Journal article · 2026 · Open access

Joint bias correction and downscaling of subseasonal forecasts via diffusion models

Maria Pyrina, Adel Imamovic, Dominik Büeler, Christoph Spirig, Daniela I. V. Domeisen

Environmental Data Science, 5 · Published 15 July 2026 · DOI 10.1017/eds.2026.10047

Open PDFView at the publisherCite this paper

In brief

“Joint bias correction and downscaling of subseasonal forecasts via diffusion models” is a 2026 journal article by Maria Pyrina and 4 co-authors, published in Environmental Data Science. OpenAlex counts 2 citations as of 20 November 2026, which puts it in the top 6% of works published in 2026 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at Environmental Data Science.

Citations
2
Most cited in
2026 (2)
Field-weighted impact
2.80
References
27
Authors
5

Abstract

Subseasonal forecasts provide valuable guidance for decision-making but remain limited by systematic biases and coarse spatial resolution, particularly over regions with complex orography. Quantile mapping (QM) is widely used for post-processing because it enables effective bias correction and downscaling, yet it applies a distributional correction and therefore neglects the case-specific dependence between forecasts and observations. To move toward a more integrated approach, we explore a diffusion-based generative framework for simultaneous probabilistic bias correction and high-resolution downscaling, with lead time explicitly included as a conditioning variable. We employ a conditional denoising diffusion model (DM) trained on high-resolution gridded observations (2 km) and conditioned on coarse-resolution ensemble-mean subseasonal forecasts (36 km) from the European Centre for Medium-Range Weather Forecasts (ECMWF) Integrated Forecasting System (IFS) subseasonal system. We focus here on a univariate temperature model and on training strategies. By learning conditional distributions of observations given forecasts and lead time, diffusion-based generative models enable case-dependent corrections that exploit forecast–observation relationships. Two training configurations are examined to assess how lead-time conditioning and data availability influence the learning of biases. Results show that the DM recovers realistic fine-scale temperature patterns and achieves meaningful lead-time-dependent bias correction across subseasonal lead times, even when trained on relatively limited datasets. However, compared to QM, the diffusion-based forecasts exhibit lower skill in probabilistic metrics such as the continuous ranked probability score (CRPS) and discrimination for extremes. Overall, this work represents a first step toward lead-time-aware subseasonal post-processing using DMs and highlights directions for future methodological development.

Cite this paper

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

APA 7

Pyrina, M., Imamovic, A., Büeler, D., Spirig, C., & Domeisen, D. I. V. (2026). Joint bias correction and downscaling of subseasonal forecasts via diffusion models. Environmental Data Science, 5. https://doi.org/10.1017/eds.2026.10047

MLA 9

Pyrina, Maria, et al. “Joint bias correction and downscaling of subseasonal forecasts via diffusion models.” Environmental Data Science, vol. 5, 2026. https://doi.org/10.1017/eds.2026.10047.

Chicago

Pyrina, Maria, Adel Imamovic, Dominik Büeler, Christoph Spirig, and Daniela I. V. Domeisen. 2026. “Joint bias correction and downscaling of subseasonal forecasts via diffusion models.” Environmental Data Science 5. https://doi.org/10.1017/eds.2026.10047.

Harvard

Pyrina, M. et al. (2026) ‘Joint bias correction and downscaling of subseasonal forecasts via diffusion models’, Environmental Data Science, 5. doi:10.1017/eds.2026.10047.

IEEE

M. Pyrina, A. Imamovic, D. Büeler, C. Spirig, and D. I. V. Domeisen, “Joint bias correction and downscaling of subseasonal forecasts via diffusion models,” Environmental Data Science, vol. 5, 2026, doi: 10.1017/eds.2026.10047.

BibTeX

@article{pyrina2026joint,
  title     = {{Joint bias correction and downscaling of subseasonal forecasts via diffusion models}},
  author    = {Pyrina, Maria and Imamovic, Adel and Büeler, Dominik and Spirig, Christoph and Domeisen, Daniela I. V.},
  journal   = {Environmental Data Science},
  year      = {2026},
  volume    = {5},
  doi       = {10.1017/eds.2026.10047},
  url       = {https://doi.org/10.1017/eds.2026.10047}
}

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

  • subseasonal forecasting
  • bias correction
  • downscaling
  • diffusion models
  • denoising diffusion probabilistic models
  • conditional generative models
  • quantile mapping
  • temperature 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?

Pyrina, M., Imamovic, A., Büeler, D., Spirig, C., & Domeisen, D. I. V. (2026). Joint bias correction and downscaling of subseasonal forecasts via diffusion models. Environmental Data Science, 5. https://doi.org/10.1017/eds.2026.10047

How many times has this paper been cited?

2 times, according to OpenAlex on 20 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 Environmental Data Science: sign in and open the PDF from this page.

Who wrote this paper?

Maria Pyrina, Adel Imamovic, Dominik Büeler, Christoph Spirig, Daniela I. V. Domeisen.

What is the DOI of this paper?

10.1017/eds.2026.10047, permanently at https://doi.org/10.1017/eds.2026.10047. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 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.