Abstract

The rainfall-runoff simulation provides the basis for the hydrological and climate change studies, and the climate studies are based on the rainfall-runoff simulation. In general, there are different models to simulate rainfall and runoff, each with different structures and inputs. In the present paper, two different models in terms of structure were selected: A) Artificial Neural network (ANN) that requires the rainfall, maximum temperature, minimum temperature and runoff data (6 ANN structures were formed based on the relations of partial auto-correlation and cross-correlation), B) Soil and Water Assessment Tool (SWAT) which requires the rainfall, maximum temperature, minimum temperature, and runoff data and the land use, Digital Elevation Model (DEM), and geological maps. In this study, the R2, NSE and MBE parameters were used to investigate the error, the monthly and annual averages to investigate the uncertainty, and the SWAT-CUP model of the SUFI-2 algorithm to select sensitive and important parameters for calibrating the SWAT model (in this study, 12 parameters were selected from the sensitive and important parameters). The results of this study showed that based on the error and uncertainty parameters, the ANN model performance (R2 = 0.76) during the validation period and the highest MBE = 0.09 in May) is better than the SWAT model (R2 = 0.67 in the validation period and the highest MBE = 1.24 in May). Also, the ANN model outperforms the SWAT model in estimating the extreme values. In general, this study found that it is a good practice to utilize the ANN model in the studies associated with climate change and the studies that do not have enough information, and to employ the SWAT model in the studies having a large amount of information and consider the routing and evaluation of the climate change effects on the erosion.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.