Forecasting of heavy metals concentration in groundwater resources of Asadabad plain using artificial neural network approach

Abstract

Nowadays 90% of the required water of Iran is secured with groundwater resources and forecasting of pollutants content in these resources is vital. Therefore, this research aimed to develop and employ the feedforward artificial neural network (ANN) to forecast the arsenic (As), lead (Pb), and zinc (Zn) concentration in groundwater resources of Asadabad plain. In this research, the ANN models were developed using MATLAB R2014 software program. The artificial intelligence models were trained with the data collected from field and then utilized as prediction tool. Levenberg-Marquardt (LM) and Bayesian regularization (BR) algorithms were employed as ANN training algorithms and their performance was evaluated using determination coefficient and the root mean square error. The results showed that the ANN models could potentially forecast heavy metals concentration in groundwater resources of the studied area. Coefficients of determination for ANN models for As, Pb and Zn in testing phase were 0.9288, 0.9823 and 0.8876, respectively. Finally, based on the simulation results, it was demonstrated that ANN could be applied effectively in forecasting the heavy metals concentration in groundwater resources of Asadabad plain.

Keywords

• neural networks
• heavy metals
• groundwater
• forecasting
• risk