Gerald Forkuor

Integration of Optical and Synthetic Aperture Radar Imagery for Improving Crop Mapping in Northwestern Benin, West Africa

Abstract: Crop mapping in West Africa is challenging, due to the unavailability of adequate satellite images (as a result of excessive cloud cover), small agricultural fields and a heterogeneous landscape. To address this challenge, we integrated high spatial resolution multi-temporal optical (RapidEye) and dual polarized (VV/VH) SAR (TerraSAR-X) data to map crops and crop groups in northwestern Benin using the random forest classification algorithm. The overall goal was to ascertain the contribution of the SAR data to crop mapping in the region. A per-pixel classification result was overlaid with vector field boundaries derived from image segmentation, and a crop type was determined for each field based on the modal class within the field. A per-field accuracy assessment was conducted by comparing the final classification result with reference data derived from a field campaign. Results indicate that the integration of RapidEye and TerraSAR-X data improved classification accuracy by 10%–15% over the use of RapidEye only. The VV polarization was found to better discriminate crop types than the VH polarization. The research has shown that if optical and SAR data are available for the whole cropping season, classification accuracies of up to 75% are achievable.

High Resolution Mapping of Soil Properties Using Remote Sensing Variables in South-Western Burkina Faso: A Comparison of Machine Learning and Multiple Linear Regression Models.

Accurate and detailed spatial soil information is essential for environmental modelling, risk assessment and decision making. The use of Remote Sensing data as secondary sources of information in digital soil mapping has been found to be cost effective and less time consuming compared to traditional soil mapping approaches. But the potentials of Remote Sensing data in improving knowledge of local scale soil information in West Africa have not been fully explored. This study investigated the use of high spatial resolution satellite data (RapidEye and Landsat), terrain/climatic data and laboratory analysed soil samples to map the spatial distribution of six soil properties–sand, silt, clay, cation exchange capacity (CEC), soil organic carbon (SOC) and nitrogen–in a 580 km2 agricultural watershed in south-western Burkina Faso. Four statistical prediction models–multiple linear regression (MLR), random forest regression (RFR), support vector machine (SVM), stochastic gradient boosting (SGB)–were tested and compared. Internal validation was conducted by cross validation while the predictions were validated against an independent set of soil samples considering the modelling area and an extrapolation area. Model performance statistics revealed that the machine learning techniques performed marginally better than the MLR, with the RFR providing in most cases the highest accuracy. The inability of MLR to handle non-linear relationships between dependent and independent variables was found to be a limitation in accurately predicting soil properties at unsampled locations. Satellite data acquired during ploughing or early crop development stages (e.g. May, June) were found to be the most important spectral predictors while elevation, temperature and precipitation came up as prominent terrain/climatic variables in predicting soil properties. The results further showed that shortwave infrared and near infrared channels of Landsat8 as well as soil specific indices of redness, coloration and saturation were prominent predictors in digital soil mapping. Considering the increased availability of freely available Remote Sensing data (e.g. Landsat, SRTM, Sentinels), soil information at local and regional scales in data poor regions such as West Africa can be improved with relatively little financial and human resources.

Shallow groundwater in the Atankwidi Catchment of the White Volta Basin: current status and future sustainability

The Atankwidi Catchment, which lies in the White Volta Basin in West Africa, is intensively cultivated by locals for economic gains. During dry seasons, farmers irrigate their crops, chiefly tomatoes, using shallow groundwater harvested from shallow ponds they dig using simple tools like an axe, hoe, bucket and bowls. Recent expansion in cultivated areas has brought to the fore the need to estimate the volume of shallow groundwater stored in the catchment’s underlying aquifer and to what extent it can sustain the incremental growth in irrigated areas.

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

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 km². 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.

Evaluating the sequential masking classification approach for improving crop discrimination in the Sudanian Savanna of West Africa

A variant of sequential masking classification is proposed for crop mapping.Individual crop types are classified using different image combinations.Accuracy of classifying individual crop classes improves by between 4% and 19%.Increased availability of satellite data can improve crop mapping in cloud-prone areas. Classification of remotely sensed data to reveal the spatial distribution of crop types has high potential for improving crop area estimates and supporting decision making. However, remotely sensed crop maps still demand improvements as e.g. variations in farm management practices (e.g. planting and harvesting dates), soil and other environmental factors cause overlaps in features available for classification and thus confusion in error matrices. In this study, a variant of the sequential masking classification technique was applied to multi-temporal optical and microwave remote sensing data (RapidEye, Landsat, TerraSAR-X) to improve the accuracy of crop discrimination in West Africa. This approach employs different sets of multi-temporal images to sequentially classify individual crop classes. The efficiency of the sequential masking approach was tested by comparing the results with that of a one-step classification, in which all crop classes were classified at the same time. Compared to the one-step classification, the sequential masking approach improved overall classification accuracies by between 6% and 9% while increments in the accuracy of individual crop classes were between 4% and 19%. The McNemars statistical test showed that the observed differences in accuracy of the two approaches were statistically significant at the 1% significance level. The findings of this study are important for crop mapping efforts in West Africa, where data and methodological constraints often hinder the accurate discrimination of crops.

Multi-Temporal Landsat Images and Ancillary Data for Land Use/Cover Change (LULCC) Detection in the Southwest of Burkina Faso, West Africa

Accurate quantification of land use/cover change (LULCC) is important for efficient environmental management, especially in regions that are extremely affected by climate variability and continuous population growth such as West Africa. In this context, accurate LULC classification and statistically sound change area estimates are essential for a better understanding of LULCC processes. This study aimed at comparing mono-temporal and multi-temporal LULC classifications as well as their combination with ancillary data and to determine LULCC across the heterogeneous landscape of southwest Burkina Faso using accurate classification results. Landsat data (1999, 2006 and 2011) and ancillary data served as input features for the random forest classifier algorithm. Five LULC classes were identified: woodland, mixed vegetation, bare surface, water and agricultural area. A reference database was established using different sources including high-resolution images, aerial photo and field data. LULCC and LULC classification accuracies, area and area uncertainty were computed based on the method of adjusted error matrices. The results revealed that multi-temporal classification significantly outperformed those solely based on mono-temporal data in the study area. However, combining mono-temporal imagery and ancillary data for LULC classification had the same accuracy level as multi-temporal classification which is an indication that this combination is an efficient alternative to multi-temporal classification in the study region, where cloud free images are rare. The LULCC map obtained had an overall accuracy of 92%. Natural vegetation loss was estimated to be 17.9% ± 2.5% between 1999 and 2011. The study area experienced an increase in agricultural area and bare surface at the expense of woodland and mixed vegetation, which attests to the ongoing deforestation. These results can serve as means of regional and global land cover products validation, as they provide a new validated data set with uncertainty estimates in heterogeneous ecosystems prone to classification errors.

Landsat-8 vs. Sentinel-2: examining the added value of sentinel-2’s red-edge bands to land-use and land-cover mapping in Burkina Faso

The availability of freely available moderate-to-high spatial resolution (10–30 m) satellite imagery received a major boost with the recent launch of the Sentinel-2 sensor by the European Space Agency. Together with Landsat, these sensors provide the scientific community with a wide range of spatial, spectral, and temporal properties. This study compared and explored the synergistic use of Landsat-8 and Sentinel-2 data in mapping land use and land cover (LULC) in rural Burkina Faso. Specifically, contribution of the red-edge bands of Sentinel-2 in improving LULC mapping was examined. Three machine-learning algorithms – random forest, stochastic gradient boosting, and support vector machines – were employed to classify different data configurations. Classification of all Sentinel-2 bands as well as Sentinel-2 bands common to Landsat-8 produced an overall accuracy, that is 5% and 4% better than Landsat-8. The combination of Landsat-8 and Sentinel-2 red-edge bands resulted in a 4% accuracy improvement over that of Landsat-8. It was found that classification of the Sentinel-2 red-edge bands alone produced better and comparable results to Landsat-8 and the other Sentinel-2 bands, respectively. Results of this study demonstrate the added value of the Sentinel-2 red-edge bands and encourage multi-sensoral approaches to LULC mapping in West Africa.

Multiscale Remote Sensing to Map the Spatial Distribution and Extent of Cropland in the Sudanian Savanna of West Africa

Food security is the topmost priority on the global agenda. Accurate agricultural statistics (i.e., cropped area) are essential for decision making and developing appropriate programs to achieve food security. However, derivation of these essential agricultural statistics, especially in developing countries, is fraught with many challenges including financial, logistical and human capacity limitations. This study investigated the use of fractional cover approaches in mapping cropland area in the heterogeneous landscape of West Africa. Discrete cropland areas identified from multi-temporal Landsat data were upscaled to MODIS resolution using random forest regression. Producer’s accuracy and user’s accuracy of the cropland class in the Landsat scale analysis averaged 95% and 94%, respectively, indicating good separability between crop and non-crop land. Validation of the fractional cropland cover map at MODIS resolution (MODIS_FCM) revealed an overall mean absolute error of 19%. Comparison of MODIS_FCM with the MODIS land cover product (e.g., MODIS_LCP) demonstrate the suitability of the proposed approach to cropped area estimation in smallholder dominant heterogeneous landscapes over existing global solutions. Comparison with official government statistics (i.e., cropped area) revealed variable levels of agreement and partly enormous disagreements, which clearly indicate the need to integrate remote sensing approaches and ground based surveys conducted by agricultural ministries in improving cropped area estimation. The recent availability of a wide range of open access remote sensing data is expected to expedite this integration and contribute missing information urgently required for regional assessments of food security in West Africa and beyond.

Agricultural land use mapping in the sudanian savanna of West Africa: Current status and future possibilities

Multi-temporal Landsat data covering the Bawku West district of Ghana were aligned to the agro-ecological calendar to map agricultural land use. Phenological curves based on NDVI and NIR were extracted. A decision tree classification based on the curves enabled the mapping of six broad classes. Results indicate the successful discrimination of irrigated land from other land use classes, but also the problem of separating natural vegetation from quasi-natural rainfed agriculture. This problem is attributed to the scale on which agriculture is practiced (small scale) and the inadequate spatial and temporal resolution of the Landsat instrument to capture the agricultural fields and cropping systems. In the following months multi-temporal (monthly) 6.5-meter RapidEye, complemented with 6-meter TerraSAR-X observations in the rainy season will be acquired for 2012 and 2013. The synergetic analysis of data from these satellite systems with contemporary field data on cropping cycles promises to improve agricultural land use mapping in this savanna region.