Evaluation of data-driven model and GIS technique performance for identification of Groundwater Potential Zones: A case of Fincha Catchment, Abay Basin, Ethiopia

Abstract

Study region: Fincha Catchment, Abay Basin, Ethiopia. Study focus: The study evaluates the performance of the data-driven (ANN) model and GIS technique for the exploration of groundwater potential zones. Lineament density, drainage density, slope, LULC, rainfall, soil, geology, and geomorphology were used as the criteria for the delineation of groundwater potential zones. The criteria were ranked and weighted in the ANN and AHP approaches. Weighted overlay analysis in the GIS platform was used in both methods to delineate the potential zones. The accuracy of the delineated groundwater potential zones in both cases was evaluated by the ROC curve developed from the pumping rate. New hydrological insights for the region: Five and four classes of groundwater potential zones were delineated in ANN and GIS respectively. This indicates that the performance of the ANN model in delineating the groundwater potential zones was better than the GIS technique. The accuracy of the predicted potential zones was evaluated and AUC computed from the ROC curve in both methods revealed an agreement of 96 % and 91 % were made between the ground-truthing points and the ANN model and between GIS platforms respectively. The performance of the ANN was better than the GIS technique in delineating the potential zones. Finally, it is concluded that the ANN model is an effective tool for the delineation of groundwater prospective zones.

Keywords

• ANN
• Data-driven
• Delineation
• GIS
• Groundwater
• Prospective zones