Due to the increasing need for water and the lack of access to its sources, it is essential to maintain and use groundwater resources. So, identifying and exploiting these resources has particular importance. Investigating interflows requires geo-electric and geotechnical studies, both of which require a lot of time and cost. Therefore, it is necessary to provide a method or model that can minimize the cost of investigating interflows as much as possible. In this research, two types of artificial neural networks- multi-layer perceptron (MLP) and radial base function (RBF) were used to study the relationship between hydro-geomorphological characteristics of the watershed basin and interflows in seven watershed sub-basins in Kerman province. Hydro-geomorphological characteristics of subsurface dams were considered as input independent variables, and the discharge of interflow in the watershed basin outlet was considered as dependent variable. The results of this study show that radial base function (RBF) with determination coefficient of 0.9182 and mean squares error of 0.0289, has more accurate results in estimating the discharge of interflow, compared to artificial neural network method of multilayer perceptron (MLP) with determination coefficient of 0.5288  and mean squares error of 0.725. Regarding the determination coefficient in the used methods, it can be concluded that the model of the neural network is the appropriate solution and low cost to check this connection in the watershed.