Conference paper · 2025 · Open access

Flow matching for in situ, spatially consistent weather forecast downscaling

David A. Landry, Anastase Charantonis, Claire Monteleoni

EGU General Assembly Conference Abstracts · Published 15 March 2025 · DOI 10.5194/egusphere-egu25-16981

Open full textCite this paper

In brief

“Flow matching for in situ, spatially consistent weather forecast downscaling” is a 2025 conference paper by David A. Landry and 2 co-authors, published in EGU General Assembly Conference Abstracts. OpenAlex counts 0 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at EGU General Assembly Conference Abstracts.

Citations
0
Authors
3

Abstract

Weather forecast downscaling, the problem of recovering accurate local predictions given a lower resolution forecast, is commonly used in operational NWP pipelines. Its purpose is to recover some of the sub-grid processes that could not be represented by the underlying numerical model due to a limited resolution. This misrepresentation provokes statistical mismatches between the observation data gathered from stations and the nearest grid point in the numerical simulation.Using a downscaling model typically requires making a compromise between spatial consistency and statistical calibration. Traditionally, these models are trained to target a traditional verification metric. Consequently, they suffer from the double penalty issue and fail to correctly model spatial correlation structures by becoming overly smooth. This is detrimental to downstream modeling tasks such as power grid management, which require a good assessment of spatially-correlated phenomena. Recently, the finer details of the atmospheric state have successfully been recovered using generative models such as denoising diffusion [2-4]. We propose a similar strategy for in situ downscaling by introducing a flow matching [1] model for that task. A cross-attention transformer [5] backbone allows us to build an internal representation for the gridded numerical forecast as well as the in situ downscaled forecast. Our model avoids the numerical instability and mode collapse issues related to Generative Adversarial Networks. It produces well-calibrated forecasts that better represent the spatial correlations between the stations when compared to non-generative alternatives. Our model makes no assumptions about the underlying forecast, and thus can be thought of in two ways. It can be considered a hybrid NWP/AI model, where we first run a numerical simulation and then downscale it. It can also be considered a supplementary forecasting product in a full machine learning pipeline.Using our flow matching weather forecast downscaling model, we run experiments on the EUPPBench post-processing dataset to predict surface temperature and wind speed. Particular care is given to evaluating the model, where we assess both the marginal performance (via the CRPS, reliability histogram, and spread-error ratio) and the joint performance (via the Energy Score, local Variogram Score and forecast spatial frequency content). The accurate representation of extreme events is evaluated using Brier scores. Further experiments discuss the pitfalls of fitting the Energy Score directly without a generative model. [1] Lipman, Y. et al. (2023) ‘Flow Matching for Generative Modeling’. arXiv. Available at: https://doi.org/10.48550/arXiv.2210.02747.[2] Couairon, G. et al. (2024) ‘ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting’. arXiv. Available at: https://doi.org/10.48550/arXiv.2412.12971.[3] Price, I. et al. (2023) ‘GenCast: Diffusion-based ensemble forecasting for medium-range weather’. arXiv. Available…

Cite this paper

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

APA 7

Landry, D. A., Charantonis, A., & Monteleoni, C. (2025). Flow matching for in situ, spatially consistent weather forecast downscaling. EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu25-16981

MLA 9

Landry, David A., et al. “Flow matching for in situ, spatially consistent weather forecast downscaling.” EGU General Assembly Conference Abstracts, 2025. https://doi.org/10.5194/egusphere-egu25-16981.

Chicago

Landry, David A., Anastase Charantonis, and Claire Monteleoni. 2025. “Flow matching for in situ, spatially consistent weather forecast downscaling.” EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu25-16981.

Harvard

Landry, D. A., Charantonis, A. and Monteleoni, C. (2025) ‘Flow matching for in situ, spatially consistent weather forecast downscaling’, EGU General Assembly Conference Abstracts. doi:10.5194/egusphere-egu25-16981.

IEEE

D. A. Landry, A. Charantonis, and C. Monteleoni, “Flow matching for in situ, spatially consistent weather forecast downscaling,” EGU General Assembly Conference Abstracts, 2025, doi: 10.5194/egusphere-egu25-16981.

BibTeX

@inproceedings{landry2025flow,
  title     = {{Flow matching for in situ, spatially consistent weather forecast downscaling}},
  author    = {Landry, David A. and Charantonis, Anastase and Monteleoni, Claire},
  booktitle = {EGU General Assembly Conference Abstracts},
  year      = {2025},
  doi       = {10.5194/egusphere-egu25-16981},
  url       = {https://doi.org/10.5194/egusphere-egu25-16981}
}

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
  • spatial consistency
  • cross-attention transformer
  • denoising diffusion
  • wind speed forecasting
  • energy score
  • forecast calibration
  • extreme event prediction

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?

Landry, D. A., Charantonis, A., & Monteleoni, C. (2025). Flow matching for in situ, spatially consistent weather forecast downscaling. EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu25-16981

How many times has this paper been cited?

0 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 EGU General Assembly Conference Abstracts: sign in and open the full text from this page.

Who wrote this paper?

David A. Landry, Anastase Charantonis, Claire Monteleoni.

What is the DOI of this paper?

10.5194/egusphere-egu25-16981, permanently at https://doi.org/10.5194/egusphere-egu25-16981. 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.