20200918_Coupling SWAT and ANN models for enhanced daily streamflow prediction


1. Title, Journal, and Authors

Title: Coupling SWAT and ANN models for enhanced daily streamflow prediction

Journal: Jornal of Hydrology

Authors: Navideh Nooria, Latif Kalilnb,*

aOdum School of Ecology, University of Georgia

bSchool of Forestry and Wildlife Science, Auburn University


2. Summary

This paper is written to develop the SWAT-ANN hybridized model and demonstrate the utility of the model. SWAT is used to delineate the watershed and predict the daily streamflow without any calibration and validation. The output data are used as input data for ANN. To build up the ANN model, the leave-one-out-site-out jackknifing method is introduced. To compare the performance of the hybrid model, the SWAT-CUP model which has the auto-calibration function is utilized.

The hybrid model shows a better performance than the SWAT-CUP model. Ordinary methods to predict ungauged watershed are regionalization and statistical methods. Especially in the regionalization method, if a watershed has the other watersheds which have different features, the adjustment is difficult. But, in this hybrid model, time and cost-effective analysis will be available without calibration and validation.


3. Application to research

- In this paper, using SWAT-ANN model is introduced to predict daily streamflow without calibration and validation. And, it shows a better performance than auto calibrated model.


4. Contact

Dae Seong Jeong / Integrated Ph.D. program


Environmental Systems Engineering Lab.

School of Earth Sciences and Environmental Engineering

Gwangju Institute of Science and Technology

1 Oryong-dong Buk-gu Gwangju, 500-712, Korea


Phone : +82-10-2003-7860

E-mail : jeongds92@gist.ac.kr

첨부 (0)