Groundwater Potential Mapping using Shannon's Entropy and Random Forest Models in the Bojnourd Township

Nowadays, water supply for sustainable development is one of the most important concerns and challenges in most countries of the world. Due to determination of groundwater potential zones are one of the important tools in the conservation, management and utilization of water resources. Thus, the present study aimed to prioritize the effective factors on groundwater potential and its susceptibility zonation using Shannon’s entropy and Random Forest in Bojnourd Township. So, layers of slope angle, slope aspect, plan curvature, profile curvature, slope length, altitude, topographic wetness index, distance from fault, fault density, distance from river, drainage density, lithology and land use are known as affecting factors on Groundwater potential and were digitized in ArcGIS software environment. Subsequently, using Shannon’s entropy and Random Forest models, weight of affective factors was calculated in R statistical package and finally groundwater potential maps were prepared for the study area. The accuracy of groundwater potential zoning has been evaluated using relative operating curve (ROC), and according to the results, the accuracy of the Shannon’s entropy model was (85.55%), which is more acceptable than the accuracy of the Random Forest model (76.95 percent). Also, layers of land use, lithology, distance from river and altitude layers had the most effect on Groundwater potential in the study area based on the Shannon’s entropy model.