H. Eva

Validation of the global land cover 2000 map

The Joint Research Centre of the European Commission (JRC), in partnership with 30 institutions, has produced a global land cover map for the year 2000, the GLC 2000 map. The validation of the GLC2000 product has now been completed. The accuracy assessment relied on two methods: a confidence-building method (quality control based on a comparison with ancillary data) and a quantitative accuracy assessment based on a stratified random sampling of reference data. The sample site stratification used an underlying grid of Landsat data and was based on the proportion of priority land cover classes and on the landscape complexity. A total of 1265 sample sites have been interpreted. The first results indicate an overall accuracy of 68.6%. The GLC2000 validation exercise has provided important experiences. The design-based inference conforms to the CEOS Cal-Val recommendations and has proven to be successful. Both the GLC2000 legend development and reference data interpretations used the FAO Land Cover Classification System (LCCS). Problems in the validation process were identified for areas with heterogeneous land cover. This issue appears in both in the GLC2000 (neighborhood pixel variations) and in the reference data (cartographic and thematic mixed units). Another interesting outcome of the GLC2000 validation is the accuracy reporting. Error statistics are provided from both the producer and user perspective and incorporates measures of thematic similarity between land cover classes derived from LCCS

Tropical forest cover monitoring: Estimates from the GRFM JERS-1 radar mosaics using wavelet zooming techniques and validation

The usefulness of the Global Rain Forest Mapping (GRFM) radar mosaics over South America for tropical forest mapping is assessed in quantitative terms. Estimates of the forest cover are derived from the GRFM mosaic over three test sites that are representative of different fragmentation patterns in Amazonia. Since classical clustering techniques are ill-suited for the GRFM dataset, a novel unsupervised segmentation technique, based on a wavelet frame that acts as a differential operator, is proposed. Validation of the radar-derived estimates is obtained using as reference data thematic maps derived from Landsat Thematic Mapper (TM). The classification accuracy, measured by confusion matrices between the radar and optical derived estimates, are found to be proportional to the landscape spatial fragmentation index. The results from the wavelet classifier are compared with those from classical ISODATA algorithm, and the improvement in accuracy given by the new method is found to be statistically significant. Also the source of omission and commission errors of the radar classification with respect to the reference TM data is discussed. A method based on mapping spatially the confusion between classes is used for the purpose. The study indicates that, within the stated accuracy limit and within the thematic context of tropical forest cover mapping, the GRFM radar mosaics offer with respect to optical data a viable alternative source of information, which however is potentially more powerful for upscaling of the results to continental scale due to the all weather capability of the radar instruments.

A novel approach to the classification of regional-scale Radar mosaics for tropical vegetation mapping

The Global Rain Forest Mapping (GRFM) radar mosaics, generated from L-band Japanese Earth Resources Satellite 1 imagery downsampled to 100-m pixel size, provide a two-season spatially continuous coverage of the humid tropical ecosystems of the world. This paper presents a novel classification approach suitable for regional-scale vegetation mapping using the GRFM datasets. The mapping system consists of: 1) an application-dependent wavelet-based edge-preserving smoothing algorithm and 2) a two-stage per-pixel hybrid learning nearest multiple-prototype (NMP) classifier, whose unsupervised first stage is a per-pixel near-optimal vector quantizer, called enhanced Linde-Buzo-Gray (ELBG), recently proposed in pattern recognition literature. Identified as ENMP (NMP with ELBG), this novel classification approach is compared against two alternative systems in the classification of forest cover disturbances located across an area in the Amazon Basin. Surface classes of interest are primary forest, degraded forest, nonforest, and water bodies. Reference maps, derived from 30-m resolution Landsat Thematic Mapper imagery, are provided by the National Aeronautics and Space Administration and the Food and Agriculture Organization of the United Nations. Abundant quantitative and qualitative evidence shows that: 1) in a forest/nonforest data-mapping task, ENMP provides a testing accuracy of 87%, in line with training accuracies, i.e., the proposed method seems capable of generalizing well over the GRFM South America dataset and 2) among three competing approaches, ENMP provides the best compromise between ease of use, mapping accuracy, and computational time. Starting from these results, ENMP is employed to generate a swamp forest map of the whole Amazon Basin from the two-season GRFM radar mosaic of South America, in the context of the Global Land Cover project (GLC 2000).

Contextual clustering for image labeling: an application to degraded forest assessment in Landsat TM images of the Brazilian Amazon

The modified adaptive pappas clustering (MPAC) algorithm, previously published in the image processing literature, is proposed as a valuable tool in the analysis of remotely sensed images where texture information is negligible. Owing to its contextual, adaptive, and multiresolutional labeling approach, MPAC preserves genuine but small regions, is easy to use (i.e., it requires minor user interaction to run), and is robust to changes in input parameters. As an application example, an MPAC-based three-stage classifier is applied to degraded forest detection in Landsat Thematic Mapper (TM) scenes of the Brazilian Amazon, where intermediate states of forest alterations caused by anthropogenic activities can be characterized by image structures 1-3 pixels wide. In three TM images of the Para test site, where classification results are validated by means of qualitative and quantitative comparisons with aerial photos, degraded forest areas cover 13% to 45% of the image ground coverage. In the Mato Grosso test site, the degraded forest class overlaps with 1) 10% of the closed-canopy forest detected by the deforestation mapping program of the Food and Agriculture Organization (FAO, 1992), and 2) 19% of the closed-canopy forest detected by the Tropical Rain Forest Information Center (TRFIC, 1996). These figures are in line with the conclusions of a study where present estimates of annual deforestation for the Brazilian Amazon are speculated to capture less than half of the forest area that is actually impoverished each year.

Remote Sensing of Land-Cover and Land-Use Dynamics

Land is changing at a rate never achieved before. This evolution needs to be documented by robust and repeatable figures. Earth Observation tools play a key-role in the production of regular estimates of the landscape changes. In this chapter, we discuss the utility of Remote Sensing data for producing information on land-cover and on land-cover/land-use changes. Basic guidelines in terms of legend, data acquisition, classification techniques and validation are explained. For illustrating global land-cover projects, the recent Global Land Cover 2000 project is described.

Detecting Intact Forests from Space: Hot Spots of Loss, Deforestation and the UNFCCC

This chapter aims to synthesise what is known about areas of rapid loss of forest in the tropics and boreal Eurasia from the 1990s onwards, based on data compiled from expert opinion and Earth observation technology. During the 1990s, forest-cover changes were much more frequent in the tropics than in other parts of the world. In particular, the Amazon basin and Southeast Asia contain a concentration of deforestation hotspots. Forest degradation in Eurasia, related mostly to unsustainable logging activities or increase in fire frequency, has been growing in recent years. The Greenpeace map of the world’s intact forests for the year 2000 depicts the remaining large forest areas, which usually contain high fractions of old-growth forest. Although rates of forest cover changes are now better assessed, uncertainties still exist about the rate of change in intact forest areas.

Use of data from the VEGETATION instrument for global environmental monitoring: some lessons from the GLC 2000 and the GBA 2000 projects

Daily global mosaics of data acquired by the VEGETATION instrument onboard the SPOT 4 between Nov. 1st, 1999 and Dec. 31st, 2000 have been used to produce a reference high quality global land cover map (GLC 2000) and the global survey of burned surfaces (GBA 2000). These products have been generated through an international partnership coordinated by the Joint Research Centre and are now freely available to users. This paper reviews briefly the results achieved and provides an assessment of the specific properties of the VEGETATION data for land cover and burn scar mapping at continental to global scales.

High-resolution tropical forest mapping of the Amazon basin: a novel classification approach for the GRFM radar mosaic

The high resolution (100 m) Global Rain Forest Mapping (GRFM) radar mosaics, providing a spatially continuous coverage of entire ecosystems, pave the way to improved estimates of bio-physical parameters related to the tropical vegetation. A new classification scheme for producing a high-resolution regional scale forest/non-forest thematic map of the Amazon is proposed. First, a new wavelet multi-resolution decomposition/reconstruction technique is employed to generate an edge-preserving piecewise constant approximation of the original radar image. Second, a two-stage hybrid learning Nearest Multiple-Prototype (NMP) classifier is applied to the reconstructed radar image. The NMP first stage employs a near-optimal vector quantization algorithm called Enhanced Linde-Buzo-Gray (ELBG). During the training phase, ELBG employs only 1% of the whole data set. At the second stage of NMP, vector prototypes are combined into land cover classes of interest by an expert photo-interpreter. In the pattern recognition phase, each pixel is labeled according to the minimum-distance-to-prototype criterion. Experimental results are reported for a thematic problem involving classes: primary forest, degraded forest, non-forest, and water bodies. Validation is performed using land cover maps provided by the Tropical Rain Forest Information Center (TRIFIC) over three test sites featuring different forest cover disturbance patterns. Main results are that the proposed classifier (i) provides a classification accuracy of 87% in forest/non-forest mapping, (ii) is capable of generalizing over the entire data set, and (iii) requires minor user interaction. It is concluded that the proposed approach responds adequately to the requirements of regional scale high-resolution vegetation mapping.