.png){kind=icon}
.png){kind=icon}
Return
Enhancing runoff simulation in data-scarce mountainous regions: a coupled SWAT and transferable transformer approach
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jhydrol.2026.135396.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposed the SWAT-HydroTransformer, a physics–data hybrid modeling framework. • Achieved significant improvements in daily runoff prediction under both baseline and non-stationary climatic conditions. • HydroTransformer adaptively shifts attention between flow memory and meteorological drivers. • HydroTransformer achieved NSEs of 0.729, 0.826, and 0.634 across three basins, indicating strong transferability.
Keywords:
SWAT-HydroTransformer
runoff prediction
hydrological modeling
transferable transformer
data-scarce regions
Journal
IF:
6.3
Papers:
2.3W
Citations:
9.8W