Estimation hydraulic conductivity via intelligent models using geophysical data

In recent years, population growth, urban community development, and consequently increased demand for various water uses such as household and agricultural uses have severely threatened groundwater resources. This issue is highly sensitive in our country due to the arid climate. Therefore, understanding the hydro geological conditions of the aquifers, understanding the groundwater flow and estimating the parameters affecting the ground water flow, such as hydraulic conductivity, is of particular importance in the management, protection, recovery, and exploitation of groundwater. In this study, the hydraulic conductivity was estimated by using artificial intelligence models (artificial neural networks (ANNs), adaptive neuro-fuzzy inference system(ANFIS), and support vector machine(SVM)). For this purpose, the results of geophysical (geoelectric) studies in Maragheh-Bonab plain were analyzed as inputs of the models. Based on the results, the support vector machine showed better performance than the other models with RMSE =1.08 and R ^ 2 = 0.97 in the test phase.