Hydrology and Earth System Sciences
Hydrology and Earth System Sciences
HESS
Articles | Volume 29, issue 24
Articles | Volume 29, issue 24
https://doi.org/10.5194/hess-29-7217-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-29-7217-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 29, issue 24
Research article
 | 
19 Dec 2025
Research article |  | 19 Dec 2025

An explainable deep learning model based on hydrological principles for flood simulation and forecasting

Xin Xiang, Shenglian Guo, Chenglong Li, and Yun Wang

Viewed

Total article views: 3,323 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
2,400 846 77 3,323 70 89
  • HTML: 2,400
  • PDF: 846
  • XML: 77
  • Total: 3,323
  • BibTeX: 70
  • EndNote: 89
Views and downloads (calculated since 07 Feb 2025)
Cumulative views and downloads (calculated since 07 Feb 2025)

Viewed (geographical distribution)

Total article views: 3,323 (including HTML, PDF, and XML) Thereof 3,265 with geography defined and 58 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 10 Mar 2026
Download
Short summary
Deep learning models achieve strong results in hydrological simulations but often lack links to physical processes. We integrate the principles of the Xinanjiang rainfall–runoff model into a recurrent neural network layer, then combine it with long short-term memory layers. This design improves accuracy while keeping the model explainable, showing small errors in flood peaks and timing.
Read more
Share