LAUSR

Abstract Groundwater is the most valuable natural resource in arid areas. Therefore, any attempt to investigate potential zones of groundwater for further management of water supply is necessary. Hence, many researchers have worked on this subject all around the world. On the other hand, the Generalized Additive Model (GAM) has been applied to environmental and ecological modelling, but its applicability to other kinds of predictive modelling such as groundwater potential mapping has not yet been investigated. Therefore, the main purpose of this study is to evaluate the performance of GAM model and then its comparison with three popular GIS-based bivariate statistical methods, namely Frequency Ratio (FR), Statistical Index (SI) and Weight-of-Evidence (WOE) for producing groundwater spring potential map (GSPM) in Lorestan Province Iran. To achieve this, out of 6439 existed springs, 4291 spring locations were selected for training phase and the remaining 2147 springs for model evaluation. Next, the thematic layers of 12 effective spring parameters including altitude, plan curvature, slope angle, slope aspect, drainage density, distance from rivers, topographic wetness index, fault density, distance from fault, lithology, soil and land use/land cover were mapped and integrated using the ArcGIS 10.2 software to generate a groundwater prospect map using mentioned approaches. The produced GSPMs were then classified into four distinct groundwater potential zones, namely low, moderate, high and very high classes. The results of the analysis were finally validated using the receiver operating characteristic (ROC) curve technique. The results indicated that out of four models, SI is superior (prediction accuracy of 85.4%) following by FR, GAM and WOE, respectively (prediction accuracy of 83.7, 77 and 76.3%). The result of groundwater spring potential map is helpful as a guide for engineers in water resources management and land use planning in order to select suitable areas to implement development schemes and also government entities.