20200928_Water Quality Prediction using SWAT-ANN coupled approach


1. Title, Journal, and Authors

Title: Water Quality Prediction using SWAT-ANN coupled approach

Journal: Navideh Nooria,*, Latif Kalinb, Sabahattin Isikb

aInstitute for Disease Modeling

bSchool of Forestry and Wildlife Science, Auburn University



2. Summary

This research is carried to prove that model the basin water qualities in unmonitored watersheds through the developing the SWAT-ANN hybrid model. The SWAT which not calibrated and validated for unmonitored stations produces the output used for the input data of ANN. ANN is carried by the Jackknifing method. Predicted variables are NH4+, NO3-, PO43-.


When comparing the results of the hybrid model with true data, the predicted results show somewhat accurate periodicities. But, there are some underestimated or overestimated phases according to the sampling area and features of each water variables. Then, the hybrid model shows better performances than SWAT-CUP which carries calibration and validation and ANN alone model. Therefore, it is proved that the hybrid model is superior to the other models and it can be able to predict the unmonitored area.


3. Originality and Creativity

- Not calibrated SWAT is adopted to make the input data for ANN to predict the unmonitored area.


4. Application to research

- This research proves that the performances of the hybrid model is superior to the alone models. So, it would be helpful to adopt this method in our research fields.


5. 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)