Abstract
Abstract In the current study, several soft-computing methods including artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), gene expression programming (GEP), and hybrid wavelet theory-GEP (WGEP) are used for modeling the groundwater's electrical conductivity (EC) variable. Hence, the groundwater samples from three sources (deep well, semi-deep well, and aqueducts), located in six basins of Iran (Urmia Lake (UL), Sefid-rud (SR), Karkheh (K), Kavir-Markazi (KM), Gavkhouni (G), and Hamun-e Jaz Murian (HJM)) with various climate conditions, were collected during 2004–2018. The results of the WGEP model with data de-noising showed the best performance in estimating the EC variable, considering all types of groundwater resources with various climatic conditions. The Root Mean Squared Error (RMSE) values of the WGEP model were varied from 162.068 to 348.911, 73.802 to 171.376, 29.465 to 351.489, 118.149 to 311.798, 217.667 to 430.730, and 76.253 to 162.992 μScm−1 in the areas of UL, SR, K, KM, G, and HJM basins. The WGEP model's performance (R-values) for deep wells, semi-deep wells, and aqueducts of the areas of the KM basin associated with the arid steppe cold (Bsk) dominant climate classification was the best. Also, the WGEP's extracted mathematical equations could be used for EC estimating in other basins.
Highlights
In recent decades, the increasing growth of industry and agriculture, as well as climate changes and human development, have increased the demand for water resources which have caused a serious challenge of water quality deterioration (Yang et al ; Kaur et al )
Deep wells located in the K and KM basins with Bsh and Bsk climate classes, semi-deep wells located in the Urmia Lake (UL), G, and Hamun-e Jaz Murian (HJM) basins with Dsa, Bwk, and Bwh climate classes, and aqueducts located in the SR basin with Csa climate type, had the highest average amount of electrical conductivity (EC) variable
The results showed that the highest water abstraction for agricultural uses, with the highest average EC for deep wells and aqueducts, is related to the KM basin
Summary
The increasing growth of industry and agriculture, as well as climate changes and human development, have increased the demand for water resources which have caused a serious challenge of water quality deterioration (Yang et al ; Kaur et al ). Khudair et al ( ) applied the ANN method without hybrid methods to predict the Water Quality Index (WQI) Their results showed that the pH and chloride variables have a significant influence on WQI prediction with the R2 value of 0.973 for the optimal model. Wagh et al ( ) used the ANN method without hybrid methods for modeling the nitrate concentration in the groundwater resources of Kadava river basin. Their results reflected that the Levenberg–Marquardt (LM) back-propagation algorithm was the effective algorithm of ANN models for the prediction of water quality variables.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
