Evolving genetic programming and other AI-based models for estimating groundwater quality parameters of the Khezri plain, Eastern Iran

Abstract

Genetic programming (GP) was used to determine relationships between groundwater quality parameters including total hardness (TH), total dissolved solids (TDS) and electrical conductivity (EC) for 240 groundwater samples collected from 12 wells in the Khezri plain, eastern Iran. The artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS) methods were also developed to further verify the estimation capability of GP by a comparison of estimated and observed values of chemical parameters. Values obtained from field observations and different models revealed the superiority of genetic programming, with values of R2 = 0.98, RMSE = 51.38 and MARE = 0.093, for TH, R2 = 0.99, RMSE = 121.35 and MARE = 0.041, for TDS and R2 = 0.97, RMSE = 96.39 and MARE = 0.067 for EC. Satisfactory performances were also produced by the ANN and ANFIS methods for the estimation of the intended water quality parameters. Genetic programming can be considered as a promising tool for automatic modeling of the hydrochemical parameters with the aim of environmental management and optimal use of groundwater resources.