DRUM: Diffusion-based runoff model for probabilistic flood forecasting
Abstract
Extreme floods pose escalating risks in a changing climate, yet forecasting remains challenging due to peak flow underestimation and high uncertainty. We introduce DRUM, a diffusion-based probabilistic deep learning approach that advances extreme flood forecasting across representative basins in the contiguous United States. DRUM outperforms state-of-the-art benchmarks, enhancing nowcasting skill for the top 0.1% of flows in 72.3% of studied basins. Under operational scenarios, DRUM extends reliable lead times by nearly a full day for 20- and 50-year floods. When evaluated with measured precipitation, an ideal condition, recall improves by 0.3-0.4 and the early warning window extends by 2.3 days for 50-year floods. The enhancement potential varies regionally, with precipitation-driven flood zones in the eastern and northwestern U.S. benefiting most, gaining 3-7 days in lead time. These findings highlight the transformative potential of diffusion models as a cutting-edge generative AI technique for advancing hydrology and broader Earth system sciences.
Cite
@article{arxiv.2412.11942,
title = {DRUM: Diffusion-based runoff model for probabilistic flood forecasting},
author = {Zhigang Ou and Congyi Nai and Baoxiang Pan and Yi Zheng and Chaopeng Shen and Peishi Jiang and Xingcai Liu and Qiuhong Tang and Wenqing Li and Ming Pan},
journal= {arXiv preprint arXiv:2412.11942},
year = {2025}
}