Document Type : Research Paper
Authors
Department of Water Engineering , Faculty of Agriculture , University of Tabriz, Tabriz, Iran
Abstract
A significant portion of precipitation in the hydrologic cycle is converted into runoff due to the characteristics of watersheds. Considering the problem that the Lake Urmia Basin is going to be shirinkage, it is important to identify the water resources of this basin and its sub-basins.
Ajichai basin, is one of the sub-basins of Lake Urmia. In this study, rainfall data of Tabriz synoptic station and runoff data of Nahand hydrometric station is used. The aim of this research is to model the daily rainfall-runoff of the Ajichai basin using intelligent machine learning models including the Artificial Neural Network (ANN), Support Vector Machine (SVM), Gene Expression Programming (GEP) and Random Forest (RF). 70% of the data was used for training and 30% of the data was used for testing the models. Statistical measures of Coefficient of determination (R2), Root Mean Square Error (RMSE), Nash-Sutcliffe Efficiency (NSE) and Wilmot Index (WI) were used to evaluate the performance of the models.
The results of this research showed that all the models had a very good performance in simulating the rainfall-runoff in the Ajichai basin. According to the obtained results, the GEP model with R2=0.84, RMSE=0.024m3.s-1, NSE=0.864 and WI=0.968 is the most accurate one in modeling rainfall-runoff of Ajichai basin. Based on the scatter plots and time series, the GEP model was more accurate than other models in modeling the rainfall-runoff values of this basin with high correlation.
According to the results, all the investigated models had good capabilities in modeling the daily rainfall-runoff in the Ajichai basin. The results of this research show the very reasonable performance of machine learning models in rainfall-runoff modeling. In general, due to the high accuracy of intelligent models, especially the GEP model in predicting daily rainfall-runoff, it is recommended to use these methods in hydrological problems.
Keywords
)