Preprint · 2026 · Open access

Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting

Shiqi Zhang, Pan Mu, Cheng Huang, Hanting Yan, Yuchao Zhu, Jinglin Zhang, Shengyong Chen, Shoujuan Shu, Cong Bai

arXiv (Cornell University) · Published 19 August 2026 · DOI 10.48550/arxiv.2608.18500

Open PDFView at the publisherCite this paper

In brief

“Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting” is a 2026 preprint by Shiqi Zhang and 8 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
0
References
41
Authors
9

Abstract

Tropical cyclones (TCs) pose severe risks from strong winds and heavy rainfall. However, forecasting their track and intensity remains challenging due to chaotic atmosphere and the rapid amplification of initial condition errors, leading to growing forecast uncertainty. While numerical weather prediction (NWP) and deep learning models have made progress, they remain computationally demanding and often fail under complex meteorological scenarios. Here, we present Tianmu-TC, a physics-constraints generative framework for global TC forecasting. Trained on Western North Pacific data, Tianmu-TC leverages physics-constraints to generate controllable outputs with reduced uncertainty thus improving forecast reliability. Experiments show Tianmu-TC outperforms deterministic and ensemble meteorological artificial intelligence models and authoritative NWP systems such as ECMWF in global ocean basins, with significantly lower computational cost. We further show Tianmu-TC performs well in challenging scenarios such as data sparsity, anomaly tracks, rapid intensification and weakening. These findings suggest physics-constraints generative AI offers a promising approach for reliable, efficient global TC forecasting.

Cite this paper

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

APA 7

Zhang, S., Mu, P., Huang, C., Yan, H., Zhu, Y., Zhang, J., Chen, S., Shu, S., & Bai, C. (2026). Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.18500

MLA 9

Zhang, Shiqi, et al. “Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2608.18500.

Chicago

Zhang, Shiqi, Pan Mu, Cheng Huang, Hanting Yan, Yuchao Zhu, Jinglin Zhang, Shengyong Chen, Shoujuan Shu, and Cong Bai. 2026. “Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.18500.

Harvard

Zhang, S. et al. (2026) ‘Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting’, arXiv (Cornell University). doi:10.48550/arxiv.2608.18500.

IEEE

S. Zhang et al., “Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2608.18500.

BibTeX

@misc{zhang2026tianmu,
  title     = {{Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting}},
  author    = {Zhang, Shiqi and Mu, Pan and Huang, Cheng and Yan, Hanting and Zhu, Yuchao and Zhang, Jinglin and Chen, Shengyong and Shu, Shoujuan and Bai, Cong},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2608.18500},
  url       = {https://doi.org/10.48550/arxiv.2608.18500}
}

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 › Tropical and Extratropical Cyclones Research

  • tropical cyclone forecasting
  • data sparsity
  • rapid intensification
  • tropical cyclone weakening
  • western North Pacific
  • computational complexity reduction

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?

Zhang, S., Mu, P., Huang, C., Yan, H., Zhu, Y., Zhang, J., Chen, S., Shu, S., & Bai, C. (2026). Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.18500

How many times has this paper been cited?

0 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?

Shiqi Zhang, Pan Mu, Cheng Huang, Hanting Yan, Yuchao Zhu, Jinglin Zhang, Shengyong Chen, Shoujuan Shu, Cong Bai.

What is the DOI of this paper?

10.48550/arxiv.2608.18500, permanently at https://doi.org/10.48550/arxiv.2608.18500. 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.