heydar ebrahimi; Alireza Moghaddam Nia; Haji Karimi
Abstract
The runoff simulation in a watershed provides insight on the processes affecting runoff generation and the stream flow characteristics like spatial and temporal variability of stream flow. This insight helps managers and planners in informed decision-makings on water resources management and planning. ...
Read More
The runoff simulation in a watershed provides insight on the processes affecting runoff generation and the stream flow characteristics like spatial and temporal variability of stream flow. This insight helps managers and planners in informed decision-makings on water resources management and planning. The objective of this study is to compare the performances of the complex SWAT model and the simple IHACRES model for simulating runoff in the Doiraj river basin, Ilam province. For this purpose, SWAT model due to having many parameters affecting stream flow and the use of GIS, and IHACRES model due to the low and easy access data requirements, are very practical. In this study, the data over a period from 1994 to 2004 and the statistical criteria of R2, bR2, and NS were used to evaluate performances of IHACRES and SWAT models. For IHACRES model, values of R2, bR2 and NS were estimated equal to 0.34, 0.112 and 0.33, respectively for calibration period and values of 0.47, 0.235 and 0.43, respectively for validation period. In addition, for SWAT model, the coefficients were estimated equal to 0.41, 0.314 and 0.12 respectively, for calibration period and values of 0.68, 0.632 and 0.56, respectively for validation period. Final results of this study showed higher performance of SWAT model relative to IHACRES model for simulating daily runoff in Doiraj river basin and can be used to simulate runoff in the watersheds with limited data and similar natural conditions.
Elham Kakaei Lafdani; Ali Reza Moghaddam Nia; Azadeh Ahmadi; Heydar Ebrahimi
Abstract
This study aimed to examine the influence of pre-processing input variables by Gamma Test on performance of Support Vector Machine in order to predict the suspended sediment amount of Doiraj River, located in Ilam Province from 1994-2004. The flow discharge and rainfall were considered as the input variables ...
Read More
This study aimed to examine the influence of pre-processing input variables by Gamma Test on performance of Support Vector Machine in order to predict the suspended sediment amount of Doiraj River, located in Ilam Province from 1994-2004. The flow discharge and rainfall were considered as the input variables and sediment discharge as the output model. Also, the duration of the model training period was determined through GT. Thereafter, in order to carry out the influence of pre-processing input variables on performance of model, the suspended sediment was predicted using SVM model while no pre-processing has been done on its input variables and the results were compared to each other. Results show the performance of the GT-SVM model in the test phase with minimum RMSE was equal to 0.96 (ton/day) and the maximum coefficient of R2 was equal to 0.98 between the predicted and actual values, was better than SVM model.