Preprint · 2026 · Open access

U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

Salva Rühling Cachay, Duncan Watson‐Parris, Rose Yu

arXiv (Cornell University) · Published 10 April 2026 · DOI 10.48550/arxiv.2604.09041

Free PDFView at the publisherCite this paper

In brief

“U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster” is a 2026 preprint by Salva Rühling Cachay and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 8 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
8
Most cited in
2026 (8)
References
40
Authors
3

Abstract

AI-based weather forecasting now rivals traditional physics-based ensembles, but state-of-the-art (SOTA) models rely on specialized architectures and massive computational budgets, creating a high barrier to entry. We demonstrate that such complexity is unnecessary for frontier performance. We introduce \ours, a probabilistic forecaster built on a standard U-Net backbone trained with a simple recipe: deterministic pre-training on Mean Absolute Error followed by short probabilistic fine-tuning on the Continuous Ranked Probability Score (CRPS) using Monte Carlo Dropout for stochasticity. As a result, our model matches or exceeds the probabilistic skill of GenCast and IFS ENS at $1.5^\circ$ resolution while reducing training compute by over $10\times$ compared to leading CRPS-based models and inference latency by over $10\times$ compared to diffusion-based models. U-Cast trains in under 12 H200 GPU-days and generates a 15-day ensemble forecast in 3 seconds. These results suggest that scalable, general-purpose architectures paired with efficient training curricula can match complex domain-specific designs at a fraction of the cost, opening the training of frontier probabilistic weather models to the broader community.

Cite this paper

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

APA 7

Cachay, S. R., Watson‐Parris, D., & Yu, R. (2026). U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.09041

MLA 9

Cachay, Salva Rühling, et al. “U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2604.09041.

Chicago

Cachay, Salva Rühling, Duncan Watson‐Parris, and Rose Yu. 2026. “U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.09041.

Harvard

Cachay, S. R., Watson‐Parris, D. and Yu, R. (2026) ‘U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster’, arXiv (Cornell University). doi:10.48550/arxiv.2604.09041.

IEEE

S. R. Cachay, D. Watson‐Parris, and R. Yu, “U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2604.09041.

BibTeX

@misc{cachay2026cast,
  title     = {{U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster}},
  author    = {Cachay, Salva Rühling and Watson‐Parris, Duncan and Yu, Rose},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2604.09041},
  url       = {https://doi.org/10.48550/arxiv.2604.09041}
}

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
  • U-Net
  • Monte Carlo dropout
  • continuous ranked probability score
  • ensemble forecasting
  • low-cost training
  • inference efficiency

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?

Cachay, S. R., Watson‐Parris, D., & Yu, R. (2026). U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.09041

How many times has this paper been cited?

8 times, according to OpenAlex on 16 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?

Salva Rühling Cachay, Duncan Watson‐Parris, Rose Yu.

What is the DOI of this paper?

10.48550/arxiv.2604.09041. The permanent link is https://doi.org/10.48550/arxiv.2604.09041.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.