Hamadan University of Medical Sciences Avicenna Journal of Environmental Health Engineering 2423-4583 4 1 2017 06 30 A Comparison of Performance of Artificial Neural Networks for Prediction of Heavy Metals Concentration in Groundwater Resources of Toyserkan Plain 11792 11792 10.5812/ajehe.11792 EN Meysam Alizamir Soheil Sobhanardakani Journal Article 10.5812/ajehe.11792 2017 04 16 2017 05 15 Nowadays, about 50% the world’s population is living in dry and semi dry regions and has utilized groundwater as a source of drinking water. Therefore, forecasting of pollutant content in these regions is vital. This study was conducted to compare the performance of artificial neural networks (ANNs) for prediction of As, Zn, and Pb content in groundwater resources of Toyserkan Plain. In this study, two types of artificial neural networks (ANNs), namely multi-layer perceptron (MLP) and Radial Basis Function (RBF) approaches, were examined using the observations of As, Zn, and Pb concentrations in groundwater resources of Toyserkan plain, Western Iran. Two statistical indicators, the coefficient of determination (R2) and root mean squared error (RMSE) were employed to evaluate the performances of various models. The results indicated that the best performance could be obtained by MLP, in terms of different statistical indicators during training and validation periods.