Groundwater Potential Mapping using Index of Entropy and Naïve Bayes Models at Ardabil Plain

Although groundwater resources have long been selected as a safe choice for resolving human water requirements, overexploitation of them, especially at Ardabil plain, has promoted a decrease in the quality and quantity of these resources. One of the significant solutions is to identification of the groundwater potential zones and exploitation of them according to their potentials. The aim of this study was to compared the efficiency of two objective models: Index of Entropy (IE) and Naïve Bayes (NB) in groundwater potential mapping of Ardabil plain, located in northwest of Iran. For this purpose, ten groundwater occurrence factors including elevation, slope, soil, rainfall, distance from river, land cover, normalized difference vegetation index (NDVI), lithology, groundwater depth, and transmissivity were used based on the availability of data. In order to reduce subjectivity in groundwater potential modeling, all spectral groundwater data layers were classified into objective classes by using Jenks optimization technique. After computing groundwater potential index for the models, receiver operating characteristic (ROC) curve and the area under the curves (AUC) were implemented for validation of the models. The AUC values for the IE and NB models are 0.728, and 0.821, respectively. The overall results approved that both of the models have good capability for demarcating groundwater potential zones but the NB model performed better than the IE model for groundwater potential mapping in Ardabil Plain. The results of accurate groundwater potential mapping at Ardabil plain can be useful for groundwater resources management and avoiding overexploitation in the plain.