Preprint · 2026 · Open access

Global reanalysis from observations alone with machine learning

Peter Lean, Ewan Pinnington, Patrick Laloyaux, Mihai Alexe, Eulalie Boucher, Simon T. K. Lang, Tomáš Kráľ, Paul Poli, Hans Hersbach, Niels Bormann, Matthew Chantry, Anthony Mcnally

arXiv (Cornell University) · Published 8 July 2026 · DOI 10.48550/arxiv.2607.07879

Free PDFView at the publisherCite this paper

In brief

“Global reanalysis from observations alone with machine learning” is a 2026 preprint by Peter Lean and 11 co-authors, published in arXiv (Cornell University). OpenAlex counts 4 citations as of 15 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at arXiv (Cornell University).

Citations
4
Most cited in
2026 (4)
References
39
Authors
12

Abstract

Earth system reanalysis datasets are foundational for weather and climate research and provide the gridded training data used by most machine learning weather prediction systems. Here we show results from a prototype system that suggest that machine learning models trained only on Earth system observations can potentially be used to generate multi-decade global reanalyses without using physics-based numerical models. The resulting gridded fields capture large-scale atmospheric structure and variability across multiple timescales, while exhibiting signs of physical coherence in several key dynamical diagnostics. Evaluations of the prototype against held-out independent atmospheric observations indicate that the root mean square vector error of upper-level winds is close to that of ERA5 when compared at a consistent resolution, and that the standard deviation of the error at the surface is between that of 4th- and 5th-generation ECMWF reanalyses (ERA-Interim and ERA5). Furthermore, while traditional reanalysis production is computationally expensive, typically taking several years to produce, the reanalysis presented here was generated during the course of a single working day. These results suggest that observation-trained machine learning models offer a promising new approach for reanalysis production from observations alone.

Cite this paper

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

APA 7

Lean, P., Pinnington, E., Laloyaux, P., Alexe, M., Boucher, E., Lang, S. T. K., Kráľ, T., Poli, P., Hersbach, H., Bormann, N., Chantry, M., & Mcnally, A. (2026). Global reanalysis from observations alone with machine learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.07879

MLA 9

Lean, Peter, et al. “Global reanalysis from observations alone with machine learning.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2607.07879.

Chicago

Lean, Peter, Ewan Pinnington, Patrick Laloyaux, Mihai Alexe, Eulalie Boucher, Simon T. K. Lang, Tomáš Kráľ, et al. 2026. “Global reanalysis from observations alone with machine learning.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.07879.

Harvard

Lean, P. et al. (2026) ‘Global reanalysis from observations alone with machine learning’, arXiv (Cornell University). doi:10.48550/arxiv.2607.07879.

IEEE

P. Lean et al., “Global reanalysis from observations alone with machine learning,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2607.07879.

BibTeX

@misc{lean2026global,
  title     = {{Global reanalysis from observations alone with machine learning}},
  author    = {Lean, Peter and Pinnington, Ewan and Laloyaux, Patrick and Alexe, Mihai and Boucher, Eulalie and Lang, Simon T. K. and Kráľ, Tomáš and Poli, Paul and Hersbach, Hans and Bormann, Niels and Chantry, Matthew and Mcnally, Anthony},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2607.07879},
  url       = {https://doi.org/10.48550/arxiv.2607.07879}
}

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

  • global reanalysis
  • atmospheric reanalysis
  • upper-air winds
  • atmospheric variability
  • ERA5 comparison

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?

Lean, P., Pinnington, E., Laloyaux, P., Alexe, M., Boucher, E., Lang, S. T. K., Kráľ, T., Poli, P., Hersbach, H., Bormann, N., Chantry, M., & Mcnally, A. (2026). Global reanalysis from observations alone with machine learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.07879

How many times has this paper been cited?

4 times, according to OpenAlex on 15 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: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Peter Lean, Ewan Pinnington, Patrick Laloyaux, Mihai Alexe, Eulalie Boucher, Simon T. K. Lang, Tomáš Kráľ, Paul Poli, Hans Hersbach, Niels Bormann, Matthew Chantry, Anthony Mcnally.

What is the DOI of this paper?

10.48550/arxiv.2607.07879. The permanent link is https://doi.org/10.48550/arxiv.2607.07879.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.