Yang et al. (2026) A hybrid method coupling physical process-driven model with generative deep learning for probabilistic flood forecasting

Identification

• Journal: Journal of Hydrology
• Year: 2026
• Date: 2026-03-01
• Authors: Xuesong Yang, Bin Xu, Yanan Li, Junliang Jin, Ran Mo, Xinrong Wang, Zichen Ren, Yao Liu, Yuchen Shi, Qisheng Zhou, Ping-an Zhong
• DOI: 10.1016/j.jhydrol.2026.135319

Research Groups

Xuesong Yang, Bin Xu, Jingwen Liu, Junliang Jin, Ran Mo, Xinrong Wang, Zichen Ren, Yao Liu, Yuchen Shi, Qisheng Zhou, Ping-an Zhong (Affiliations not specified in the provided text).

Short Summary

This paper proposes a novel hybrid method that integrates a physical process-driven model with generative deep learning to enhance the accuracy and reliability of probabilistic flood forecasting.

Objective

• To develop and evaluate a hybrid method that couples physical process-driven models with generative deep learning for improved probabilistic flood forecasting.

Study Configuration

• Spatial Scale: Not specified in the provided text.
• Temporal Scale: Not specified in the provided text.

Methodology and Data

• Models used: Physical process-driven model, Generative deep learning.
• Data sources: Not specified in the provided text.

Main Results

• Not available in the provided pre-print text.

Contributions

• Introduces a novel hybrid methodology by combining the strengths of physical process-driven models with generative deep learning for flood forecasting.
• Aims to advance the state-of-the-art in probabilistic flood forecasting by leveraging an integrated modeling approach.

Funding

• Not specified in the provided text.

Citation

@article{Yang2026hybrid,
  author = {Yang, Xuesong and Xu, Bin and Li, Yanan and Jin, Junliang and Mo, Ran and Wang, Xinrong and Ren, Zichen and Liu, Yao and Shi, Yuchen and Zhou, Qisheng and Zhong, Ping-an},
  title = {A hybrid method coupling physical process-driven model with generative deep learning for probabilistic flood forecasting},
  journal = {Journal of Hydrology},
  year = {2026},
  doi = {10.1016/j.jhydrol.2026.135319},
  url = {https://doi.org/10.1016/j.jhydrol.2026.135319}
}