.png){kind=icon}
.png){kind=icon}
Return
FloodTransformer: Efficient real-time high-resolution flood forecasting
.png){kind=icon}
PRE
AI
Z
J
W
F
Y
W
DOI：10.1016/j.envsoft.2025.106832.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• An AI-hydrodynamic hybrid approach is proposed for real-time flood forecasting. • Calibrated 3Di model produces diverse simulations for robust AI training • FloodTransformer achieves efficient, large-scale, and high-resolution prediction. • A tokenised sequential encoder–decoder enables multi-step predictions in a single run. • Physics-informed multi-task optimisation enhances model accuracy and consistency.
Journal
E
IF:
4.6
Papers:
511
Citations:
1.8W
Organization
Cited Papers