Systematic and random transitions of land-cover types in Burkina Faso,West Africa

In-depth statistical analysis of forest transition between land-cover types over time can reveal the dominant signals of landscape transformation, which are needed in order to develop appropriate land management strategies. We applied a recently developed methodology to analyse the transition matrix of six land-cover classes, derived from 1986 and 2002 Landsat images of an area of 15?675 km² in southern Burkina Faso. Results show that most landscape transformations followed a systematic process. In addition, some transitions occurred as an apparently random process, probably caused by uncommon or sporadic events. Degradation of woodland to shrub-/grassland over 15.7% of the landscape, increases in biomass from woodland to dense forest on 10% of the landscape and conversion of 6% of the landscape from shrub-/grassland to cropland were the dominant signals of forest-cover transitions. From a planning perspective, the dominance of systematic processes should facilitate regional land-use planning and sustainable forest management in a context of immigration and agricultural intensification.     

基于随机森林的遥感土地利用分类及景观格局分析

2009年福建平潭综合实验区设立,作为闽台合作及国家对外开放的窗口,其土地利用变化主要受社会经济因素的影响和自然地理环境的制约,也与未来的土地利用规划密切相关.本文利用1990、2000、2010和2017年4期Landsat遥感影像数据,定量分析近27年的土地利用变化对景观格局的影响.结果表明:(1)在选择合适训练样本的情况下,利用随机森林方法可获得较高的遥感土地利用分类精度(4期遥感影像分类的总体精度均在87%以上,Kappa系数均在0.84以上);(2)1990~2017年,水域面积急剧减少31.04 km2,流失的水域主要转化为建设用地和林地;建设用地增加40.98 km2,年平均增长1.52 km2.近十年呈快速增长趋势,年平均增长3.87 km2;(3)在斑块类型级别上,逐年增加的建设用地导致最大斑块占景观面积比例(LPI)、聚合度(AI)和边缘密度(ED)呈上升趋势,其中LPI受到建设用地增加的影响最显著.在景观类型级别上,多样性(SHDI)和景观形状(LSI)呈下降趋势.     

Land-use change analysis in Yulin prefecture,northwestern China using remote sensing and GIS

Rapid land-use change has taken place in many arid and semi-arid regions of China such as Yulin prefecture over the last decade due to rehabilitation measures. In this paper, land-use change dynamics were investigated by the combined use of satellite remote sensing and geographical information systems (GIS). Our objectives were to determine land-use transition rates among land-use types in Yulin prefecture over 14 years from 1986-2000 and to quantify the changes of various landscape metrics using FRAGSTATS, the spatial pattern analysis program for Categorical Maps. Using 30-m resolution Landsat Thematic Mapper (TM) data from the Institute of Remote Sensing Application (IRSA) in China, we classified images into six land-use types: cropland, forestland, grassland, water, urban and/or built-up land, and barren land. Significant changes in land-use occurred within the area over the study period. The results show the significant decrease in barren land was mainly due to conversion to grassland. Cropland increased by 3.39%, associated with conversions from grassland and barren land. The landscape has become more continuous, clumped and more homogeneous. The study demonstrates that the integration of satellite remote sensing and GIS was an effective approach for analysing the direction, rate and spatial pattern of land-use change.     

Landscape changes of the Ejin Delta in the Heihe River Basin in Northwest China from 1930 to 2010

The Heihe River Basin is located in the arid and semi-arid region of Northwest China; during the past 80 years, this basin has experienced water resource competition between irrigation agriculture and ecological demand in its middle and lower reaches, respectively. The land cover of the Ejin Delta in the lower reaches of the Heihe River Basin was interpreted and analysed for four different periods using a map created by Dr Sven Hedin in the 1930s, Corona satellite images taken in 1961, and Landsat Thematic Mapper (TM) images taken in 2000 and 2010. Overall, the results show that (1) the coarse resolution of the 1930s map increased the uncertainty of analysis in the study area and (2) the river area in the Ejin Delta decreased by 91.0% from the 1930s to 2000. In addition, two major terminal lakes, Gaxun Nuur Lake and Sogo Nuur Lake, dried up in 1961 and 1992, respectively, and the area of Populus euphratica decreased by 76.1% from the 1930s to 2000. Most reeds were overtaken by shrubs between the 1930s and 1961, which caused the area of reeds to decrease from 3481 to 1332 km² and the area of shrubs to increase from 805 to 2795 km². From the 1930s to 2000, the desert and alkaline land areas increased by 42.2% and 52.4%, respectively. (3) After the water transfer project was implemented in 2000, the area of Sogo Nuur Lake recovered to 40.58 km² by 2010. The areas of Populus euphratica, shrubland, and reedland showed a recovering trend, with increases of 4.5%, 6.5%, and 43.5%, respectively, by 2010. The desert and alkaline land areas decreased by 4.2% and 15.2%, respectively, by 2010. The area of cultivated land increased from 25 km² in 1961 to 85 km² in 2000 and rapidly approached 160 km² in 2010. These changes over time indicated that the ecological habitat in the Ejin Delta deteriorated between the 1930s and 2000. However, the water transfer project effectively changed the degradation trend.     

Characterizing changes in grassland desertification based on Landsat images of the Ongniud and Naiman Banners,Inner Mongolia

Desertification is treated as an important and critical environmental hazard. In the face of increasingly serious grassland desertification, China has made great efforts to combat desertification and a series of key national ecological projects has been launched. However, accurate, timely, and effective monitoring and assessment are required to determine whether these projects work well. The Horqin sandy land represents the largest area of sandy land in China. In this article, the Naiman and Ongniud Banners were studied because these contain the main desertified grassland in Horqin. Next, a desertification classification and grading system was designed for the Horqin sandy land after conducting fieldwork. Based on spectral mixture analysis (SMA) and decision-tree methods, we interpreted Landsat Thematic Mapper/Enhanced Thematic Mapper Plus/Operational Land Imager (TM/ETM+/OLI) images of the study area from four years: 1985, 1992, 2001, and 2013. Overall, the following results were obtained. The total area of desertified grassland in the Naiman and Ongniud Banners increased from 5979 km² in 1985 to 9195 km² in 1992 (an increase of 53.79%) and then decreased to 7828 km² in 2001 and to 6023 km² in 2013. The changes in the areas of desertified grassland with various degrees of desertification displayed the same trends as that of the total desertified grassland area. The severely desertified grassland expanded from 1872 km² in 1985 to 3723 km² in 1992 before shrinking to 2189 km² in 2013. The annual rates of expansion of desertified grassland during the periods 1985–1992, 1992–2001, and 2001–2013 were 7.68%, ?1.65%, and ?1.92%, respectively, and the corresponding expansion rates of severely desertified grassland were 14.12%, ?3.48%, and ?1.19%, respectively. Both the desertified grasslands and the areas with various degrees of desertification displayed significant expansion during the period 1985–1992. Since 1992, this trend has reduced. During the study period, the changes in temperature and precipitation did not benefit the reversal of grassland sandy desertification. Furthermore, the growing population and expansion of livestock production and farming inhibited such reversal. However, the results presented in this article suggest that a reversal in grassland sandy desertification has been occurring since 1992. The results indicate that ecological engineering measures have helped reverse desertification and have promoted the restoration of grassland vegetation.     

Quantifying the spatial differences of landscape change in the Hai River Basin,China, in the 1990s

Quantifying a landscape pattern and its change is essential for monitoring and assessing the ecological consequences of land-use/land-cover (LULC) change and human interference. In this study, a combination of landscape pattern indices and land-use dynamics indices based on remote-sensing images was employed to analyse and compare the spatial and temporal dynamics of the landscape pattern in the Hai River Basin (HRB), China, in the 1990s. During this decade, the change in the landscape pattern was mainly driven by intense human-induced alterations. Overall, the landscape pattern changed considerably, progressively becoming more fragmented and diverse, with widespread encroachment of cropland because of rapid urbanization. The change in the landscape pattern exhibited distinctive spatial differences between the mountains and the plains, as well as between urban and rural areas, with higher fragmentation in the plain region and urban fringes or newly urbanizing areas. The changes in the landscape pattern around Beijing resulted in more fragmented and diverse landscape types. A detailed examination of the Jing–Guang (Beijing–Guangzhou) railway line transect and two other subregions indicated that urbanization contributed mostly to the spatial differences of landscape change through population growth, transportation improvements and rapid economic development. Spatial differences in the change in the landscape pattern were induced by economic growth, population increase and government policy.     

基于RS和GIS的黄河下游沿岸县域土地利用与景观格局演变的驱动力研究 ——以河南省封丘县为例

以位于黄河下游沿岸的河南省封丘县为研究区域,通过遥感影像解译、地理信息系统和景观格局计算软件,分析了该区域1990、2000年土地利用和景观格局的变化特征,运用典型相关分析方法,找出土地利用和景观格局变化的驱动因子,结果如下：研究期间居民点与建设用地增加2 934.87 hm2,其它类型用地减少,尤其是旱地、水体分别减少1 084.81 hm2、1 717.92 hm2;以种植业用地为基质（旱地、水田用地比例之和近80%）的农业景观较为稳定,但农业结构单一、景观多样性较低;人口数量、粮食生产、对优越生活条件的追求等农业社会经济条件的变化是研究区土地利用与景观格局演变的驱动因子。     

基于遥感与GIS的北京市土地利用动态演化模式研究

将土地利用动态变化模型与景观生态学景观格局模型相结合，在1988－2000年北京市遥感数据的基础上，分析了北京市土地利用动态变化模式。研究表明，地形条件对北京市土地利用类型的形成及土寺利用动态变化具有重要影响。在平原地区，农田、城乡居民点及独立工矿用地居于主导地位，土地利用动态变化主要表现为城乡居民点扩展占用耕地及生态退耕。在台地、丘陵和山地地区，林地、草地等自然景观居于主导地位，土地利用动态变化主要表现为生态退耕。北京市土寺利用格局的动态变化表现了城市化、工业化高速发展与退耕还林等生态建设政策实施对土地利用空间格局产生的影响。自然景观增加，景观多样性半加。在自然景观中，林地面积增加，破碎度减小，斑块边界趋于平滑；草地面积减少，趋于破碎。在人文景观中，城镇、农村居民点斑块增大，趋于紧凑，有利于用地节约。农田受到城镇农村居民点扩展及退耕还林政策的双重影响，面积大量减少，破碎度增加。     

The application of a binary division procedure to the classification of forest subcategories using MODIS time-series data during 2000–2010 in China

Forests account for more than 23% of China’s total area. As the most important terrestrial ecosystem, forests have tremendous ecological value. However, it remains difficult to classify forest subcategories at the national scale. In this study, a newly developed binary division procedure was used to categorize forest areas, including their spatiotemporal dynamics, during the period 2000–2010. Time-series images acquired using the Moderate Resolution Imaging Spectroradiometer (MODIS), together with auxiliary data on land use, climate zoning, and topography, were utilized. Hierarchical classification and zoning were combined with remote-sensing auto-classification. Based on the forest extent mask, the state-level forest system was divided into four classes and 18 subcategories. The method achieved an acceptable overall accuracy of 73.1%, based on a comparison to the sample points of China’s fourth forest general survey data set. In 2010, the total forest area was 1.755 × 10⁶ km², and the total area of and shrubs was 4.885 × 10⁵ km². The total area of woodland increased by 2536.25 km² during the decade 2000–2010. The shrub subcategories exhibited almost no change during this time period; however, significant changes in forest area occurred in the mountainous region of Northeast China as well as in the hilly regions of Southern China. The main transformations took place in cold-temperate and temperate mountainous deciduous coniferous forest, subtropical deciduous coniferous forest, subtropical evergreen coniferous forest, and temperate and subtropical deciduous broadleaved mixed forests. The binary division procedure proposed herein can be used not only to rapidly classify more forest subcategories and monitor their dynamic changes, but also to improve the classification accuracy compared with global and national land-cover maps.     

Changes in agricultural cropland areas between a water-surplus year and a water-deficit year impacting food security,determined using MODIS 250 m time-series data and spectral matching techniques,in the Krishna River basin (India)

The objective of this study was to investigate the changes in cropland areas as a result of water availability using Moderate Resolution Imaging Spectroradiometer (MODIS) 250 m time-series data and spectral matching techniques (SMTs). The study was conducted in the Krishna River basin in India, a very large river basin with an area of 265 752 km² (26 575 200 ha), comparing a water-surplus year (2000–2001) and a water-deficit year (2002–2003). The MODIS 250 m time-series data and SMTs were found ideal for agricultural cropland change detection over large areas and provided fuzzy classification accuracies of 61–100% for various land‐use classes and 61–81% for the rain-fed and irrigated classes. The most mixing change occurred between rain-fed cropland areas and informally irrigated (e.g. groundwater and small reservoir) areas. Hence separation of these two classes was the most difficult. The MODIS 250 m-derived irrigated cropland areas for the districts were highly correlated with the Indian Bureau of Statistics data, with R ²-values between 0.82 and 0.86.

The change in the net area irrigated was modest, with an irrigated area of 8 669 881 ha during the water-surplus year, as compared with 7 718 900 ha during the water-deficit year. However, this is quite misleading as most of the major changes occurred in cropping intensity, such as changing from higher intensity to lower intensity (e.g. from double crop to single crop). The changes in cropping intensity of the agricultural cropland areas that took place in the water-deficit year (2002–2003) when compared with the water-surplus year (2000–2001) in the Krishna basin were: (a) 1 078 564 ha changed from double crop to single crop, (b) 1 461 177 ha changed from continuous crop to single crop, (c) 704 172 ha changed from irrigated single crop to fallow and (d) 1 314 522 ha changed from minor irrigation (e.g. tanks, small reservoirs) to rain-fed. These are highly significant changes that will have strong impact on food security. Such changes may be expected all over the world in a changing climate.     

Change analysis of land surface temperature based on robust statistics in the estuarine area of Pearl River (China) from 1990 to 2000 by Landsat TM/ETM+ data

The estuarine area of Pearl River that has taken great changes in land cover since 1990 is a typical area for studying the change of land surface temperature (LST). The LST of the years 1990 and 2000 in this area was estimated from the data of Landsat TM/ETM+ band 6, respectively, and three scales, corresponding to high, normal and low temperature ranges, were divided by a robust statistical method. The results show that the area of high temperature range in 2000 has an increase of 250 km² compared with the year 1990. The urban‐used land and the bare land are the main land cover types constituting the high temperature range area.     

基于TM影像的城郊景观土地利用初步研究--以北京昌平沙河区为例

北京市是全国的政治、经济和文化中心，城镇扩张速度较快。中国加入世界贸易组织和北京申办奥运会的成功，将使城镇进一步扩展。随着城市向郊区的扩张，城郊景观成为城市和郊区的过渡带，该过渡带的景观土地利用发生了巨大变化。借助TM遥感影像采用两种方法来解译北京昌平沙河区景观土地利用：其一是利用TM影像的4、5、3波段的假彩色合成来该地区的土地利用解译；其二是借助TM影像3和4波段计算的NDVI来判定土地利用，并与土地统计数据对比，结果表明第一种方法解译城郊景观的土地利用类型效果较好，而第二种方法对有植被覆盖的土地利用类型解译较好。     

利用Landsat影像构建河西绿洲土地利用信息图谱——以张掖市甘州区为例

基于地学信息图谱理论,结合GIS和RS技术,利用河西绿洲甘州区1975年、1987年、1999年和2009年四期Landsat影像作为土地利用信息提取的基础空间数据,构建了一系列土地利用信息图谱,通过图谱来分析研究区的土地利用时空变化规律。结果表明:1975年～2009年河西绿洲甘州区的土地利用发生了显著变化,耕地、建设用地和未利用地呈现出持续的增加态势,其中耕地主要来源于草地、林地和未利用地的转化;林地、草地和水域面积呈减小趋势,主要表现为草地退化、开垦为耕地。     

Temporal and spatial variations of grassland desertification monitoring in Tibet of China

Tibet, the largest region of the Qinghai–Tibet Plateau, is undergoing extensive grassland deterioration and desertification due to both human and natural factors. Alpine meadow and grassland restoration is difficult after degradation; consequently, the desertification of the Tibetan grassland has attracted substantial social attention. This article considered Amdo, Baingoin, Coqên, and Zhongba counties in Tibet as the study areas, employed remote-sensing data, and developed Tibetan grassland desertification classification indices based on field surveys. Moreover, this study used spectral mixture analysis (SMA) methods to interpret remote-sensing image data from the study areas during three periods (1990, 2000, and 2009) and considered the bare sand (gravel) area proportion as the main basis for the evaluation of grassland desertification. The results of this study demonstrate that the slightly, moderately, and severely desertified grasslands of the monitoring zone covered a total area of 114,113.16 km² in 1990, accounting for 82.12% of the study area. The area exhibited no change in 2000 and decreased by 4472.31 km² in 2009. The severely desertified grassland area declined from 1990 to 2009. The degree of grassland desertification in these four Tibetan counties diminished from 1990 to 2009, and the grassland desertification area exhibited a gradual reduction during the same period. Regarding other soil coverage types, the ice and snow area markedly changed and declined to approximately one-third of its original extent during these 20 years, and most of the ice and snow area was converted to bare land and various types of desertified grassland.     

The change of land cover and land use and its impact factors in upriver key regions of the Yellow River

Owing to the influence of global change, land cover and land use have changed significantly over the last decade in the cold and arid regions of China, such as Madoi County which is located in the source area of the Yellow River. In this paper, land‐use/cover change and landscape dynamics are investigated using satellite remote sensing (RS) and a geographical information system (GIS). The objectives of this paper are to determine land‐use/cover transition rates between different cover types in the Madoi County over 10 years e.g., from 1990 to 2000. Second, the changes of landscape metrics using various indices and models are quantified. The impact factors of LUCC (Land‐Use land cover Change) are systematically identified by integrating remote sensing as well as statistical data, including climate, frozen soil, hydrological data and the socio‐economic data. Using 30 m×30 m spatial resolution Landsat (Enhanced) Thematic Mapper (TM/ETM+) data in our study area, nine land cover classes can be discriminated. Our results show that Grassland, Marshes and Water Bodies decrease notably, while oppositely, Sands ‐ Gobi and Barren land increase significantly. The number of lakes with an acreage larger than six hectares decreased from 405 in 1990 to 261 in 2000. Numerous small lakes dried out. The area of grassland with a high cover fraction decreased as well, while the surface area of grassland with a medium level of cover fraction increased. The medium cover fraction grassland mainly originates from high cover fraction grassland. The desertification of land is a serious issue. (ii) The inter‐transformations between Grasslands, Barren Land, Sands, Gobi, Water Bodies and Marshes are remarkable. The Shannon–Weaver Diversity Index (SWDI), the Evenness Index (EI) and the extent of Landscape Heterogeneity (LH) has improved. Marshes have become more fragmented hence, with less connected patches. (iii) In the recent 30 years, average annual temperature, the power of evaporation and the index of dryness did increase significantly. Moreover, soil moisture content (SMC) decreased and the drought trend accelerated. The degradation of frozen soil has impacted on the decrease of surface water area and induced a drop in groundwater levels. Monitoring LUCC in sensitive regions would not only benefit from a study of vulnerable ecosystems in cold and high altitude regions, but would provide scientifically based decision‐making tools for local governments as well.     

遥感与地理信息系统技术在湿地研究中的应用

基于遥感和地理信息技术,对黄河三角洲河口湿地土地利用/覆盖现状和变化进行分析,利用多维信息图像对土地利用状况进行分类,然后利用景观分析法对该地区土地利用/覆盖变化信息进行评定,并对变化驱动力做出推断,最后据此提出合理利用和保护黄河三角洲湿地的建议。     

Quantitative detection of change in grass cover from multi-temporal TM satellite data

In this paper, change in grassland cover near Lake Qinghai, west China was quantitatively detected from satellite remote-sensing data. Two Thematic Mapper images recorded in 1987 and 2000 were radiometrically corrected and used to derive the Normalized Difference Vegetation Index (NDVI). The NDVI image in 2000, after standardization via in situ measured spectra, was converted to a map of grass cover with the aid of in situ grass-cover samples. Another map was produced from the 1987 image after it was radiometrically benchmarked to the 2000 image using the calibration to like-values method. Comparison of these two maps revealed that a total of 36.28 km² of grassland had a higher cover, versus 44.72 km² that experienced grassland degradation in the study area. The absolute cover changed by a net value of??1.27%. The magnitude of change is related inversely to the value of the cover. The large majority of the area (82.6%), however, had a small change that was within ±20%. With this proposed method, it is possible to quantify changes in grassland cover from multi-temporal satellite data if one set of ground samples are concurrently collected with one of the satellite images.     

Classification accuracy and trend assessments of land cover- land use changes from principal components of land satellite images

The paper evaluated the accuracy of classifying Land Cover-Land Use (LCLU) types and assessed the trends of their changes from Principal Components (PC) of Land satellite (Landsat) images. The accuracy of the image classification of LCLU was evaluated using the confusion matrices and assessed with cross-referencing of samples of LCLU types interpreted and classified from System Pour l’Observation de la Terre (SPOT) images and topographical map. LCLU changes were detected, quantified, and statistically analysed. The interpretation error of the composite image of Landsat Enhanced Thematic Mapper Plus (Landsat ETM⁺) (2006) was high compared with that from the PC image of Landsat ETM⁺ (2006). From 1986 – 2006 the area covered by settlements increased by 0.8% (230,380.00 km²), agricultural land decreased by 7.5% (1009.40 km²), vegetation cover decreased by 0.9% (114.00 km²) while waterbody increased by 0.2% (25.91 km²). Also, from 1986 – 2006 the average annual rates of change in the area of settlements was 6.7%. Agricultural land and bare land showed fluctuations of change rates from 6.7% and 5.0% annually in 1986 and 2006 respectively. The quantitative evidences of LCLU changes revealed the growth of settlements. The conversions of land from agriculture to urban land represent the most significant land cover changes. The rate of change was as high as 4.8% for settlements while agricultural lands were converted at 5.0% per year. The Principal Component Analysis (PCA) of the Landsat images and supervised classification method used made it possible to classify and determine the area of LCLU classes from the set of Landsat images without prior depiction and delimitation of individual LCLU type. It permitted the measurement of area of each LCLU class at a high accuracy level and kept the level of error relatively constant. The PCA analysis in this study affirms the previous research findings. Future research works should focus on the use of remotely sensed images with high temporal and spatial resolutions such as Quick Bird and SPOT 6 to develop effective and accurate LCLU change mapping and monitoring at the local scale.

The PCA technique has been used quite widely to study changes in land cover and land use in many ‘developed’ countries but much still needs to be done in developing and undeveloped countries where land cover and land use change is poorly mapped and knowledge of such changes is very important for planning development of the country.     

A Markovian and cellular automata land-use change predictive model of the Usangu Catchment

Usangu Catchment, in Tanzania, is vital for its rice production in which more than 30% of Tanzanian rice is grown. The catchment is a part of the Southern Agricultural Corridor of Tanzania where major agricultural intensification is expected to take place. Given the role of this catchment, it is important to investigate the effect of agricultural intensification, land-use/land-cover (LULC) change and climate variability on water balance in the catchment. Thus, the objective of the study was to simulate Usangu Catchment’s LULC of 2020 based on LULC of 2000, 2006 and 2013 using Markov Chain and Cellular Automata Analysis.Social, edaphic, climatic and landscape geomorphology factors governing the LULC change and distribution were used to prepare LULC suitability maps in geographical information system.The relative importance of LULC change factors was determined using the analytic hierarchy process and aggregated using weighted linear combination under multi-criteria evaluation approach. The model was validated using simulated and observed LULC 2013. The standard kappa coefficient (κ-standard) and overall agreements of the model were 0.6776 and 0.9125, respectively. The error due to quantity is 0.0243 while error due to allocation is 0.0667. The simulated LULC 2020 scenario shows the increase in urban area by 8.2% and a major decrease in forestland and shrubs by 20.6% and 6.9%, respectively. About 19.6% grassland and 8.5% of agricultural land in 2013 will be converted to urban land by 2020. On the other hand, about 372.0 km² (10.4%) of wetlands and 368.2 km² (10.3%) of woodlands will be converted to agricultural land. The 2020 LULC simulation model of Usangu developed in this study provide some useful information for future LULC scenarios and data for water balance models and preparation of future ecological conservation plans.     

Wetland mapping in the Congo Basin using optical and radar remotely sensed data and derived topographical indices

This study reports results of a classification tree approach to mapping the wetlands of the Congo Basin, focusing on the Cuvette Centrale of the Congo River watershed, an area of 1,176,000 km². Regional expert knowledge was used to train passive optical remotely sensed imagery of the Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+) sensors, JERS-1 active radar L-band imagery, and topographical indices derived from 3 arc sec elevation data of the Shuttle Radar Topography Mission (SRTM). All data inputs were resampled to a common 57 m resolution grid. A classification tree bagging procedure was employed to produce a final map of per-grid cell wetland probability. Thirty bagged trees were ranked and the median result was selected to produce the final wetland probability map. Thresholding the probability map at < 0.5 yielded a proportion of wetland cover for the study area of 32%, equivalent to 360,000 km². Wetlands predominate in the CARPE Lake Tele-Lake Tumba landscape located in the western part of the Democratic Republic of the Congo and the south-eastern Republic of Congo, where they constitute 56% of the landscape. Local topography depicting relative elevation for sub-catchments proved to be the most valuable discriminator of wetland cover. However, all sources of information (i.e. optical, radar and topography) featured prominently in contributing to the classification tree procedure, reinforcing the idea that multi-source data are useful in the characterization of wetland land cover. The method employed freely available data and a fully automated process, except for training data collection. Comparisons to existing maps and in situ field observations indicate improvements compared to previous efforts.