| Title: | Adaptability of machine learning methods and hydrological models to discharge simulations in datasparse glaciated watersheds |
| Authors: | Ji, H., Y. Chen, G. Fang, Z. Li, W. Duan and Q. Zhang |
| Year: | 2021 |
| Journal: | Journal of Arid Land |
| Volume (Issue): | 13(6) |
| Pages: | 549–567 |
| Article ID: | |
| DOI: | 10.1007/s40333-021-0066-5 |
| URL (non-DOI journals): | |
| Model: | SWAT_Glacier & SWAT |
| Broad Application Category: | hydrologic only |
| Primary Application Category: | model comparison |
| Secondary Application Category: | snowmelt, frozen soil and/or glacier melt processes |
| Watershed Description: | 63,000 km^2 Aksu River, which is a tributary of the Tarim River, and 12,900 km^2 Kumaric River; both are located in northwest China. |
| Calibration Summary: | |
| Validation Summary: | |
| General Comments: | |
| Language: | English |
| Keywords: | hydrological simulation; long short-term memory; extreme gradient boosting; support vector regression;
SWAT_Glacier model; Tianshan Mountains |