Multi-sensor mapping of West African land cover using MODIS, ASAR and TanDEM-X/TerraSAR-X data

Geßner, Ursula; Machwitz, Miriam; Esch, Thomas; Tillack, Adina; Naeimi, Vahid; Kuenzer, Claudia; Dech, Stefan

doi:10.1016/j.rse.2015.03.029

Cited by 61 publications

(41 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combined with the SRTM digital elevation model (DEM) and derivatives (slope, surface roughness, topographic wetness index [66]), an input dataset for a Random Forest (RF) classification was composed. RF is a supervised ensemble classifier developed by Breiman [67,68], reported to be stable with limited or imbalanced input data [69], not to overfit [68,70] and to generally yield high accuracies in land use and land cover classification (e.g., [71][72][73]). Field observations, flight campaigns and Google Earth were used as reference for model training and validation.…”

Section: Lulc Changes At the Catchment Scalementioning

confidence: 99%

Sustainability in the Food-Water-Ecosystem Nexus: The Role of Land Use and Land Cover Change for Water Resources and Ecosystems in the Kilombero Wetland, Tanzania

et al. 2017

View full text Add to dashboard Cite

Land Use Land Cover Change (LULCC) has a significant impact on water resources and ecosystems in sub-Saharan Africa (SSA). On the basis of three research projects we aim to describe and discuss the potential, uncertainties, synergies and science-policy interfaces of satellite-based integrated research for the Kilombero catchment, comprising one of the major agricultural utilized floodplains in Tanzania. LULCC was quantified at the floodplain and catchment scale analyzing Landsat 5 and Sentinel 2 satellite imagery applying different adapted classification methodologies. LULC maps at the catchment scale serve as spatial input for the distributed, process-based ecohydrological model SWAT (Soil Water Assessment Tool) simulating the changes in the spatial and temporal water balance in runoff components caused by LULCC. The results reveal that over the past 26 years LULCC has significantly altered the floodplain and already shows an impact on the ecosystem by degrading the existing wildlife corridors. On the catchment scale the anomalies of the water balance are still marginal, but with the expected structural changes of the catchment there is an urgent need to increase the public awareness and knowledge of decision makers regarding the effect of the relationship between LULCC, water resources and environmental degradation.

show abstract

Section: Lulc Changes At the Catchment Scalementioning

confidence: 99%

Sustainability in the Food-Water-Ecosystem Nexus: The Role of Land Use and Land Cover Change for Water Resources and Ecosystems in the Kilombero Wetland, Tanzania

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Agricultural extent can be deduced from global land cover maps such as the 500 m MODIS (Moderate Resolution Imaging Spectroradiometer) product MCD12Q1 [11], the 300 m ESA CCI (European Space Agency, Climate Change Initiative) land cover product [12] or the Chinese 30 m products FROM-GLC (Finer Resolution Observation and Monitoring of Global Land Cover) and GLOBELAND30 [13,14]. However, the usability of this data is often limited for detailed regional scale applications due to low spatial resolution, missing thematic complexity, temporal availability or regional accuracy [15][16][17]. Regionally optimized land cover information for West Africa based on moderate resolution (250 m) remote sensing data [15] give a good overview of the distribution of agriculture in Burkina Faso.…”

Section: Introductionmentioning

confidence: 99%

“…However, the usability of this data is often limited for detailed regional scale applications due to low spatial resolution, missing thematic complexity, temporal availability or regional accuracy [15][16][17]. Regionally optimized land cover information for West Africa based on moderate resolution (250 m) remote sensing data [15] give a good overview of the distribution of agriculture in Burkina Faso. Nonetheless, they face difficulties in the discrimination of small-scale agriculture from natural vegetation classes and are so far not available for recent years.…”

Section: Introductionmentioning

confidence: 99%

Monitoring Agricultural Expansion in Burkina Faso over 14 Years with 30 m Resolution Time Series: The Role of Population Growth and Implications for the Environment

et al. 2017

Self Cite

View full text Add to dashboard Cite

Burkina Faso ranges amongst the fastest growing countries in the world with an annual population growth rate of more than three percent. This trend has consequences for food security since agricultural productivity is still on a comparatively low level in Burkina Faso. In order to compensate for the low productivity, the agricultural areas are expanding quickly. The mapping and monitoring of this expansion is difficult, even on the basis of remote sensing imagery, since the extensive farming practices and frequent cloud coverage in the area make the delineation of cultivated land from other land cover and land use types a challenging task. However, as the rapidly increasing population could have considerable effects on the natural resources and on the regional development of the country, methods for improved mapping of LULCC (land use and land cover change) are needed. For this study, we applied the newly developed ESTARFM (Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model) framework to generate high temporal (8-day) and high spatial (30 m) resolution NDVI time series for all of Burkina Faso for the years 2001, 2007, and 2014. For this purpose, more than 500 Landsat scenes and 3000 MODIS scenes were processed with this automated framework. The generated ESTARFM NDVI time series enabled extraction of per-pixel phenological features that all together served as input for the delineation of agricultural areas via random forest classification at 30 m spatial resolution for entire Burkina Faso and the three years. For training and validation, a randomly sampled reference dataset was generated from Google Earth images and based on expert knowledge. The overall accuracies of 92% (2001), 91% (2007), and 91% (2014) indicate the well-functioning of the applied methodology. The results show an expansion of agricultural area of 91% between 2001 and 2014 to a total of 116,900 km 2 . While rainfed agricultural areas account for the major part of this trend, irrigated areas and plantations also increased considerably, primarily promoted by specific development projects. This expansion goes in line with the rapid population growth in most provinces of Burkina Faso where land was still available for an expansion of agricultural area. The analysis of agricultural encroachment into protected areas and their surroundings highlights the increased human pressure on these areas and the challenges of environmental protection for the future.

show abstract

“…From the data availability aspect, multi-sensor/source data including optical, SAR, and GIS data have been used as inputs for classification [6][7][8][9]. To properly treat input data for classification, advanced classification methodologies such as machine learning approaches and object-based classification Remote Sens.…”

Section: Introductionmentioning

confidence: 99%

Self-Learning Based Land-Cover Classification Using Sequential Class Patterns from Past Land-Cover Maps

2017

View full text Add to dashboard Cite

Abstract:To improve the accuracy of classification with a small amount of training data, this paper presents a self-learning approach that defines class labels from sequential patterns using a series of past land-cover maps. By stacking past land-cover maps, unique sequence rule information from sequential change patterns of land-covers is first generated, and a rule-based class label image is then prepared for a given time. After the most informative pixels with high uncertainty are selected from the initial classification, rule-based class labels are assigned to the selected pixels. These newly labeled pixels are added to training data, which then undergo an iterative classification process until a stopping criterion is reached. Time-series MODIS NDVI data sets and cropland data layers (CDLs) from the past five years are used for the classification of various crop types in Kansas. From the experiment results, it is found that once the rule-based labels are derived from past CDLs, the labeled informative pixels could be properly defined without analyst intervention. Regardless of different combinations of past CDLs, adding these labeled informative pixels to training data increased classification accuracy and the maximum improvement of 8.34 percentage points in overall accuracy was achieved when using three CDLs, compared to the initial classification result using a small amount of training data. Using more than three consecutive CDLs showed slightly better classification accuracy than when using two CDLs (minimum and maximum increases were 1.56 and 2.82 percentage points, respectively). From a practical viewpoint, using three or four CDLs was the best choice for this study area. Based on these experiment results, the presented approach could be applied effectively to areas with insufficient training data but access to past land-cover maps. However, further consideration should be given to select the optimal number of past land-cover maps and reduce the impact of errors of rule-based labels.

show abstract

Multi-sensor mapping of West African land cover using MODIS, ASAR and TanDEM-X/TerraSAR-X data

Cited by 61 publications

References 50 publications

Sustainability in the Food-Water-Ecosystem Nexus: The Role of Land Use and Land Cover Change for Water Resources and Ecosystems in the Kilombero Wetland, Tanzania

Sustainability in the Food-Water-Ecosystem Nexus: The Role of Land Use and Land Cover Change for Water Resources and Ecosystems in the Kilombero Wetland, Tanzania

Monitoring Agricultural Expansion in Burkina Faso over 14 Years with 30 m Resolution Time Series: The Role of Population Growth and Implications for the Environment

Self-Learning Based Land-Cover Classification Using Sequential Class Patterns from Past Land-Cover Maps

Contact Info

Product

Resources

About