Predicting arsenic and heavy metals contamination inudgroundwater resources of Ghahavand plain based on anudartificial neural network optimized by imperialist competitiveudalgorithm

摘要

Background: The effects of trace elements on human health and the environment gives importance toudthe analysis of heavy metals contamination in environmental samples and, more particularly, humanudfood sources. Therefore, the current study aimed to predict arsenic and heavy metals (Cu, Pb, and Zn)udcontamination in the groundwater resources of Ghahavand Plain based on an artificial neural networkud(ANN) optimized by imperialist competitive algorithm (ICA).udMethods: This study presents a new method for predicting heavy metal concentrations in theudgroundwater resources of Ghahavand plain based on ANN and ICA. The developed approaches wereudtrained using 75% of the data to obtain the optimum coefficients and then tested using 25% of the data.udTwo statistical indicators, the coefficient of determination (R2) and the root-mean-square error (RMSE),udwere employed to evaluate model performance. A comparison of the performances of the ICA-ANN andudANN models revealed the superiority of the new model. Results of this study demonstrate that heavyudmetal concentrations can be reliably predicted by applying the new approach.udResults: Results from different statistical indicators during the training and validation periods indicateudthat the best performance can be obtained with the ANN-ICA model.udConclusion: This method can be employed effectively to predict heavy metal concentrations in theudgroundwater resources of Ghahavand plain.udKeywords: Neural networks (computer), Groundwater, Models, Algorithms, Trace elements