Validation and comparison of 1 km global land cover products in China

Four 1 km global land cover products are currently available to the scientific community: the University of Maryland (UMD) global land cover product, the International Geosphere–Biosphere Programme Data and Information System Cover (IGBP‐DISCover), the MODerate resolution Imaging Spectrometer (MODIS) global land cover product and Global Land Cover 2000 (GLC2000). Because of differences in data sources, temporal scales, classification systems and methodologies, it is important to compare and validate these global maps before using them for a variety of studies at regional to global scales. This study aimed to perform the validation and comparison of the four global land cover datasets, and to examine the suitability and accuracy of different coarse spatial resolution datasets in mapping and monitoring cropland across China. To meet this objective, we compared the four global land cover products with the National Land Cover Dataset 2000 (NLCD‐2000) at three scales to evaluate the accuracy of estimates of aggregated cropland areas in China. This was followed by a spatial comparison to assess the accuracies of the four products in estimating the spatial distribution of cropland across China. A comparative analysis showed that there are varying levels of apparent discrepancies in estimating the cropland of China between these four global land cover datasets, and that both area totals and spatial (dis)agreement between them vary from region to region. Among these, the MODIS dataset has the best fit in depicting China's croplands. The coarse spatial resolution and the per pixel classification approach, as well as landscape heterogeneity, are the main reasons for the large discrepancies between the global land cover datasets tested and the reference data.     

NDVI-derived land cover classifications at a global scale

Phenological differences among vegetation types, reflected in temporal variations in the Normalized Difference Vegetation Index (NDVI) derived from satellite data, have been used to classify land cover at continental scales. Extending this technique to global scales raises several issues: identifying land cover types that are spectrally distinct and applicable at the global scale; accounting for phasing of seasons in different parts of the world; validating results in the absence of reliable information on global land cover; and acquiring high quality global data sets of satellite sensor data for input to land cover classifications. For this study, a coarse spatial resolution (one by one degree) data set of monthly NDVI values for 1987 was used to explore these methodological issues. A result of a supervised, maximum likelihood classification of eleven cover types is presented to illustrate the feasibility of using satellite sensor data to increase the accuracy of global land cover information, although the result has not been validated systematically. Satellite sensor data at finer spatial resolutions that include other bands in addition to NDVI, as well as methodologies to better identify and describe gradients between cover types, could increase the accuracy of results of global land cover data sets derived from satellite sensor data.     

Land cover classification with coarse spatial resolution data to derive continuous and discrete maps for complex regions

Regularly updated land cover information at continental or national scales is a requirement for various land management applications as well as biogeochemical and climate modeling exercises. However, monitoring or updating of map products with sufficient spatial detail is currently not widely practiced due to inadequate time-series coverage for most regions of the Earth. Classifications of coarser spatial resolution data can be automatically generated on an annual or finer time scale. However, discrete land cover classifications of such data cannot sufficiently quantify land surface heterogeneity or change. This study presents a methodology for continuous and discrete land cover mapping using moderate spatial resolution time series data sets. The method automatically selects sample data from higher spatial resolution maps and generates multiple decision trees. The leaves of decision trees are interpreted considering the sample distribution of all classes yielding class membership maps, which can be used as estimates for the diversity of classes in a coarse resolution cell. Results are demonstrated for the heterogeneous, small-patch landscape of Germany and the bio-climatically varying landscape of South Africa. Results have overall classification accuracies of 80%. A sensitivity analysis of individual modules of the classification process indicates the importance of appropriately chosen features, sample data balanced among classes, and an appropriate method to combine individual classifications. The comparison of classification results over several years not only indicates the method's consistency, but also its potential to detect land cover changes.     

全球环境变化视角下的土地覆盖分类系统研究综述

全球环境变化需要精确和最新的区域到全球尺度的土地覆盖数据集以支撑生态系统评估、生物多样性保护、气候变化研究和环境建模。然而,在土地覆盖分类数据集建立过程中,建立科学标准的分类系统至关重要,它影响着数据产品的集成与共享,数据的应用领域与范围。通过对区域尺度、全球尺度及可扩展的FAO土地覆盖分类系统进行评述,指出：① 目前国内外没有普遍认可并广泛应用的标准土地覆盖分类系统,这种分类系统的非标准化影响了数据产品的应用以及对土地覆盖变化的监测;② 复合特征是土地覆盖的固有属性,有效地表达与特征量化复合类型是需要不断努力去解决的问题;③ 我国迫切需要建立一套标准的土地覆盖分类系统,一方面能够与国际土地覆盖产品接轨,另一方面充分体现我国的自然环境特征。     

A comparative analysis of the Global Land Cover 2000 and MODIS land cover data sets

Accurate and up-to-date global land cover data sets are necessary for various global change research studies including climate change, biodiversity conservation, ecosystem assessment, and environmental modeling. In recent years, substantial advancement has been achieved in generating such data products. Yet, we are far from producing geospatially consistent high-quality data at an operational level. We compared the recently available Global Land Cover 2000 (GLC-2000) and MODerate resolution Imaging Spectrometer (MODIS) global land cover data to evaluate the similarities and differences in methodologies and results, and to identify areas of spatial agreement and disagreement. These two global land cover data sets were prepared using different data sources, classification systems, and methodologies, but using the same spatial resolution (i.e., 1 km) satellite data. Our analysis shows a general agreement at the class aggregate level except for savannas/shrublands, and wetlands. The disagreement, however, increases when comparing detailed land cover classes. Similarly, percent agreement between the two data sets was found to be highly variable among biomes. The identified areas of spatial agreement and disagreement will be useful for both data producers and users. Data producers may use the areas of spatial agreement for training area selection and pay special attention to areas of disagreement for further improvement in future land cover characterization and mapping. Users can conveniently use the findings in the areas of agreement, whereas users might need to verify the informaiton in the areas of disagreement with the help of secondary information. Learning from past experience and building on the existing infrastructure (e.g., regional networks), further research is necessary to (1) reduce ambiguity in land cover definitions, (2) increase availability of improved spatial, spectral, radiometric, and geometric resolution satellite data, and (3) develop advanced classification algorithms.     

Tropical forest mapping from coarse spatial resolution satellite data: Production and accuracy assessment issues

Global to regional datasets from coarse spatial resolution satellite sensors are increasingly becoming available. Land cover and vegetation extent maps are among the terrestrial products derived from such data. Whilst they provide a previously unavailable synoptic view of global situations, accuracy assessment methodological issues are often ignored when creating these digital databases or producing statistics from such sources. This paper looks at how these issues are addressed in the framework of the Joint Research Centre's TREES (Tropical Ecosystem Environment observation by Satellite) project, initiated to map and monitor the pan-tropical humid forest belt using Advanced Very High Resolution Radiometer (AVHRR) data. The paper shows that without accuracy assessment and a correction procedure, both the thematic legend and statistical data derived from coarse spatial maps can be misleading.     

Evaluation of MODIS gross primary productivity and land cover products for the humid tropics using oil palm trees in Peninsular Malaysia and Google Earth imagery

Conducting quantitative studies on the carbon balance or productivity of oil palm is important in understanding the role of this ecosystem in global climate change. In this study, we evaluated the accuracy of MODIS (Moderate Resolution Imaging Spectroradiometer) annual gross primary productivity (GPP) (the product termed MOD-17) and its upstream products, especially the MODIS land cover product (the product termed MOD-12). We used high-resolution Google Earth images to classify the land cover classes and their percentage cover within each 1 km spatial resolution MODIS pixel. We used field-based annual GPP for 2006 to estimate GPP for each pixel based on percentage cover. Both land cover and GPP were then compared to MODIS land cover and GPP products. The results show that for pure pixels that are 100% covered by mature oil palm trees, the RMSE (root mean square error) between MODIS and field-based annual GPP is 18%, and that this is increased to 27% for pixels containing mostly oil palm. Overall, for an area of about 42 km² the RMSE is 26%. We conclude that land cover classification (at 1 km resolution) is one of the main factors for the discrepancy between MODIS and field-based GPP. We also conclude that the accuracy of the MODIS GPP product could be improved significantly by using higher-resolution land cover maps.     

Super-resolution land cover mapping with indicator geostatistics

Many satellite images have a coarser spatial resolution than the extent of land cover patterns on the ground, leading to mixed pixels whose composite spectral response consists of responses from multiple land cover classes. Spectral unmixing procedures only determine the fractions of such classes within a coarse pixel without locating them in space. Super-resolution or sub-pixel mapping aims at providing a fine resolution map of class labels, one that displays realistic spatial structure (without artifact discontinuities) and reproduces the coarse resolution fractions. In this paper, existing approaches for super-resolution mapping are placed within an inverse problem framework, and a geostatistical method is proposed for generating alternative synthetic land cover maps at the fine (target) spatial resolution; these super-resolution realizations are consistent with all the information available.More precisely, indicator coKriging is used to approximate the probability that a pixel at the fine spatial resolution belongs to a particular class, given the coarse resolution fractions and (if available) a sparse set of class labels at some informed fine pixels. Such Kriging-derived probabilities are used in sequential indicator simulation to generate synthetic maps of class labels at the fine resolution pixels. This non-iterative and fast simulation procedure yields alternative super-resolution land cover maps that reproduce: (i) the observed coarse fractions, (ii) the fine resolution class labels that might be available, and (iii) the prior structural information encapsulated in a set of indicator variogram models at the fine resolution. A case study is provided to illustrate the proposed methodology using Landsat TM data from SE China.     

Sources of error in accuracy assessment of thematic land-cover maps in the Brazilian Amazon

Valid measures of map accuracy are critical, yet can be inaccurate even when following well-established procedures. Accuracy assessment is particularly problematic when thematic classes lie along a land-cover continuum, and boundaries between classes are ambiguous. In this study, we examined error sources introduced during accuracy assessment of a regional land-cover map generated from Landsat Thematic Mapper (TM) data in Rondônia, southwestern Brazil. In this dynamic, highly fragmented landscape, the dominant land-cover classes represent a continuum from pasture to second growth to primary forest. We used high spatial resolution, geocoded videography as a reference, and focused on second-growth forest because of its potential contribution to the regional carbon balance. To quantify subjectivity in reference data labeling, we compared reference data produced by five trained interpreters. We also quantified the impact of other error sources, including geolocation errors between the map and reference data, land-cover changes between dates of data collection, heterogeneous reference samples, and edge pixels.Interpreters disagreed on classification of almost 30% of the samples; mixed reference samples and samples located in transitional classes accounted for a majority of disagreements. Agreement on second-growth forest labels between any two interpreters averaged below 50%, while agreement on primary forest was over 90%. Greater than 30% of disagreement between map and reference data was attributed to geolocation error, and 2.4% of disagreement was attributed to change in land cover between dates. After geocorrection, 24% of remaining disagreements corresponded to reference samples with mixed land cover, and 47% corresponded to edge pixels on the classified map. These findings suggest that: (1) labels of continuous land-cover types are more subjective and variable than commonly assumed, especially for transitional classes; however, using multiple interpreters to produce the reference data classification increases reference data accuracy; and (2) validation data sets that include only non-mixed, non-edge samples are likely to result in overly optimistic accuracy estimates, not representative of the map as a whole. These results suggest that different regional estimates of second-growth extent may be inaccurate and difficult to compare.     

Super resolution land cover mapping of hyperspectral images using the deep image prior-based approach

ABSTRACT

Due to the instantaneous field-of-view (IFOV) of the sensor and diversity of land cover types, some pixels, usually named mixed pixels, contain more than one land cover type. Soft classification can predict the portion of each land cover type in mixed pixels in the absence of spatial distribution. The spatial distribution information in mixed pixels can be solved by super resolution mapping (SRM). Typically, SRM involves two steps: soft class value estimation, which is similar to the image super resolution of image restoration, and land cover allocation. A new SRM approach utilizes a deep image prior (DIP) strategy combined with a super resolution convolutional neural network (SRCNN) to estimate fine resolution fraction images for each land cover type; then, a simple and efficient classifier is used to allocate subpixel land cover types under the constraint of the generated fine fraction images. The proposed approach can use prior information of input images to update network parameters and no longer require training data. Experiments on three different cases demonstrate that the subpixel classification accuracy of the proposed DIP-based SRM approach is significantly better than the three conventional SRM approaches and a transfer learning-based neural network SRM approach. In addition, the DIP-SRM approach performs very robustly about small-area objects within multiple land cover types and significantly reduces soft classification uncertainty. The results of this paper provide an extension for utilizing SRCNN to address SRM issues in hyperspectral images.     

MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets

Information related to land cover is immensely important to global change science. In the past decade, data sources and methodologies for creating global land cover maps from remote sensing have evolved rapidly. Here we describe the datasets and algorithms used to create the Collection 5 MODIS Global Land Cover Type product, which is substantially changed relative to Collection 4. In addition to using updated input data, the algorithm and ancillary datasets used to produce the product have been refined. Most importantly, the Collection 5 product is generated at 500-m spatial resolution, providing a four-fold increase in spatial resolution relative to the previous version. In addition, many components of the classification algorithm have been changed. The training site database has been revised, land surface temperature is now included as an input feature, and ancillary datasets used in post-processing of ensemble decision tree results have been updated. Further, methods used to correct classifier results for bias imposed by training data properties have been refined, techniques used to fuse ancillary data based on spatially varying prior probabilities have been revised, and a variety of methods have been developed to address limitations of the algorithm for the urban, wetland, and deciduous needleleaf classes. Finally, techniques used to stabilize classification results across years have been developed and implemented to reduce year-to-year variation in land cover labels not associated with land cover change. Results from a cross-validation analysis indicate that the overall accuracy of the product is about 75% correctly classified, but that the range in class-specific accuracies is large. Comparison of Collection 5 maps with Collection 4 results show substantial differences arising from increased spatial resolution and changes in the input data and classification algorithm.     

Using short-term MODIS time-series to quantify tree cover in a highly heterogeneous African savanna

Reliable mapping of tree cover and tree-cover change at regional, continental, and global scales is critical for understanding key aspects of ecosystem structure and function. In savannas, which are characterized by a variable mixture of trees and grasses, mapping tree cover can be especially challenging due to the highly heterogeneous nature of these ecosystems. Our objective in this article was to develop improved tools for large-scale classification of savanna tree cover in grass-dominated savanna ecosystems that vary substantially in woody cover over fine spatial scales. We used multispectral, low-resolution Moderate Resolution Imaging Spectroradiometer (MODIS) satellite imagery to identify the bands and metrics that are best suited to quantify woody cover in an area of the Serengeti National Park, Tanzania. We first used 1-m resolution panchromatic IKONOS data to quantify tree cover for February 2010 in an area of highly variable tree cover. We then upscaled the classification to MODIS (250 m) resolution. We used a 2 year time series (IKONOS date ± 1 year) of MODIS 16 day composites to identify suitable metrics for quantifying tree cover at low resolution, and calculated and compared the explanatory power of three different variable classes for four MODIS bands using Lasso regression: longitudinal summary statistics for individual spectral bands (e.g. mean and standard deviation), Fourier harmonics, and normalized difference vegetation index (NDVI) green-up metrics. Longitudinal summary statistics showed better explanatory power (R ² = 73% for calibration data; R ² = 61% for validation data) than Fourier or green-up metrics. The mid-infrared, near-infrared, and NDVI bands were all important predictors of tree cover. Mean values for the time series were more important than other metrics, suggesting that multispectral data may be more valuable than within-band seasonal variation obtained from time series data for mapping tree cover. Our best model improved substantially over the MODIS Vegetation Continuous Fields product, often used for quantifying tree cover in savanna systems. Quantifying tree cover at coarse spatial resolution using remote-sensing approaches is challenging due to the low amount and high heterogeneity of tree cover in many savanna systems, and our results suggest that products that work well at global scales may be inadequate for low-tree-cover systems such as the Serengeti. We show here that, even in situations where tree cover is low (<10%) and varies considerably across space, satisfactory predictive power is possible when broad spectral data can be obtained even at coarse spatial resolution.     

Decision tree regression for soft classification of remote sensing data

In recent years, decision tree classifiers have been successfully used for land cover classification from remote sensing data. Their implementation as a per-pixel based classifier to produce hard or crisp classification has been reported in the literature. Remote sensing images, particularly at coarse spatial resolutions, are contaminated with mixed pixels that contain more than one class on the ground. The per-pixel approach may result in erroneous classification of images dominated by mixed pixels. Therefore, soft classification approaches that decompose the pixel into its class constituents in the form of class proportions have been advocated. In this paper, we employ a decision tree regression approach to determine class proportions within a pixel so as to produce soft classification from remote sensing data. Classification accuracy achieved by decision tree regression is compared with those achieved by the most widely used maximum likelihood classifier, implemented in the soft mode, and a supervised version of the fuzzy c-means classifier. Root Mean Square Error (RMSE) and fuzzy error matrix based measures have been used for accuracy assessment of soft classification.     

Evaluation of MK-4 multispectral satellite photography in land cover classification of eastern Ontario

Russian MK-4 multispectral satellite photography has been investigated for potential in land cover classification. Thematic maps were generated using maximum likelihood, neural network and context classifiers. Classifications of the raw spectral data, of spectral transforms, and of combined spectral/textural data were evaluated. Low point-based class accuracies resulted for land cover types exhibiting high spatial variability at the given pixel spacing of 7.5m, while more spatially homogeneous cover types were well classified. Several issues arose which need to be addressed for effective future use of high-resolution satellite sensors in regional land cover mapping. They include the need for further research in techniques for classification and accuracy assessment which are sensitive to the spatial variance of such high resolution imagery, and optimization of class attribute definitions.     

Improving global scale land cover classifications with multi-directional POLDER data and a decision tree classifier

Several investigations indicate that the Bidirectional Reflectance Distribution Function (BRDF) contains information that can be used to complement spectral information for improved land cover classification accuracies. Prior studies on the addition of BRDF information to improve land cover classifications have been conducted primarily at local or regional scales. Thus, the potential benefits of adding BRDF information to improve global to continental scale land cover classification have not yet been explored. Here we examine the impact of multidirectional global scale data from the first Polarization and Directionality of Earth Reflectances (POLDER) spacecraft instrument flown on the Advanced Earth Observing Satellite (ADEOS-1) platform on overall classification accuracy and per-class accuracies for 15 land cover categories specified by the International Geosphere Biosphere Programme (IGBP).

A set of 36,648 global training pixels (7 × 6 km spatial resolution) was used with a decision tree classifier to evaluate the performance of classifying POLDER data with and without the inclusion of BRDF information. BRDF ‘metrics’ for the eight-month POLDER on ADEOS-1 archive (10/1996–06/1997) were developed that describe the temporal evolution of the BRDF as captured by a semi-empirical BRDF model. The concept of BRDF ‘feature space’ is introduced and used to explore and exploit the bidirectional information content. The C5.0 decision tree classifier was applied with a boosting option, with the temporal metrics for spectral albedo as input for a first test, and with spectral albedo and BRDF metrics for a second test. Results were evaluated against 20 random subsets of the training data.

Examination of the BRDF feature space indicates that coarse scale BRDF coefficients from POLDER provide information on land cover that is different from the spectral and temporal information of the imagery. The contribution of BRDF information to reducing classification errors is also demonstrated: the addition of BRDF metrics reduces the mean, overall classification error rates by 3.15% (from 18.1% to 14.95% error) with larger improvements for producer's accuracies of individual classes such as Grasslands (+ 8.71%), Urban areas (+ 8.02%), and Wetlands (+ 7.82%). User's accuracies for the Urban (+ 7.42%) and Evergreen Broadleaf Forest (+ 6.70%) classes are also increased. The methodology and results are widely applicable to current multidirectional satellite data from the Multi-angle Imaging Spectroradiometer (MISR), and to the next generation of POLDER-like multi-directional instruments.     

基于时序MODIS反射率产品统计检验方法的土地覆盖更新

土地覆盖产品的生产是遥感领域的研究热点。全球范围土地覆盖产品因其在空间范围上的巨大尺度,生产周期较长,因此产品的时间跨度也很大,需要具有与之相对应的快速生成与更新技术,以提高产品的时间分辨率。使用MODIS历史土地覆盖产品和反射率产品,采用平均值显著性统计检验的思想,实现土地覆盖产品的快速更新。在MODIS条带号为h26v05的结果中选取宁夏自治区作为检验样区,通过目视检验和精度评价的方法对土地覆盖更新结果进行检验,总体精度为90.0290%。对水、混交林、草原、城市和建成区、裸地或低植被覆盖地变化的趋势和变化原因进行分析论证,表明采用平均值显著性统计检验的思想使用时序反射率产品对土地覆盖产品进行自动化快速更新是可行的。     

Mapping regional land cover with MODIS data for biological conservation: Examples from the Greater Yellowstone Ecosystem, USA and Pará State, Brazil

The paper investigated the application of MODIS data for mapping regional land cover at moderate resolutions (250 and 500 m), for regional conservation purposes. Land cover maps were generated for two major conservation areas (Greater Yellowstone Ecosystem—GYE, USA and the Pará State, Brazil) using MODIS data and decision tree classifications. The MODIS land cover products were evaluated using existing Landsat TM land cover maps as reference data. The Landsat TM land cover maps were processed to their fractional composition at the MODIS resolution (250 and 500 m). In GYE, the MODIS land cover was very successful at mapping extensive cover types (e.g. coniferous forest and grasslands) and far less successful at mapping smaller habitats (e.g. wetlands, deciduous tree cover) that typically occur in patches that are smaller than the MODIS pixels, but are reported to be very important to biodiversity conservation. The MODIS classification for Pará State was successful at producing a regional forest/non-forest product which is useful for monitoring the extreme human impacts such as deforestation. The ability of MODIS data to map secondary forest remains to be tested, since regrowth typically harbors reduced levels of biodiversity. The two case studies showed the value of using multi-date 250 m data with only two spectral bands, as well as single day 500 m data with seven spectral bands, thus illustrating the versatile use of MODIS data in two contrasting environments. MODIS data provide new options for regional land cover mapping that are less labor-intensive than Landsat and have higher resolution than previous 1 km AVHRR or the current 1 km global land cover product. The usefulness of the MODIS data in addressing biodiversity conservation questions will ultimately depend upon the patch sizes of important habitats and the land cover transformations that threaten them.     

Thematic accuracy of the National Land Cover Database (NLCD) 2001 land cover for Alaska

The National Land Cover Database (NLCD) 2001 Alaska land cover classification is the first 30-m resolution land cover product available covering the entire state of Alaska. The accuracy assessment of the NLCD 2001 Alaska land cover classification employed a geographically stratified three-stage sampling design to select the reference sample of pixels. Reference land cover class labels were determined via fixed wing aircraft, as the high resolution imagery used for determining the reference land cover classification in the conterminous U.S. was not available for most of Alaska. Overall thematic accuracy for the Alaska NLCD was 76.2% (s.e. 2.8%) at Level II (12 classes evaluated) and 83.9% (s.e. 2.1%) at Level I (6 classes evaluated) when agreement was defined as a match between the map class and either the primary or alternate reference class label. When agreement was defined as a match between the map class and primary reference label only, overall accuracy was 59.4% at Level II and 69.3% at Level I. The majority of classification errors occurred at Level I of the classification hierarchy (i.e., misclassifications were generally to a different Level I class, not to a Level II class within the same Level I class). Classification accuracy was higher for more abundant land cover classes and for pixels located in the interior of homogeneous land cover patches.     

Validation of a large area land cover product using purpose-acquired airborne video

Large area land cover products generated from remotely sensed data are difficult to validate in a timely and cost effective manner. As a result, pre-existing data are often used for validation. Temporal, spatial, and attribute differences between the land cover product and pre-existing validation data can result in inconclusive depictions of map accuracy. This approach may therefore misrepresent the true accuracy of the land cover product, as well as the accuracy of the validation data, which is not assumed to be without error. Hence, purpose-acquired validation data is preferred; however, logistical constraints often preclude its use — especially for large area land cover products. Airborne digital video provides a cost-effective tool for collecting purpose-acquired validation data over large areas. An operational trial was conducted, involving the collection of airborne video for the validation of a 31,000 km² sub-sample of the Canadian large area Earth Observation for Sustainable Development of Forests (EOSD) land cover map (Vancouver Island, British Columbia, Canada). In this trial, one form of agreement between the EOSD product and the airborne video data was defined as a match between the mode land cover class of a 3 by 3 pixel neighbourhood surrounding the sample pixel and the primary or secondary choice of land cover for the interpreted video. This scenario produced the highest level of overall accuracy at 77% for level 4 of classification hierarchy (13 classes). The coniferous treed class, which represented 71% of Vancouver Island, had an estimated user's accuracy of 86%. Purpose acquired video was found to be a useful and cost-effective data source for validation of the EOSD land cover product. The impact of using multiple interpreters was also tested and documented. Improvements to the sampling and response designs that emerged from this trial will benefit a full-scale accuracy assessment of the EOSD product and also provides insights for other regional and global land cover mapping programs.     

Global land cover classification at 1 km spatial resolution using a classification tree approach

This paper on reports the production of a 1 km spatial resolution land cover classification using data for 1992-1993 from the Advanced Very High Resolution Radiometer (AVHRR). This map will be included as an at-launch product of the Moderate Resolution Imaging Spectroradiometer (MODIS) to serve as an input for several algorithms requiring knowledge of land cover type. The methodology was derived from a similar effort to create a product at 8 km spatial resolution, where high resolution data sets were interpreted in order to derive a coarse-resolution training data set. A set of 37 294 x 1 km pixels was used within a hierarchical tree structure to classify the AVHRR data into 12 classes. The approach taken involved a hierarchy of pair-wise class trees where a logic based on vegetation form was applied until all classes were depicted. Multitemporal AVHRR metrics were used to predict class memberships. Minimum annual red reflectance, peak annual Normalized Difference Vegetation Index (NDVI), and minimum channel three brightness temperature were among the most used metrics. Depictions of forests and woodlands, and areas of mechanized agriculture are in general agreement with other sources of information, while classes such as low biomass agriculture and high-latitude broadleaf forest are not. Comparisons of the final product with regional digital land cover maps derived from high-resolution remotely sensed data reveal general agreement, except for apparently poor depictions of temperate pastures within areas of agriculture. Distinguishing between forest and non-forest was achieved with agreements ranging from 81 to 92% for these regional subsets. The agreements for all classes varied from an average of 65% when viewing all pixels to an average of 82% when viewing only those 1 km pixels consisting of greater than 90% one class within the high-resolution data sets.