Use of Artificial Neural Network and Imperialist Competitive Algorithm to Evaluate the Groundwater Quality of Jolfa Plain for Various Uses

management of these resources. The use of modern methods, including ANN and evolutionary algorithms in estimating water quality, due to its high speed, convergence and efficiency, saves and reduces costs and the best management. The main purpose of this study is to evaluate the results of the chemical analysis of groundwater samples from 14 wells in Jolfa plain and also estimate the ground water quality parameters using imperialist competitive algorithm (ICA) and ANN. Therefore, ground water quality parameters include TDS, EC and SAR estimate using imperialist competitive algorithm (ICA) and ANN and groundwater resources quality in terms of drinking, agriculture and industry were examined by Wilcox, Schuler and Piper and standards. Correlation coefficient of (R2) 90%, indicates the acceptable accuracy of ANN compared with ICA algorithm in estimating groundwater quality parameters. By using different diagrams the results show that the hardness of samples are too much and not suitable for drinking. It should also be noted that a very high hardness and corrosion of sample, water not be used in industry. The salinity of 7 samples is very high and according classification is located in C4S2 class and not suitable for agricultural consumption.