Enhancing Flood Forecasting with Deep Learning: A Scalable Alternative to Traditional Hydrodynamic Models

Weeraphat Duangkhwan

doi:10.1016/j.envsoft.2025.106841

Enhancing Flood Forecasting with Deep Learning: A Scalable Alternative to Traditional Hydrodynamic Models

2025-12-19

0

PRE

AI

W

Weeraphat Duangkhwan

C

Chaiwat Ekkawatpanit *

C

Chanchai Petpongpan

D

Duangrudee Kositgittiwong

S

So Kazama

Y

Yusuke Hiraga

C

Chai Jaturapitakkul

DOI：10.1016/j.envsoft.2025.106841

Original

Original request for help

Save

Abstract

En 中文

• Our framework predicted water levels and mapped floods, mimicking HEC-RAS 1D/2D. • High accuracy with low RMSE reduced computational demands significantly. • The framework robustly mapped floods using recorded data.

Enhancing Flood Forecasting with Deep Learning: A Scalable Alternative to Traditional Hydrodynamic Models

Abstract

Journal

Organization

Cited Papers

Citing Papers