Author(s): M. Zare; M. Koch
Linked Author(s):
Keywords: No keywords
Abstract: ABSTRACT: The Miandarband plain is one of the most fertile plains of the Kermanshah province, Iran. The major water supply for agriculture is groundwater. In this regard, simulation and prediction of groundwater level (GL) fluctuations plays an important role for effective water resources management. GL-changes are complex to model, as they depend on many nonlinear and uncertain factors, thus, selecting suitable numerical or stochastic models that could simulate the nonlinearity and complex patterns is of great importance. Artificial Neural Networks (ANN) and/or fuzzy logic models are one family of models that have proven to be very useful to that regard. In this study, after data completion, using a novel multiple linear regression approach the Feed Forward Neural Network (FFNN) model with one hidden layer whose perceptrons have been optimized in the-training phase with three methods (Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient) and the Adaptive Network-Fuzzy Inference System (ANFIS) have been applied and evaluated for GL-fluctuations simulation and prediction in the Miandarband plain, Iran. The results show that both model approaches can be used with acceptable accuracy, wherefore the ANFIS-model performs better than the three FFNN-model variants. In fact, the values of R 2 and RMSE for ANFIS are 0.97 and 0.48, respectively, in the training phase and 0.96 and0.52 in the testing phase.
Year: 2016