Preprint · 2025 · Open access

Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework

Shuangshuang He, Hongli Liang, Yuan‐Ting Zhang, Xingyuan Yuan

arXiv (Cornell University) · Published 6 January 2025 · DOI 10.48550/arxiv.2501.02905

Open PDFView at the publisherCite this paper

In brief

“Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework” is a 2025 preprint by Shuangshuang He and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 5 citations as of 20 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
5
Most cited in
2026 (4)
References
39
Authors
4

Abstract

High-resolution precipitation forecasts are crucial for providing accurate weather prediction and supporting effective responses to extreme weather events. Traditional numerical models struggle with stochastic subgrid-scale processes, while recent deep learning models often produce blurry results. To address these challenges, we propose a physics-inspired deep learning framework for high-resolution (0.05\textdegree{} $\times$ 0.05\textdegree{}) ensemble precipitation forecasting. Trained on ERA5 and CMPA high-resolution precipitation datasets, the framework integrates deterministic and probabilistic components. The deterministic model, based on a 3D SwinTransformer, captures average precipitation at mesoscale resolution and incorporates strategies to enhance performance, particularly for moderate to heavy rainfall. The probabilistic model employs conditional diffusion in latent space to account for uncertainties in residual precipitation at convective scales. During inference, ensemble members are generated by repeatedly sampling latent variables, enabling the model to represent precipitation uncertainty. Our model significantly enhances spatial resolution and forecast accuracy. Rank histogram shows that the ensemble system is reliable and unbiased. In a case study of heavy precipitation in southern China, the model outputs align more closely with observed precipitation distributions than ERA5, demonstrating superior capability in capturing extreme precipitation events. Additionally, 5-day real-time forecasts show good performance in terms of CSI scores.

Cite this paper

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

APA 7

He, S., Liang, H., Zhang, Y., & Yuan, X. (2025). Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.02905

MLA 9

He, Shuangshuang, et al. “Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2501.02905.

Chicago

He, Shuangshuang, Hongli Liang, Yuan‐Ting Zhang, and Xingyuan Yuan. 2025. “Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.02905.

Harvard

He, S. et al. (2025) ‘Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework’, arXiv (Cornell University). doi:10.48550/arxiv.2501.02905.

IEEE

S. He, H. Liang, Y. Zhang, and X. Yuan, “Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2501.02905.

BibTeX

@misc{he2025skillful,
  title     = {{Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework}},
  author    = {He, Shuangshuang and Liang, Hongli and Zhang, Yuan‐Ting and Yuan, Xingyuan},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2501.02905},
  url       = {https://doi.org/10.48550/arxiv.2501.02905}
}

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

  • high-resolution precipitation
  • physics-informed deep learning
  • Swin Transformer
  • conditional diffusion models
  • latent space
  • precipitation uncertainty
  • heavy rainfall
  • subgrid-scale processes

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?

He, S., Liang, H., Zhang, Y., & Yuan, X. (2025). Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.02905

How many times has this paper been cited?

5 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?

Shuangshuang He, Hongli Liang, Yuan‐Ting Zhang, Xingyuan Yuan.

What is the DOI of this paper?

10.48550/arxiv.2501.02905, permanently at https://doi.org/10.48550/arxiv.2501.02905. 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.