Prediction of groundwater level in basement complex terrain using artificial neural network: a case of Ijebu-Jesa, southwestern Nigeria

Empirical relationship between geoelectric parameters and groundwater level in boreholes/wells has not been established. Also, prediction of groundwater level from geoelectric parameters had hitherto not been reported. In order to overcome these challenges, the capability of artificial neural network (ANN) to model nonlinear system was explored in this study to predict groundwater level from geoelectric parameters. To achieve the above objectives, the ground water level (GWL) of all the accessible wells in the study area was obtained and this was used as the output parameter for the ANN model. A total of fifty-one (51) parametric vertical electrical soundings (VES) stations were occupied at each of the well location by adopting Schlumberger array configuration with electrode spacing (AB/2) ranging from 1 to 100 m. The VES data were quantitatively interpreted to generate geoelectric parameters believed to be controlling the groundwater flow and storage in the area. These parameters served as input for ANN model. The capability of ANN as a nonlinear modeling system was thereafter applied to produce a model that can predict the GWL from the input parameters. The efficiency of the model was evaluated by estimating the mean square error (MSE) and the regression coefficient (R) for the model. The results established that seasonal variation has little effect on the water fluctuation in the wells. Two aquifer types, weathered and fractured basement aquifer types, were delineated in the area. The results of the ANN model validation showed low MSE of 0.0014286 and the high regression coefficient (R) of 0.98731. This indicates that ANN can be used to predict GWL in a basement complex terrain with reasonably good accuracy. It is concluded that the ANN can effectively predict GWL from geoelectric parameters.