Temporal and spatial estimation of groundwater electrical conductivity using soft computing approaches: analysis of East Azerbaijan Province, Iran

Abstract The evaluation of groundwater quality plays an important role in the management groundwater. main objectives present work are to develop a novel soft computing framework including Adaptive Neuro-Fuzzy Inference System (ANFIS), Wavelet-ANFIS (WANFIS), Gene Expression Programming (GEP), and Wavelet-GEP (WGEP) for temporal spatial estimation electrical conductivity (EC) East Azerbaijan province, Iran over 2001–2020. results demonstrate importance wavelet transform application; performance percentage enhancement WANFIS WGEP models compared ANFIS GEP, using RMSE criterion, ranged from 15.48 51.09% 5.06 86.95%, respectively. All developed showed superior others. impact land use characteristics, climatic conditions, geological features on that there is direct relationship between extent agricultural land, semi-arid climate conditions EC amounts. demonstrated values increase east west, indicating exchange surface study area. Moreover, changes significantly across width fault, with northern part fault higher than southern part.