Journal article · 2026 · Open access

A multi‐scale loss formulation for learning a probabilistic model with proper score optimisation

Simon T. K. Lang, Martin Leutbecher, Pedro Maciel

Quarterly Journal of the Royal Meteorological Society · Published 4 September 2026 · DOI 10.1002/qj.70291

Open PDFView at the publisherCite this paper

In brief

“A multi‐scale loss formulation for learning a probabilistic model with proper score optimisation” is a 2026 journal article by Simon T. K. Lang and 2 co-authors, published in Quarterly Journal of the Royal Meteorological Society. OpenAlex counts 14 citations as of 20 November 2026, which puts it in the top 5% of works published in 2026 by citations. It is open access under a CC BY-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
14
Most cited in
2026 (11)
Field-weighted impact
15.43
References
26
Authors
3

Abstract

We assess the impact of a multi‐scale loss formulation for training probabilistic machine‐learned weather forecasting models. The multi‐scale loss is tested in AIFS‐CRPS, a machine‐learned weather forecasting model developed at the European Centre for Medium‐Range Weather Forecasts. AIFS‐CRPS is trained by directly optimising the almost fair continuous ranked probability score. The multi‐scale loss better constrains small‐scale variability without negatively impacting forecast skill. This opens up promising directions for future work in scale‐aware model training.

Cite this paper

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

APA 7

Lang, S. T. K., Leutbecher, M., & Maciel, P. (2026). A multi‐scale loss formulation for learning a probabilistic model with proper score optimisation. Quarterly Journal of the Royal Meteorological Society. https://doi.org/10.1002/qj.70291

MLA 9

Lang, Simon T. K., et al. “A multi‐scale loss formulation for learning a probabilistic model with proper score optimisation.” Quarterly Journal of the Royal Meteorological Society, 2026. https://doi.org/10.1002/qj.70291.

Chicago

Lang, Simon T. K., Martin Leutbecher, and Pedro Maciel. 2026. “A multi‐scale loss formulation for learning a probabilistic model with proper score optimisation.” Quarterly Journal of the Royal Meteorological Society. https://doi.org/10.1002/qj.70291.

Harvard

Lang, S. T. K., Leutbecher, M. and Maciel, P. (2026) ‘A multi‐scale loss formulation for learning a probabilistic model with proper score optimisation’, Quarterly Journal of the Royal Meteorological Society. doi:10.1002/qj.70291.

IEEE

S. T. K. Lang, M. Leutbecher, and P. Maciel, “A multi‐scale loss formulation for learning a probabilistic model with proper score optimisation,” Quarterly Journal of the Royal Meteorological Society, 2026, doi: 10.1002/qj.70291.

BibTeX

@article{lang2026multi,
  title     = {{A multi‐scale loss formulation for learning a probabilistic model with proper score optimisation}},
  author    = {Lang, Simon T. K. and Leutbecher, Martin and Maciel, Pedro},
  journal   = {Quarterly Journal of the Royal Meteorological Society},
  year      = {2026},
  doi       = {10.1002/qj.70291},
  url       = {https://doi.org/10.1002/qj.70291}
}

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

  • probabilistic weather forecasting
  • proper scoring rules
  • continuous ranked probability score
  • small-scale variability
  • forecast skill

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?

Lang, S. T. K., Leutbecher, M., & Maciel, P. (2026). A multi‐scale loss formulation for learning a probabilistic model with proper score optimisation. Quarterly Journal of the Royal Meteorological Society. https://doi.org/10.1002/qj.70291

How many times has this paper been cited?

14 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Simon T. K. Lang, Martin Leutbecher, Pedro Maciel.

What is the DOI of this paper?

10.1002/qj.70291, permanently at https://doi.org/10.1002/qj.70291. 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.