Preprint · 2026 · Open access

Flow Matching for Convective-Scale Precipitation Downscaling

Tom Wetherell

arXiv (Cornell University) · Published 29 May 2026 · DOI 10.48550/arxiv.2606.00281

Open PDFView at the publisherCite this paper

In brief

“Flow Matching for Convective-Scale Precipitation Downscaling” is a 2026 preprint by Tom Wetherell, published in arXiv (Cornell University). OpenAlex counts 2 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
2
Most cited in
2025 (1)
References
22
Authors
1

Abstract

Generative machine learning is an increasingly important complement to dynamical downscaling for producing high-resolution precipitation projections, with diffusion models currently the leading approach. Flow matching is a related generative framework that has recently achieved strong results across image, video and other domains, and shown early promise for downscaling. We train a flow matching model to map daily precipitation from 8 km to 2 km over a convective-scale domain centred on Singapore, and benchmark it against CPMGEM, a score-based diffusion model. Flow matching achieves consistently better spatial skill: higher fractions skill score at every precipitation threshold and neighbourhood scale tested, and tighter structure and amplitude components of the SAL score with comparable location skill. However, flow matching underestimates the upper tail of the precipitation distribution, resulting in a dry bias in the climatological mean. These results suggest that flow matching is a competitive generative framework for convective-scale precipitation downscaling, particularly well suited to capturing spatial structure.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wetherell, T. (2026). Flow Matching for Convective-Scale Precipitation Downscaling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.00281

MLA 9

Wetherell, Tom. “Flow Matching for Convective-Scale Precipitation Downscaling.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2606.00281.

Chicago

Wetherell, Tom. 2026. “Flow Matching for Convective-Scale Precipitation Downscaling.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.00281.

Harvard

Wetherell, T. (2026) ‘Flow Matching for Convective-Scale Precipitation Downscaling’, arXiv (Cornell University). doi:10.48550/arxiv.2606.00281.

IEEE

T. Wetherell, “Flow Matching for Convective-Scale Precipitation Downscaling,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2606.00281.

BibTeX

@misc{wetherell2026flow,
  title     = {{Flow Matching for Convective-Scale Precipitation Downscaling}},
  author    = {Wetherell, Tom},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2606.00281},
  url       = {https://doi.org/10.48550/arxiv.2606.00281}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations

  • flow matching
  • precipitation downscaling
  • generative models
  • diffusion models
  • dry bias

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Wetherell, T. (2026). Flow Matching for Convective-Scale Precipitation Downscaling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.00281

How many times has this paper been cited?

2 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Tom Wetherell.

What is the DOI of this paper?

10.48550/arxiv.2606.00281, permanently at https://doi.org/10.48550/arxiv.2606.00281. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.