prediction of heavy metals contamination in the groundwater of arak region using artificial neural network and multiple linear regression

prediction of the heavy metals in the groundwater is important in developing any appropriate remediation strategy. this paper attempts to predict heavy metals (pb, zn and cu) in the groundwater from arak city, using artificial neural network (ann) algorithm by taking major elements (hco3, so4) in the groundwater from arak city. for this purpose, contamination sources in the groundwater were recorded based on 150 data samples and several models were trained and tested using collected data to determine the optimum model in which each model involved two inputs and three outputs. the results obtained (the comparison between the predicted and the measured data) indicate that multilayer perceptron neural networks model (ann) has strong potential to estimation of the heavy metals in the groundwater with high degree of accuracy and robustness.