Journal article · 2025 · Open access

Advancing seasonal prediction of tropical cyclone activity with a hybrid AI-physics climate model

Gan Zhang, Megha Rao, Janni Yuval, Ming Zhao

Environmental Research Letters, 20(9), 094031 · Published 6 August 2025 · DOI 10.1088/1748-9326/adf864

Open full textCite this paper

In brief

“Advancing seasonal prediction of tropical cyclone activity with a hybrid AI-physics climate model” is a 2025 journal article by Gan Zhang and 3 co-authors, published in Environmental Research Letters. OpenAlex counts 19 citations as of 20 November 2026, which puts it in the top 5% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Environmental Research Letters.

Citations
19
Most cited in
2026 (16)
Field-weighted impact
4.91
References
52
Authors
4

Abstract

Machine learning (ML) models are successful with weather forecasting and have shown progress in climate simulations, yet leveraging them for useful climate predictions needs exploration. Here we show this feasibility using neural general circulation model (NeuralGCM), a hybrid ML-physics atmospheric model developed by Google, for seasonal predictions of large-scale atmospheric variability and Northern Hemisphere tropical cyclone (TC) activity. Inspired by physical model studies, we simplify boundary conditions, assuming sea surface temperature and sea ice follow their climatological cycle but persist anomalies present at the initialization time. With such forcings, NeuralGCM can generate 100 simulation days in ∼8 min with a single graphics processing unit while simulating realistic atmospheric circulation and TC climatology patterns. This configuration yields useful seasonal predictions (July–November) for the tropical atmosphere and various TC activity metrics. Notably, the predicted and observed TC frequency in the North Atlantic and East Pacific basins are significantly correlated during 1990–2023 (r = ∼0.7), suggesting prediction skill comparable to existing physical GCMs. Despite challenges associated with model resolution and simplified boundary forcings, the model-predicted interannual variations demonstrate significant correlations with the observed sub-basin TC tracks (p < 0.1) and basin-wide accumulated cyclone energy (ACE) (p < 0.01) of the North Atlantic and North Pacific basins. These findings highlight the promise of leveraging ML models with physical insights to model TC risks and deliver seamless weather-climate predictions.

Cite this paper

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

APA 7

Zhang, G., Rao, M., Yuval, J., & Zhao, M. (2025). Advancing seasonal prediction of tropical cyclone activity with a hybrid AI-physics climate model. Environmental Research Letters, 20(9), 094031. https://doi.org/10.1088/1748-9326/adf864

MLA 9

Zhang, Gan, et al. “Advancing seasonal prediction of tropical cyclone activity with a hybrid AI-physics climate model.” Environmental Research Letters, vol. 20, no. 9, 2025, p. 094031. https://doi.org/10.1088/1748-9326/adf864.

Chicago

Zhang, Gan, Megha Rao, Janni Yuval, and Ming Zhao. 2025. “Advancing seasonal prediction of tropical cyclone activity with a hybrid AI-physics climate model.” Environmental Research Letters 20 (9): 094031. https://doi.org/10.1088/1748-9326/adf864.

Harvard

Zhang, G. et al. (2025) ‘Advancing seasonal prediction of tropical cyclone activity with a hybrid AI-physics climate model’, Environmental Research Letters, 20(9), p. 094031. doi:10.1088/1748-9326/adf864.

IEEE

G. Zhang, M. Rao, J. Yuval, and M. Zhao, “Advancing seasonal prediction of tropical cyclone activity with a hybrid AI-physics climate model,” Environmental Research Letters, vol. 20, no. 9, p. 094031, 2025, doi: 10.1088/1748-9326/adf864.

BibTeX

@article{zhang2025advancing,
  title     = {{Advancing seasonal prediction of tropical cyclone activity with a hybrid AI-physics climate model}},
  author    = {Zhang, Gan and Rao, Megha and Yuval, Janni and Zhao, Ming},
  journal   = {Environmental Research Letters},
  year      = {2025},
  volume    = {20},
  number    = {9},
  pages     = {094031},
  doi       = {10.1088/1748-9326/adf864},
  url       = {https://doi.org/10.1088/1748-9326/adf864}
}

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 activity
  • seasonal forecasting
  • North Atlantic tropical cyclones
  • accumulated cyclone energy
  • tropical cyclone tracks
  • sea surface temperature anomalies
  • sea ice anomalies
  • interannual variability

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, G., Rao, M., Yuval, J., & Zhao, M. (2025). Advancing seasonal prediction of tropical cyclone activity with a hybrid AI-physics climate model. Environmental Research Letters, 20(9), 094031. https://doi.org/10.1088/1748-9326/adf864

How many times has this paper been cited?

19 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 Environmental Research Letters: sign in and open the full text from this page.

Who wrote this paper?

Gan Zhang, Megha Rao, Janni Yuval, Ming Zhao.

What is the DOI of this paper?

10.1088/1748-9326/adf864, permanently at https://doi.org/10.1088/1748-9326/adf864. 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.