Guardado en:
Detalles Bibliográficos
Autores principales: Ou, Zhigang, Nai, Congyi, Pan, Baoxiang, Zheng, Yi, Shen, Chaopeng, Jiang, Peishi, Liu, Xingcai, Tang, Qiuhong, Li, Wenqing, Pan, Ming
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2412.11942
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914154771644416
author Ou, Zhigang
Nai, Congyi
Pan, Baoxiang
Zheng, Yi
Shen, Chaopeng
Jiang, Peishi
Liu, Xingcai
Tang, Qiuhong
Li, Wenqing
Pan, Ming
author_facet Ou, Zhigang
Nai, Congyi
Pan, Baoxiang
Zheng, Yi
Shen, Chaopeng
Jiang, Peishi
Liu, Xingcai
Tang, Qiuhong
Li, Wenqing
Pan, Ming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11942
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DRUM: Diffusion-based runoff model for probabilistic flood forecasting
Ou, Zhigang
Nai, Congyi
Pan, Baoxiang
Zheng, Yi
Shen, Chaopeng
Jiang, Peishi
Liu, Xingcai
Tang, Qiuhong
Li, Wenqing
Pan, Ming
Geophysics
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.
title DRUM: Diffusion-based runoff model for probabilistic flood forecasting
topic Geophysics
url https://arxiv.org/abs/2412.11942