somewhat constrained, there is potential for coarser applications in the context of developing REDD baselines and monitoring using categorical mapping of forest degradation (with a trade-off in inference power) by means of relatively low-cost remote sensing and ancillary data.

Public perceptions about climate change mitigation in British Columbia's forest sector

PubMed Central

Hagerman, Shannon; Kozak, Robert; Hoberg, George

2018-01-01

The role of forest management in mitigating climate change is a central concern for the Canadian province of British Columbia. The successful implementation of forest management activities to achieve climate change mitigation in British Columbia will be strongly influenced by public support or opposition. While we now have increasingly clear ideas of the management opportunities associated with forest mitigation and some insight into public support for climate change mitigation in the context of sustainable forest management, very little is known with respect to the levels and basis of public support for potential forest management strategies to mitigate climate change. This paper, by describing the results of a web-based survey, documents levels of public support for the implementation of eight forest carbon mitigation strategies in British Columbia’s forest sector, and examines and quantifies the influence of the factors that shape this support. Overall, respondents ascribed a high level of importance to forest carbon mitigation and supported all of the eight proposed strategies, indicating that the British Columbia public is inclined to consider alternative practices in managing forests and wood products to mitigate climate change. That said, we found differences in levels of support for the mitigation strategies. In general, we found greater levels of support for a rehabilitation strategy (e.g. reforestation of unproductive forest land), and to a lesser extent for conservation strategies (e.g. old growth conservation, reduced harvest) over enhanced forest management strategies (e.g. improved harvesting and silvicultural techniques). We also highlighted multiple variables within the British Columbia population that appear to play a role in predicting levels of support for conservation and/or enhanced forest management strategies, including environmental values, risk perception, trust in groups of actors, prioritized objectives of forest management and socio-demographic factors. PMID:29684041