Numerically modelling groundwater in an arid area with ANN-generated dynamic boundary conditions

Groundwater is sensitive to the climate change and agricultural activities in arid and semi-arid areas. Over the past several decades, human activities, such as groundwater extraction for irrigation, have resulted in aquifer overdraft and disrupted the natural equilibrium in these areas. Regional groundwater simulation is important to determine appropriate groundwater management policies, and numerical simulation has become the most popular method. However, most groundwater models were developed with static boundary conditions. In this research, the Minqin oasis, an arid region located in northwest China, was selected as the study area. An artificial neural network (ANN) was developed to simulate effects of weather conditions, agricultural activities and surface water on groundwater level in a dynamic boundary of the domain. Subsequently, a groundwater numerical model, named ANN-FEFLOW model, was developed, with a dynamic boundary condition defined by the ANN model. The verifying results showed that the model has higher precision, with a root mean square error (RMSE) of 0.71 m, relative error (RE) of 17.96% and R-2 of 0.84 relative to the great groundwater change. Furthermore, the groundwater model has higher precision than the conventional groundwater model with static boundary condition, particularly in the area near the dynamic boundary. This study demonstrated that dynamic boundaries can improve the precision of the regional groundwater model in an arid area and that ANN can provide higher accuracy prediction capability for groundwater levels with dynamic boundary. Copyright (C) 2010 John Wiley & Sons, Ltd.