Preprint · 2026 · Open access
Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts
arXiv (Cornell University) · Published 28 May 2026 · DOI 10.48550/arxiv.2605.30184
In brief
“Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts” is a 2026 preprint by Fanny Lehmann and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 11 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 11
- Most cited in
- 2026 (11)
- References
- 1
- Authors
- 7
Abstract
While AI weather models excel at short-to-medium range forecasts (up to 15 days), they frequently suffer from ill-defined "instabilities" when rolled out over longer horizons. This work addresses the lack of a formal taxonomy by categorizing these failures into three distinct regimes: blow-up, drift, and loss of seasonality, through year-long rollouts of nine state-of-the-art AI weather models. Our analysis reveals that stability hinges on the treatment of small spatio-temporal scales: unstable models amplify high-frequency energy, while stable models act as denoisers when noise is added to their inputs. Far from reducing these models to mere stochastic parrots, our findings highlight that stable models generate unique weather trajectories, conditioned on the initial state. We verify our findings through ablation studies on architectural design choices, conducted using state-of-the-art Vision Transformer (ViT) AI weather model architectures.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Lehmann, F., Özdemir, F., Cheng, Y., Hoefler, T., Schemm, S., Soja, B. S., & Mishra, S. (2026). Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.30184
MLA 9
Lehmann, Fanny, et al. “Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2605.30184.
Chicago
Lehmann, Fanny, Fırat Özdemir, Yun Cheng, Torsten Hoefler, Sebastian Schemm, Benedikt S. Soja, and Siddhartha Mishra. 2026. “Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.30184.
Harvard
Lehmann, F. et al. (2026) ‘Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts’, arXiv (Cornell University). doi:10.48550/arxiv.2605.30184.
IEEE
F. Lehmann et al., “Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2605.30184.
BibTeX
@misc{lehmann2026weather,
title = {{Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts}},
author = {Lehmann, Fanny and Özdemir, Fırat and Cheng, Yun and Hoefler, Torsten and Schemm, Sebastian and Soja, Benedikt S. and Mishra, Siddhartha},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2605.30184},
url = {https://doi.org/10.48550/arxiv.2605.30184}
}
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
- long-term forecasting
- drift instability
- spatio-temporal scales
- noise reduction
- vision transformer
- forecast benchmarking
- model architecture
Work with this paper
Most-cited papers in Earth and Planetary Sciences
- The ERA5 global reanalysisHans Hersbach, Bill Bell, Paul Berrisford and 40 more · Quarterly Journal of the Royal Meteorological Society · 2020 · 35,424 citations
- The NCEP/NCAR 40-Year Reanalysis ProjectEugenia Kalnay, Masao Kanamitsu, Robert E. Kistler and 19 more · Bulletin of the American Meteorological Society · 1996 · 28,486 citations
- Chemical and isotopic systematics of oceanic basalts: implications for mantle composition and processesShen‐Su Sun, W. F. McDonough · Geological Society London Special Publications · 1989 · 26,603 citations
- The ERA‐Interim reanalysis: configuration and performance of the data assimilation systemDick P. Dee, Sakari M. Uppala, A. J. Simmons and 33 more · Quarterly Journal of the Royal Meteorological Society · 2011 · 25,245 citations
- PAST: PALEONTOLOGICAL STATISTICAL SOFTWARE PACKAGE FOR EDUCATION AND DATA ANALYSISØyvind Hammer, David A. T. Harper, Paul D. Ryan · 2001 · 17,871 citations
Questions about this paper
How do I cite this paper in APA style?
Lehmann, F., Özdemir, F., Cheng, Y., Hoefler, T., Schemm, S., Soja, B. S., & Mishra, S. (2026). Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.30184
How many times has this paper been cited?
11 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?
Fanny Lehmann, Fırat Özdemir, Yun Cheng, Torsten Hoefler, Sebastian Schemm, Benedikt S. Soja, Siddhartha Mishra.
What is the DOI of this paper?
10.48550/arxiv.2605.30184. The permanent link is https://doi.org/10.48550/arxiv.2605.30184.
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.