A diffusion model trained on ERA5 reanalysis downscales global climate data to 0.25° resolution while capturing statistical distributions and extremes.
(2023) Debias coarsely, sample conditionally: statistical downscaling through optimal transport and probabilistic diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SerpentFlow aligns large-scale wind patterns across GCM and observational domains then uses flow-matching to generate consistent fine-scale multivariate wind fields, outperforming standard bias correction in spatial coherence and robustness.
citing papers explorer
-
IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales
A diffusion model trained on ERA5 reanalysis downscales global climate data to 0.25° resolution while capturing statistical distributions and extremes.
-
Generative Unsupervised Downscaling of Climate Models via Domain Alignment: Application to Wind Fields
SerpentFlow aligns large-scale wind patterns across GCM and observational domains then uses flow-matching to generate consistent fine-scale multivariate wind fields, outperforming standard bias correction in spatial coherence and robustness.