Journal article · 2026 · Open access

Neural general circulation models for modeling precipitation

Janni Yuval, Ian Langmore, Dmitrii Kochkov, Stephan Hoyer

Science Advances, 12(2), eadv6891 · Published 7 January 2026 · DOI 10.1126/sciadv.adv6891

Open PDFView at the publisherCite this paper

In brief

“Neural general circulation models for modeling precipitation” is a 2026 journal article by Janni Yuval and 3 co-authors, published in Science Advances. OpenAlex counts 39 citations as of 20 November 2026, which puts it in the top 2% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Science Advances.

Citations
39
Most cited in
2026 (33)
Field-weighted impact
46.28
References
71
Authors
4

Abstract

General circulation models (GCMs) struggle to accurately simulate precipitation, particularly extremes and the diurnal cycle, which are crucial for both human activities and natural processes. Although hybrid models combining machine learning and physics offer a promising avenue to improve the simulation of precipitation, they have yet to outperform existing GCMs. Here, we present a hybrid model built on the differentiable NeuralGCM framework. This differentiability facilitates direct training on satellite-based precipitation observations, unlike previous attempts at hybrid models that relied on high-resolution simulations as training data. Our model runs at 2.8° resolution and, in the context of climate, demonstrates substantial improvements over existing GCMs, the ERA5 reanalysis, and a global cloud-resolving model in simulating precipitation. In the context of mid-range precipitation forecasting, it outperforms the ECMWF ensemble. This advance paves the way for more reliable simulations of current climate and demonstrates how training on observations can be used to improve GCMs.

Cite this paper

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

APA 7

Yuval, J., Langmore, I., Kochkov, D., & Hoyer, S. (2026). Neural general circulation models for modeling precipitation. Science Advances, 12(2), eadv6891. https://doi.org/10.1126/sciadv.adv6891

MLA 9

Yuval, Janni, et al. “Neural general circulation models for modeling precipitation.” Science Advances, vol. 12, no. 2, 2026, p. eadv6891. https://doi.org/10.1126/sciadv.adv6891.

Chicago

Yuval, Janni, Ian Langmore, Dmitrii Kochkov, and Stephan Hoyer. 2026. “Neural general circulation models for modeling precipitation.” Science Advances 12 (2): eadv6891. https://doi.org/10.1126/sciadv.adv6891.

Harvard

Yuval, J. et al. (2026) ‘Neural general circulation models for modeling precipitation’, Science Advances, 12(2), p. eadv6891. doi:10.1126/sciadv.adv6891.

IEEE

J. Yuval, I. Langmore, D. Kochkov, and S. Hoyer, “Neural general circulation models for modeling precipitation,” Science Advances, vol. 12, no. 2, p. eadv6891, 2026, doi: 10.1126/sciadv.adv6891.

BibTeX

@article{yuval2026neural,
  title     = {{Neural general circulation models for modeling precipitation}},
  author    = {Yuval, Janni and Langmore, Ian and Kochkov, Dmitrii and Hoyer, Stephan},
  journal   = {Science Advances},
  year      = {2026},
  volume    = {12},
  number    = {2},
  pages     = {eadv6891},
  doi       = {10.1126/sciadv.adv6891},
  url       = {https://doi.org/10.1126/sciadv.adv6891}
}

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

  • precipitation simulation
  • satellite precipitation observations
  • heavy rainfall
  • diurnal cycle
  • climate modeling

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?

Yuval, J., Langmore, I., Kochkov, D., & Hoyer, S. (2026). Neural general circulation models for modeling precipitation. Science Advances, 12(2), eadv6891. https://doi.org/10.1126/sciadv.adv6891

How many times has this paper been cited?

39 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 Science Advances: sign in and open the PDF from this page.

Who wrote this paper?

Janni Yuval, Ian Langmore, Dmitrii Kochkov, Stephan Hoyer.

What is the DOI of this paper?

10.1126/sciadv.adv6891, permanently at https://doi.org/10.1126/sciadv.adv6891. 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.