English

Downscaling Extreme Rainfall Using Physical-Statistical Generative Adversarial Learning

Atmospheric and Oceanic Physics 2022-12-06 v1 Machine Learning Applications

Abstract

Modeling the risk of extreme weather events in a changing climate is essential for developing effective adaptation and mitigation strategies. Although the available low-resolution climate models capture different scenarios, accurate risk assessment for mitigation and adaption often demands detail that they typically cannot resolve. Here, we develop a dynamic data-driven downscaling (super-resolution) method that incorporates physics and statistics in a generative framework to learn the fine-scale spatial details of rainfall. Our method transforms coarse-resolution (0.25×0.250.25^{\circ} \times 0.25^{\circ}) climate model outputs into high-resolution (0.01×0.010.01^{\circ} \times 0.01^{\circ}) rainfall fields while efficaciously quantifying uncertainty. Results indicate that the downscaled rainfall fields closely match observed spatial fields and their risk distributions.

Keywords

Cite

@article{arxiv.2212.01446,
  title  = {Downscaling Extreme Rainfall Using Physical-Statistical Generative Adversarial Learning},
  author = {Anamitra Saha and Sai Ravela},
  journal= {arXiv preprint arXiv:2212.01446},
  year   = {2022}
}
R2 v1 2026-06-28T07:20:55.489Z