Evaluation of groundwater vulnerability using data mining technique in Hashtgerd plain

Groundwater vulnerability assessment is an effective informative method to provide basis for determining source of pollution. Vulnerability maps are employed as an important solution in order to handle entrance of pollution into the aquifers. A common way to develop groundwater vulnerability map is DRASTIC index. Meanwhile, application of the method is not easy for any aquifer due to choosing appropriate constant values of weights and ranks. Clustering technique would be an influential method for regionalization of groundwater flow zone to facilitate vulnerability assessment of groundwater aquifers. In this study, a new approach using k-means clustering is applied to make vulnerability maps. Four features of depth to groundwater, hydraulic conductivity, recharge value and vadose zone are considered at the same time as features of clustering. Five regions are recognized out of the Hashtgerd plain. Each zone corresponds to a different level of vulnerability. The results show that clustering provides a more realistic vulnerability map so that, Pearson’s correlation coefficients between nitrate concentrations and clustering vulnerability is 72%.