Integrating GIS and remote sensing for land use/land cover mapping and groundwater potential assessment for climate-smart cocoa irrigation in Ghana.

Although Ghana is a leading global cocoa producer, its production and yield have experienced declines in recent years due to various factors, including long-term climate change such as increasing temperatures and changing rainfall patterns, as well as drought events. With the increasing exposure of cocoa-producing regions to extreme weather events, the vulnerability of cocoa production is also expected to rise. Supplemental irrigation for cocoa farmers has emerged as a viable adaptation strategy to ensure a consistent water supply and enhance yield. However, understanding the potential for surface and groundwater irrigation in the cocoa-growing belt remains limited. Consequently, this study aims to provide decision-support maps for surface and groundwater irrigation potential to aid planning and investment in climate-smart cocoa irrigation. Utilizing state-of-the-art geospatial and remote sensing tools, data, and methods, alongside in-situ groundwater data, we assess the irrigation potential within Ghana's cocoa-growing areas. Our analysis identified a total area of 22,126 km2 for cocoa plantations and 125.2 km2 for surface water bodies within the cocoa-growing regions. The multi-criteria analysis (MCA) revealed that approximately 80% of the study area exhibits moderate to very high groundwater availability potential. Comparing the MCA output with existing borehole locations demonstrated a reasonable correlation, with about 80% of existing boreholes located in areas with moderate to very high potential. Boreholes in very high potential areas had the highest mean yield of 90.7 l/min, while those in low groundwater availability potential areas registered the lowest mean yield of 58.2 l/min. Our study offers a comprehensive evaluation of water storage components and their implications for cocoa irrigation in Ghana. While groundwater availability shows a generally positive trend, soil moisture and surface water have been declining, particularly in the last decade. These findings underline the need for climate-smart cocoa irrigation strategies that make use of abundant groundwater resources during deficit periods. A balanced conjunctive use of surface and groundwater resources could thus serve as a sustainable solution for maintaining cocoa production in the face of climate change.

Predicting reference soil groups using legacy data: A data pruning and Random Forest approach for tropical environment (Dano catchment, Burkina Faso).

Predicting taxonomic classes can be challenging with dataset subject to substantial irregularities due to the involvement of many surveyors. A data pruning approach was used in the present study to reduce such source errors by exploring whether different data pruning methods, which result in different subsets of a major reference soil groups (RSG) - the Plinthosols - would lead to an increase in prediction accuracy of the minor soil groups by using Random Forest (RF). This method was compared to the random oversampling approach. Four datasets were used, including the entire dataset and the pruned dataset, which consisted of 80% and 90% respectively, and standard deviation core range of the Plinthosols data while cutting off all data points belonging to the outer range. The best prediction was achieved when RF was used with recursive feature elimination along with the non-oversampled 90% core range dataset. This model provided a substantial agreement to observation, with a kappa value of 0.57 along with 7% to 35% increase in prediction accuracy for smaller RSG. The reference soil groups in the Dano catchment appeared to be mainly influenced by the wetness index, a proxy for soil moisture distribution.

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.