Application of Combined Artificial Neural Network and Wavelet Theory for Flow Rate Prediction and Comparing the Results with those of ANFIS (Case Study: The Kor River)

Due to the prolonged droughts in the recent decades, the importance of predicting the flow rate of surface water in rivers for water resources management increases. In this regard, the flow rates in the natural water ways, which is the most important supplement source for water in dam storages, are considered as the most vital factors in predicting surface water. In this study, a combined powerful model, using the artificial neural networks and wavelet theory, was developed to predict the flow rate of the Kor River at the Dashtbal hydrometric station located at the upstream of the Doroudzan Dam. The comparison of the results obtained from this model with those predicted by ANFIS inculcate the superiority of the former providing that the employed parameters are adequately selected. The ANFIS model with 4 Gaussian functions, and the Daubechies 4 wavelet within the third decomposition level occupied the 2nd and 3rd positions in accurate prediction after the combined model developed in this study.