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.
The era5 global reanalysis
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A conditional diffusion model trained on partitioned incomplete samples for physical dynamics achieves asymptotic convergence to the true generative process under mild conditions and outperforms baselines in imputation.
citing papers explorer
-
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.
-
Incomplete Data, Complete Dynamics: A Diffusion Approach
A conditional diffusion model trained on partitioned incomplete samples for physical dynamics achieves asymptotic convergence to the true generative process under mild conditions and outperforms baselines in imputation.