Delineating groundwater potential zones in Western Cameroon Highlands using GIS based Artificial Neural Networks model and remote sensing data

For the sustainable use of groundwater, this study analyzes groundwater potential in Western Cameroon Highlands using artificial neural network model (ANN), GIS tools and remote sensing. Twelve factors believed to influence the groundwater occurrence were selected from literature and field investigations and used as input data. Satellite ALOS PALSAR, LANDSAT OLI, SRTM data processing techniques and GIS spatial analysis tools were used to prepare these maps. Pumping rates from 189 wells were considered as groundwater potential data and randomly divided into a training and a test sets. An ANN based on the relationship between groundwater productivity data and the above factors was implement on MATLAB. Each factor’s weight and relative importance was determined by the backpropagation training method. Then the groundwater potential indices were calculated and the final map was created using GIS tools. The resulting groundwater potential map was validated using Area-Under -Curve analysis with data that had not been used for training. An average accuracy of 95% were obtained. As another validation, the groundwater potential map was validated by overlaying the actual pumping rates data with an overall accuracy of 83.2%. Five categories of groundwater potential zones have been demarcated. Major portions are areas with “good” (26.54%) as well as “Moderate” (28.73%) potentials while a few scattered areas have poor (17.66%) and very poor (9.02%). The “very good” potential areas (18.06%) are mainly concentrated at the eastern part of the study area. This groundwater potential information will be useful for effective groundwater management and exploration.