A proper design of the architecture of Artificial Neural Network (ANN) models can provide a robust tool in water resources modelling and forecasting. The performance of different neural networks in groundwater level forecasting was examined in order to identify an optimal ANN model for groundwater level forecast. The Devasugur nala watershed was selected for the study, located at northern part of Raichur district Karnataka and comes under middle Krishna river basin. Elman or Recurrent Neural Network (RNN) trained with Bayesian Regularization (BR), Levenberg Marquardt (LM) and Gradient Descent with Momentum and Adaptive Learning Rate Back propagation (GDX) algorithm models were developed. The results revealed that RNN with LM algorithm provided better prediction than the other models with highest correlation efficiency () and lowest RMSE () value during validation period. Overall it was observed that the ANN based algorithm was a better choice for the groundwater level forecasting. | Simulation of groundwater level using recurrent neural network RNN in Raichur district Karnataka India
