A comparison of multi-spectral, multi-angular, and multi-temporal remote sensing datasets for fractional shrub canopy mapping in Arctic Alaska

Shrub cover appears to be increasing across many areas of the Arctic tundra biome, and increasing shrub cover in the Arctic has the potential to significantly impact global carbon budgets and the global climate system. For most of the Arctic, however, there is no existing baseline inventory of shrub canopy cover, as existing maps of Arctic vegetation provide little information about the density of shrub cover at a moderate spatial resolution across the region. Remotely-sensed fractional shrub canopy maps can provide this necessary baseline inventory of shrub cover. In this study, we compare the accuracy of fractional shrub canopy (> 0.5 m tall) maps derived from multi-spectral, multi-angular, and multi-temporal datasets from Landsat imagery at 30 m spatial resolution, Moderate Resolution Imaging SpectroRadiometer (MODIS) imagery at 250 m and 500 m spatial resolution, and MultiAngle Imaging Spectroradiometer (MISR) imagery at 275 m spatial resolution for a 1067 km² study area in Arctic Alaska. The study area is centered at 69 °N, ranges in elevation from 130 to 770 m, is composed primarily of rolling topography with gentle slopes less than 10°, and is free of glaciers and perennial snow cover. Shrubs > 0.5 m in height cover 2.9% of the study area and are primarily confined to patches associated with specific landscape features. Reference fractional shrub canopy is determined from in situ shrub canopy measurements and a high spatial resolution IKONOS image swath. Regression tree models are constructed to estimate fractional canopy cover at 250 m using different combinations of input data from Landsat, MODIS, and MISR. Results indicate that multi-spectral data provide substantially more accurate estimates of fractional shrub canopy cover than multi-angular or multi-temporal data. Higher spatial resolution datasets also provide more accurate estimates of fractional shrub canopy cover (aggregated to moderate spatial resolutions) than lower spatial resolution datasets, an expected result for a study area where most shrub cover is concentrated in narrow patches associated with rivers, drainages, and slopes. Including the middle infrared bands available from Landsat and MODIS in the regression tree models (in addition to the four standard visible and near-infrared spectral bands) typically results in a slight boost in accuracy. Including the multi-angular red band data available from MISR in the regression tree models, however, typically boosts accuracy more substantially, resulting in moderate resolution fractional shrub canopy estimates approaching the accuracy of estimates derived from the much higher spatial resolution Landsat sensor. Given the poor availability of snow and cloud-free Landsat scenes in many areas of the Arctic and the promising results demonstrated here by the MISR sensor, MISR may be the best choice for large area fractional shrub canopy mapping in the Alaskan Arctic for the period 2000-2009.     

Single tree detection in very high resolution remote sensing data

Tree detection is a major focus in the field of (semi-) automatic extraction of forest information from very high resolution remote sensing data. Many existing tree crown delineation algorithms require a set of seed pixels to start the process of image segmentation. In this study, different methods of obtaining seed pixels (semi-) automatically from orthophotos and digital surface models derived from stereo digital camera imagery are tested and compared. The UltracamD digital camera provides images with a stereo overlap of about 90% and this paper presents a new method of DSM generation based on multiple stereo pairs. The evaluation of the DSMs shows that by using a multiple image approach, also referred to as block-based approach, the quality is significantly increased: the mean difference between the estimated values and 356 measured upper layer tree heights is only 0.77 m with a standard deviation of 2.39 m.

In terms of seed generation, the morph algorithm (2d) used in this paper detected 64% of the trees visible in the aerial photos with an error margin of around 25% both for commission and omission in a dense natural forest. The orthophoto-based local maximum approach generally yielded lower accuracies and more multiple hits than the morph algorithm. 3d seed generation from the block based model returned about 70% correct hits for the upper tree canopy layer. All evaluations are performed based on field measurements and visual aerial photo interpretation. Furthermore, the dependence of successful tree detection on the dominance of a tree within the stand is analyzed. As expected, suppressed trees are more likely to be omitted. The segmentation proved to be useful, as the automatically generated segments had a similar number of correct hits as achieved by visual interpretation, with the only drawback being a higher error of commission.     

Height growth reconstruction of a boreal forest canopy over a period of 58 years using a combination of photogrammetric and lidar models

Field data describing the height growth of trees or stands over several decades are very scarce. Consequently, our capacity of analyzing forest dynamics over large areas and long periods of time is somewhat limited. This study proposes a new method for retrospectively reconstructing plot-wise average dominant tree height based on a time series of high-resolution canopy height maps, termed canopy height models (CHMs). The absolute elevation of the canopy surface, or digital surface model (DSM), was first reconstructed by applying image-matching techniques to stereo-pairs of aerial photographs acquired in 1945, 1965, 1983, and 2003. The historical CHMs were then created by subtracting the bare earth elevation provided from a recent lidar survey from the DSMs. A method for estimating average dominant tree height from these historical CHMs was developed and calibrated for each photographic year. The accuracy of the resulting remote sensing height estimates was compared to age-height data reconstructed based on dendrometric measurements. The height bias of the remote sensing estimates relative to the verification data ranged from 0.52 m to 1.55 m (1.16 m on average). The corresponding root-mean-square errors varied between 1.49 m and 2.88 m (2.03 m average). Despite being slightly less accurate than historical field data, the quality of the remote sensing estimates is sufficient for many types of forest dynamics studies. The procedures for implementing this method, with the exception of the calibration phase, are entirely automated such that forest height growth curves can be reconstructed and mapped over large areas for which recent lidar data and historical photographs exist.     

Global mapping of foliage clumping index using multi-angular satellite data

Global mapping of the vegetation clumping index is attempted for the first time using multi-angular POLDER 1 data based on a methodology that has been demonstrated to be applicable to Canada's landmass. The clumping index quantified the level of foliage grouping within distinct canopy structures, such as tree crowns, shrubs, and row crops, relative to a random distribution. Vegetation foliage clumping significantly alters its radiation environment and therefore affects vegetation growth as well as water and carbon cycles. The clumping index is useful in ecological and meteorological models because it provides new structural information in addition to the effective LAI retrieved from mono-angle remote sensing and allows accurate separation of sunlit and shaded leaves in the canopy. The relationship between an angular index (normalized difference between hotspot and darkspot) and the clumping index is explored using a geometrical optical model named “4-Scale”. A simplified version of the mechanistic hotspot model used in 4-Scale is developed to derive the hotspot reflectance from multi-angle measurements for mapping purposes. An accurate clumping map for areas with significant tree (shrub) covers has been achieved, although further research is required to reduce topographic effects.     

Integration of varying spatial,spectral and temporal high-resolution optical images for individual tree crown isolation

Automated methods for capturing geometric and spectral properties of individual tree crowns are becoming increasingly viable options for use in natural resource planning. Crown isolation techniques are needed that are capable of adapting to the changing availability and resolutions of remotely sensed data. Data integration, or the fusion of two distinct data entities, offers a methodological framework that can compensate for the shortcomings of individual datasets while enhancing their desirable features. This study sought to develop a method of data integration for high-resolution optical images of varying spatial and temporal resolutions to improve the automatic detection and delineation of individual tree crowns. A marker-controlled watershed segmentation (MCWS) algorithm was developed for a 30-cm-per-pixel-side airborne colour infrared (CIR) digital image of a leaf-on apple (Malus spp.) orchard. Three methods of obtaining the markers needed for the MCWS algorithm were tested: (1) manual marker selection, (2) template/correlation selection using the 30-cm CIR image, and (3) template/correlation selection using a 15-cm-per-pixel-side true (TRU) colour leaf-off aerial image. The effectiveness of integrating marker data of different temporal and spatial resolutions with the segmentation process of the CIR image scene was tested. A comparison of crown isolation results using markers derived within the segmented 30-cm CIR digital imagery with results from markers derived from the 15-cm TRU image scene indicated greater accuracies to detect and isolate tree crowns with data integration.     

基于分类回归树的密云水库上游森林覆盖度遥感估算

森林覆盖度是描述森林生态状况的重要指标,也是气候、水文模型的重要输入参数。以多时相的HJ星 CCD数据为主要数据源,利用分类回归树的方法对密云水库上游的森林覆盖度进行了遥感估算,通过基于高分航片提取的样本数据对估算结果进行了验证,并与传统回归模型进行了比较分析。结果表明:以HJ星及其他辅助数据为数据源,采用分类回归树的方法估测森林覆盖度可以达到较高的精度,拟合决定系数R²达到0.749,建模均方根及验证均方根误差分别为0.068和0.118,均明显优于传统回归模型,适用于大区域的森林覆盖度遥感估算。     

Change detection with heterogeneous data using ecoregional stratification, statistical summaries and a land allocation algorithm

A ca. 1980 national-scale land-cover classification based on aerial photo interpretation was combined with 2000 AVHRR satellite imagery to derive land cover and land-cover change information for forest, urban, and agriculture categories over a seven-state region in the U.S. To derive useful land-cover change data using a heterogeneous dataset and to validate our results, we a) stratified the classification using predefined ecoregions, b) developed statistical relationships by ecoregion between land-cover proportions derived from the 1980 national-level classification and aggregate statistical data that were available in time series for all regions in the U.S., c) classified multi-temporal AVHRR data using a process that constrained the results to the estimated proportions of land covers in ecoregions within a multi-objective land allocation (MOLA) procedure, d) interpreted land cover from a sample of aerial photographs from 2000, following the protocols used to produce the 1980 classification for use in accuracy assessment of land cover and land-cover change data, and e) compared land cover and land-cover change results for the MOLA method with an unsupervised classification alone. Overall accuracies for the 2000 MOLA and unsupervised land-cover classifications were 85% and 82%, respectively. On average, the 1980-2000 land-cover change RMSEs were one order of magnitude lower using the MOLA method compared with those based on the unsupervised data.     

Estimating fractional cover of plant functional types in African savannah from harmonic analysis of MODIS time-series data

Assessments of tree/grass fractional cover in savannahs using remote sensing are challenging due to the heterogeneous mixture of the two plant functional types. Time-series decomposition models can be used to characterize vegetation phenology from satellite data, but have rarely been used for attributing phenological signal components to different plant functional types. Here, tree/grass dynamics are assessed in savannah ecosystems using time-series decomposition of 14 years of Moderate Resolution Imaging Spectroradiometer (MODIS) normalized difference vegetation index data acquired from 2002 to 2015. The decomposition method uses harmonic analysis and tests the individual harmonic terms for statistical significance. Field data of fractional cover of trees and grasses were collected for 28 plots in Kruger National Park, South Africa. Matching MODIS pixels were analysed for their tree/grass phenological signals. Tree/grass annual and interannual variability were then assessed based on the harmonic models. In most harmonic cycles, grass-dominated sites had higher amplitudes than tree-dominated sites, while the tree green-up started earlier than grasses, before the start of the wet season. While changes in tree phenology are gradual, grasses present higher variability over time. Tree cover showed a significant correlation with the amplitude (r (correlation coefficient) = ?0.59, p = 0.001) and phase of the first harmonic term (r = ?0.73, p = 0.0001) and the number of cycles of the second harmonic term (r = 0. 56, p = 0.002). Grass cover was also significantly correlated with the amplitude (r = 0. 51, p = 0.005) and phase of the first harmonic term (r = 0.55, p = 0.002) and the number of cycles of the second harmonic term (r = ?0.52, p = 0.005). The positive correlation of grass cover with phase and negative correlation with number of cycles is indicating a late greening period and higher variability, respectively. Tree cover estimated from the phase of the strongest harmonic term showed a positive correlation with field-measured tree cover (R² (coefficient of determination) = 0.55, p < 0.01, slope = 0.93, root mean square error = 13.26%). The estimated tree cover also had a strong correlation with the woody cover map (r = 0.78, p < 0.01) produced by Bucini. The results show that MODIS time-series data can be used to estimate the fractional tree cover in heterogeneous savannahs from the phase of the plant functional type’s phenological behaviour. This study shows that harmonic analysis is able to discriminate between fractional cover by trees and grasses in savannahs. The quantitative analysis of tree/grass phenology from satellite time-series data enables a better understanding of the dynamics of the tree/grass competition and coexistence.     

Mapping canopy height using a combination of digital stereo‐photogrammetry and lidar

Ranging techniques such as lidar (LIght Detection And Ranging) and digital stereo‐photogrammetry show great promise for mapping forest canopy height. In this study, we combine these techniques to create hybrid photo‐lidar canopy height models (CHMs). First, photogrammetric digital surface models (DSMs) created using automated stereo‐matching were registered to corresponding lidar digital terrain models (DTMs). Photo‐lidar CHMs were then produced by subtracting the lidar DTM from the photogrammetric DSM. This approach opens up the possibility of retrospective mapping of forest structure using archived aerial photographs. The main objective of the study was to evaluate the accuracy of photo‐lidar CHMs by comparing them to reference lidar CHMs. The assessment revealed that stereo‐matching parameters and left–right image dissimilarities caused by sunlight and viewing geometry have a significant influence on the quality of the photo DSMs. Our study showed that photo‐lidar CHMs are well correlated to their lidar counterparts on a pixel‐wise basis (r up to 0.89 in the best stereo‐matching conditions), but have a lower resolution and accuracy. It also demonstrated that plot metrics extracted from the lidar and photo‐lidar CHMs, such as height at the 95th percentile of 20 m×20 m windows, are highly correlated (r up to 0.95 in general matching conditions).     

Object-based delineation of urban tree canopy: assessing change in Oklahoma City, 2006–2013

With a burgeoning global population, the pressures of urbanization are increasingly prevalent. The need to quantify urban greenness remains significant due to environmental impact and its relationship with human well-being. Utilizing 1 m discrete-return airborne lidar-derived digital terrain models (DTMs) and digital surface models (DSMs), aerial imagery, and lidar-imagery fusion, this study assesses vegetation, specifically tree canopy, change within Oklahoma City between 2006 and 2013. Specifically, we (1) identify an accurate object-based image analysis (OBIA) method for the detection of urban vegetation outlines, and (2) apply that method to locate and quantify vegetation change and assess spatial patterns in Oklahoma City between 2006 and 2013. The proposed OBIA approach extracts urban vegetation coverage from aerial imagery and lidar-based models with around 89% accuracy. Regarding vegetation change, Oklahoma City lost 9.69 km² (3.74 mi²) of tree canopy coverage, which accounted for a 2% loss in total greenness.     

Mapping the land-cover distribution in arid and semiarid urban landscapes with Landsat Thematic Mapper imagery

Mapping the land-cover distribution in arid and semiarid urban landscapes using medium spatial resolution imagery is especially difficult due to the mixed-pixel problem in remotely sensed data and the confusion of spectral signatures among bare soils, sparse density shrub lands, and impervious surface areas (ISAs hereafter). This article explores a hybrid method consisting of linear spectral mixture analysis (LSMA), decision tree classifier, and cluster analysis for mapping land-cover distribution in two arid and semiarid urban landscapes: Urumqi, China, and Phoenix, USA. The Landsat Thematic Mapper (TM) imagery was unmixed into four endmember fraction images (i.e. high-albedo object, low-albedo object, green vegetation (GV), and soil) using the LSMA approach. New variables from these fraction images and TM spectral bands were used to map seven land-cover classes (i.e. forest, shrub, grass, crop, bare soil, ISA, and water) using the decision tree classifier. The cluster analysis was further used to modify the classification results. QuickBird imagery in Urumqi and aerial photographs in Phoenix were used to assess classification accuracy. Overall classification accuracies of 86.0% for Urumqi and 88.7% for Phoenix were obtained, much higher accuracies than those utilizing the traditional maximum likelihood classifier (MLC). This research demonstrates the necessity of using new variables from fraction images to distinguish between ISA and bare soils and between shrub and other vegetation types. It also indicates the different effects of spatial patterns of land-cover composition in arid and semiarid landscapes on urban land-cover classification.     

Forest fuel treatment detection using multi-temporal airborne lidar data and high-resolution aerial imagery: a case study in the Sierra Nevada Mountains,California

Treatments to reduce forest fuels are often performed in forests to enhance forest health, regulate stand density, and reduce the risk of wildfires. Although commonly employed, there are concerns that these forest fuel treatments (FTs) may have negative impacts on certain wildlife species. Often FTs are planned across large landscapes, but the actual treatment extents can differ from the planned extents due to operational constraints and protection of resources (e.g. perennial streams, cultural resources, wildlife habitats). Identifying the actual extent of the treated areas is of primary importance to understand the environmental influence of FTs. Light detection and ranging (lidar) is a powerful remote-sensing tool that can provide accurate measurements of forest structures and has great potential for monitoring forest changes. This study used the canopy height model (CHM) and canopy cover (CC) products derived from multi-temporal airborne laser scanning (ALS) data to monitor forest changes following the implementation of landscape-scale FT projects. Our approach involved the combination of a pixel-wise thresholding method and an object-of-interest (OBI) segmentation method. We also investigated forest change using normalized difference vegetation index (NDVI) and standardized principal component analysis from multi-temporal high-resolution aerial imagery. The same FT detection routine was then applied to compare the capability of ALS data and aerial imagery for FT detection. Our results demonstrate that the FT detection using ALS-derived CC products produced both the highest total accuracy (93.5%) and kappa coefficient (κ) (0.70), and was more robust in identifying areas with light FTs. The accuracy using ALS-derived CHM products (the total accuracy was 91.6%, and the κ was 0.59) was significantly lower than that using ALS-derived CC, but was still higher than using aerial imagery. Moreover, we also developed and tested a method to recognize the intensity of FTs directly from pre- and post-treatment ALS point clouds.     

Modelling of spatial dynamics and biodiversity conservation on Lure mountain (France)

Our study is part of a multi-disciplinary research project aimed at stimulating debate among researchers and local managers. The central question of this multi-disciplinary research project was to better understand and manage high biodiversity value open habitats threatened with shrub encroachment and landscape closure, a common problem throughout Europe. Here, we study shrub encroachment and its impact on biodiversity conservation in Mount Ventoux, a MAB Biosphere Reserve located at the southernmost tip of the French Alps. We show how using a multi-agent modelling approach provide a valuable framework to confront two potentially conflicting conservation efforts in this mountain Mediterranean landscape, that of the within-species diversity of a tree (Abies alba, the European silver fir) and that of an endangered species (Vipera ursinii ursinii, the Orsini viper). A companion modelling approach – approach which aims at transmitting and sharing knowledge, methods and tools that help understand and strengthen the collective decision making process of stakeholders sharing a common resource – was used in order to collectively represent the main activities underway on the mountain and to have a tool to address both open landscapes rehabilitation and restoration of forest environments. The co-construction of the model allowed us to build a shared representation of the territory under study and to develop and compare alternative management scenarios with local stakeholders, both to evaluate their impact on biodiversity and to provide information for forest and grazing management practice.     

Area-based quality control of airborne laser scanning 3D models for different land classes using terrestrial laser scanning: sample survey in Houston,USA

Airborne laser scanning (ALS) is a remote-sensing technique that provides scale-accurate 3D models consisting of dense point clouds with x, y planimetric coordinates and altitude z. Using ALS, very high-resolution (VHR) digital surface models (DSMs) have been widely used for commercial and scientific applications since the early 1990s. Although there is widespread usage, there has been little comprehensive investigation of quality control for ALS DSMs in the literature, as most studies have been limited to assessing point-based vertical accuracy. This article is dedicated to investigating the quality of ALS DSMs for different land classes using statistical and visual approaches based on absolute and relative vertical accuracy metrics. Rather than a limited number of ground control points (GCP), the model-to-model-based approach is applied and DSMs derived from terrestrial laser scanning (TLS) point clouds that have around 5 mm absolute and 3 mm relative geolocation accuracy were used as the reference data for comparison. The results demonstrate that in open, grass, and building land classes, the ALS DSMs reached both standard deviation (σ) and normalized median absolute deviation (NMAD) of 3–5 cm after the elimination of any systematic biases. This result sufficiently satisfies the vertical accuracy requirements for 1/1000-scale topographic maps determined by National Digital Elevation Program (NDEP) specifications. In tall vegetation, a higher number of discrepancies larger than 0.5 m exist, reversing the relation between σ and NMAD. These vegetation errors also do not appear to be normally distributed. As an additional investigation, the performance of ALS DEMs under dense high-vegetation areas was assessed. These under-canopy ALS DEMs, created using only classified ground returns, offer both σ and NMAD of 12–14 cm, a performance level that is difficult to achieve under-canopy using photogrammetric techniques.     

Tree cover and height estimation in the Fennoscandian tundra-taiga transition zone using multiangular MISR data

The tundra-taiga transition zone stretches around the northern hemisphere separating boreal forest to the south from treeless tundra to the north. Tree cover and height are important variables to characterize this vegetation transition. Accurate continuous fields of tree cover and height would enable the delineation of the forest extent according to different criterion and provide useful data for change detection of this climatically sensitive ecotone. This study examined if multiangular remote sensing data has potential to improve the accuracy of the tree cover and height estimates in relation to nadir-view data. The satellite data consisted of Multi-angle Imaging SpectroRadiometer (MISR) data at 275 m and 1.1 km resolutions. The study area was located in the Fennoscandian tundra-taiga transition zone, in northernmost Finland. The continuous fields of tree cover and height were estimated using neural networks, which were trained and assessed by high-resolution biotope inventory data. The spectral-angular data together produced lower estimation errors than single band nadir, multispectral nadir or single band multiangular data alone. RMSE of the tree cover estimates reduced from 7.8% (relative RMSE 67.4%) to 6.5% (56.1%) at 275 m resolution, and from 5.4% (49.2%) to 4.1% (36.9%) at 1.1 km resolution, when multispectral nadir data were used together with multiangular data. RMSE of the tree height estimates reduced from 2.3 m (44.3%) to 2.0 m (37.6%) and from 1.8 m (35.4%) to 1.3 m (25.4%), respectively. The largest estimation errors occurred in mires and in areas of dense shrub cover, but the use of multiangular data also reduced estimation errors in these areas. The results suggest that directional information has potential to improve the tree cover and height estimates, and hence the accuracy of the land cover change detection in the tundra-taiga transition zone.     

Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments

Remotely sensed images and processing techniques are a primary tool for mapping changes in tropical forest types important to biodiversity and environmental assessment. Detailed land cover data are lacking for most wet tropical areas that present special challenges for data collection. For this study, we utilize decision tree (DT) classifiers to map 32 land cover types of varying ecological and economic importance over an 8000 km² study area and biological corridor in Costa Rica. We assess multivariate QUEST DTs with unbiased classification rules and linear discriminant node models for integrated vegetation mapping and change detection. Predictor variables essential to accurate land cover classification were selected using importance indices statistically derived with classification trees. A set of 35 variables from SRTM-DEM terrain variables, WorldClim grids, and Landsat TM bands were assessed.

Of the techniques examined, QUEST trees were most accurate by integrating a set of 12 spectral and geospatial predictor variables for image subsets with an overall cross-validation accuracy of 93% ± 3.3%. Accuracy with spectral variables alone was low (69% ± 3.3%). A random selection of training and test set pixels for the entire landscape yielded lower classification accuracy (81%) demonstrating a positive effect of image subsets on accuracy. A post-classification change comparison between 1986 and 2001 reveals that two lowland forest types of differing tree species composition are vulnerable to agricultural conversion. Tree plantations and successional vegetation added forest cover over the 15-year time period, but sometimes replaced native forest types, reducing floristic diversity. Decision tree classifiers, capable of combining data from multiple sources, are highly adaptable for mapping and monitoring land cover changes important to biodiversity and other ecosystem services in complex wet tropical environments.     

Estimating life-form cover fractions in California sage scrub communities using multispectral remote sensing

The California sage scrub (CSS) community type in California's Mediterranean-type ecosystems is known for its high biodiversity and is home to a large number of rare, threatened, and endangered species. Because of extensive urban development in the past fifty years, this ecologically significant community type is highly degraded and fragmented. To conserve endangered CSS communities, monitoring internal conditions of communities is as crucial as monitoring distributions of the community type in the region. Vegetation type mapping and field sampling of individual plants provide ecologically meaningful information about CSS communities such as spatial distribution and species compositions, respectively. However, both approaches only provide spatially comprehensive information but no information about internal conditions or vice versa. Therefore, there is a need for monitoring variables which fill the information gap between vegetation type maps and field-based data. A number of field-based studies indicate that life-form fractional cover is an effective indicator of CSS community health and habitat quality for CSS-obligated species. This study investigates the effectiveness of remote sensing approaches for estimating fractional cover of true shrub, subshrub, herb, and bare ground in CSS communities of southern California. Combinations of four types of multispectral imagery ranging from 0.15 m resolution scanned color infrared aerial photography to 10 m resolution SPOT 5 multispectral imagery and three image processing models - per-pixel, object-based, and spectral mixture models - were tested.An object-based image analysis (OBIA) routine consistently yielded higher accuracy than other image processing methods for estimating all cover types. Life-form cover was reliably predicted, with error magnitudes as low as 2%. Subshrub and herb cover types required finer spatial resolution imagery for more accurate predictions than true shrub and bare ground types. Positioning of sampling grids had a substantial impact on the reliability of accuracy assessment, particularly for cover estimates predicted using multiple endmember spectral mixture analysis (MESMA) applied to SPOT imagery. Of the approaches tested in this study, OBIA using pansharpened QuickBird imagery is one of the most promising approaches because of its high accuracy and processing efficiency and should be tested for more heterogeneous CSS landscapes. MESMA applied to SPOT imagery should also be examined for effectiveness in estimating factional cover over more extensive habitat areas because of its low data cost and potential for conducting retrospective studies of vegetation community conditions.     

Comparison and assessment of coarse resolution land cover maps for Northern Eurasia

Information on land cover at global and continental scales is critical for addressing a range of ecological, socioeconomic and policy questions. Global land cover maps have evolved rapidly in the last decade, but efforts to evaluate map uncertainties have been limited, especially in remote areas like Northern Eurasia. Northern Eurasia comprises a particularly diverse region covering a wide range of climate zones and ecosystems: from arctic deserts, tundra, boreal forest, and wetlands, to semi-arid steppes and the deserts of Central Asia. In this study, we assessed four of the most recent global land cover datasets: GLC-2000, GLOBCOVER, and the MODIS Collection 4 and Collection 5 Land Cover Product using cross-comparison analyses and Landsat-based reference maps distributed throughout the region. A consistent comparison of these maps was challenging because of disparities in class definitions, thematic detail, and spatial resolution. We found that the choice of sampling unit significantly influenced accuracy estimates, which indicates that comparisons of reported global map accuracies might be misleading. To minimize classification ambiguities, we devised a generalized legend based on dominant life form types (LFT) (tree, shrub, and herbaceous vegetation, barren land and water). LFT served as a necessary common denominator in the analyzed map legends, but significantly decreased the thematic detail. We found significant differences in the spatial representation of LFT's between global maps with high spatial agreement (above 0.8) concentrated in the forest belt of Northern Eurasia and low agreement (below 0.5) concentrated in the northern taiga-tundra zone, and the southern dry lands. Total pixel-level agreement between global maps and six test sites was moderate to fair (overall agreement: 0.67-0.74, Kappa: 0.41-0.52) and increased by 0.09-0.45 when only homogenous land cover types were analyzed. Low map accuracies at our tundra test site confirmed regional disagreements and difficulties of current global maps in accurately mapping shrub and herbaceous vegetation types at the biome borders of Northern Eurasia. In comparison, tree dominated vegetation classes in the forest belt of the region were accurately mapped, but were slightly overestimated (10%-20%), in all maps. Low agreement of global maps in the northern and southern vegetation transition zones of Northern Eurasia is likely to have important implications for global change research, as those areas are vulnerable to both climate and socio-economic changes.     

Performance evaluation of classification trees for building detection from aerial images and LiDAR data: a comparison of classification trees models

This study assesses the performance of three classification trees (CT) models (entropy, gain ratio and gini) for building detection by the fusion of airborne laser scanner data and multispectral aerial images. Data from four study areas with different sensors and scene characteristics were used to assess the performance of the models. The process of performance evaluation is based on four criteria: model validation and testing, classification accuracies, relative importance of input variables, as well as transferability of CT derived from one data set to another. The LiDAR point clouds were filtered to generate a digital terrain model (DTM) based on the orthogonal polynomials, and then a digital surface model (DSM) and the normalized digital surface model (nDSM) were generated. A set of 26 uncorrelated feature attributes were derived from the original aerial images, LiDAR intensity image, DSM and nDSM. Finally, the three CT models were used to classify buildings, trees, roads and ground from aerial images, LiDAR data and the generated attributes, with the most accurate average classifications of 95% being achieved. The entropy splitting algorithm proved to be a preferable algorithm for building detection from aerial images and LiDAR data.     

Use of a dark object concept and support vector machines to automate forest cover change analysis

An automated method was developed for mapping forest cover change using satellite remote sensing data sets. This multi-temporal classification method consists of a training data automation (TDA) procedure and uses the advanced support vector machines (SVM) algorithm. The TDA procedure automatically generates training data using input satellite images and existing land cover products. The derived high quality training data allow the SVM to produce reliable forest cover change products. This approach was tested in 19 study areas selected from major forest biomes across the globe. In each area a forest cover change map was produced using a pair of Landsat images acquired around 1990 and 2000. High resolution IKONOS images and independently developed reference data sets were available for evaluating the derived change products in 7 of those areas. The overall accuracy values were over 90% for 5 areas, and were 89.4% and 89.6% for the remaining two areas. The user's and producer's accuracies of the forest loss class were over 80% for all 7 study areas, demonstrating that this method is especially effective for mapping major disturbances with low commission errors. IKONOS images were also available in the remaining 12 study areas but they were either located in non-forest areas or in forest areas that did not experience forest cover change between 1990 and 2000. For those areas the IKONOS images were used to assist visual interpretation of the Landsat images in assessing the derived change products. This visual assessment revealed that for most of those areas the derived change products likely were as reliable as those in the 7 areas where accuracy assessment was conducted. The results also suggest that images acquired during leaf-off seasons should not be used in forest cover change analysis in areas where deciduous forests exist. Being highly automatic and with demonstrated capability to produce reliable change products, the TDA-SVM method should be especially useful for quantifying forest cover change over large areas.