DRUM: Diffusion-based runoff model for probabilistic flood forecasting

TL;DR

DRUM is a diffusion-based deep learning model that significantly improves probabilistic flood forecasting, extending lead times and enhancing accuracy for extreme floods across diverse U.S. basins.

Contribution

This paper introduces DRUM, a novel diffusion-based probabilistic model that outperforms existing methods in flood forecasting and extends reliable warning lead times.

Findings

Outperforms state-of-the-art benchmarks in flood prediction.

Extends reliable lead times by nearly a day for major floods.

Improves early warning windows by over 2 days under ideal conditions.

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.