Document Type : Research Article
Assistant Professor, Department of Water Engineering, University of Mohaghegh Ardabili, Ardabil, Iran
Assistant Professor, Department of Water Engineering, University of Kurdistan, Kurdistan, Iran
Water Engineering Expert, Department of Water Engineering, University of Mohaghegh Ardabili, Ardabil, Iran
Streamflow forecasting is necessary for water resources management and planning in rivers, lakes, reservoirs and protection of river banks during flood. In this study, different soft computing models including artificial neural networks (ANN), the hybrid of wavelet-artificial neural networks (WANN), gene expression programming (GEP) and least square-support vector machines (LS-SVM) were utilized for river flow estimation of Khiav-Chay. Statistical measures and ANOVA test were used for evaluation of applied models. The results indicated that WANN model was the best model with the highest correlation coefficient (R=0.877) and the lowest root mean squared error (RMSE=0.696) and Nash Sutcliff coefficient (NS=0.767) in validation phase. The results of ANOVA test were in agreement with statistical criteria values and WANN model with the lowest F statistic (F=0.11) and the highest significant resultant (0.75) was selected as the best model. Furthermore, in estimation of maximum discharge, WANN with mean relative error of 30.19% has the minimum error of estimation compared to other models.