Groundwater Modelling of the Saq Aquifer Using Artificial Intelligence and Hydraulic Simulations

Abstract

Water resources are directly related to the economic conditions of a region. Precise estimation of groundwater is an important step toward better planning and management. This book chapter is dedicated to modelling groundwater in terms of both quantity and quality utilizing ANN (artificial neural networks), ANFIS (adaptive neuro-fuzzy inference system), and the numerical-hydraulic modeling by MODFLOW (modular three-dimensional finite-difference groundwater flow model). The model performance was determined using mean of square error and Nash-Sutcliffe efficiency of model. The pumping data of the area was used to determine the parameters of Saq Aquifer (Qassim, Saudi Arabia) including specific storage and transmissivity. It has been found that the ANFIS model is the most effective for qualitative and quantitative modelling of the aquifer. Following sensitivity analysis, different future scenarios for sustainable groundwater pumping were examined. This book chapter presents research findings that will be useful for engineers, planners, and managers of water systems in arid areas.