Journal article · 2025 · Open access

Comparison of AI and NWP Models in Operational Severe Weather Forecasting: A Study on Tropical Cyclone Predictions

Yang Shi, Rong Hu, Naigeng Wu, Hualong Zhang, Xinhang Liu, Zhilin Zeng, Jing Zhu, Pucheng Han, Cong Luo, Hongyan Zhang, Jie He, Xiaoming Shi

Journal of Geophysical Research Machine Learning and Computation, 2(2) · Published 30 May 2025 · DOI 10.1029/2024jh000481

Open PDFView at the publisherCite this paper

In brief

“Comparison of AI and NWP Models in Operational Severe Weather Forecasting: A Study on Tropical Cyclone Predictions” is a 2025 journal article by Yang Shi and 11 co-authors, published in Journal of Geophysical Research Machine Learning and Computation. OpenAlex counts 23 citations as of 20 November 2026. It is open access under a CC BY-NC licence: the full text is free to read at Journal of Geophysical Research Machine Learning and Computation.

Citations
23
Most cited in
2026 (22)
Field-weighted impact
6.36
References
34
Authors
12

Abstract

Data‐driven artificial intelligence weather prediction (AIWP) models show great potential in weather forecasts, facilitating paradigm shift of prediction from a deductive to an inductive inference. However, this shift raises concerns regarding the performance of the AIWP models in severe weather forecasting. Tropical cyclones (TCs) are one of the most typical cases of severe weather prediction. In this study, we compare Western Pacific TCs in 2023 produced by the AIWP model, Pangu‐Weather, with those generated by numerical weather prediction (NWP) models, specifically the European Center for Medium‐Range Weather Forecasts (ECMWF) and the National Centers for Environmental Prediction (NCEP), in the operational context. We analyze the impact of different initial conditions (ICs) on AIWP models, representative by Pangu‐Weather, in TC forecasting. Our analysis includes statistical evaluation of forecast skill related to TC activity, track, intensity, and a case study on the physical structure of a TC. The Pangu‐Weather model exhibits superior forecast skills compared to the NWP model regarding TC tracks and environmental variables within TC activity domains, particularly at longer forecast lead times. However, the overly smooth forecasts of Pangu‐Weather and the coarse‐resolution ICs with reduced information of TCs potentially lead to the underestimation of intensity and a weakened dynamic‐thermodynamic structure of TCs. Also, Pangu‐Weather shows low sensitivity to ICs concerning TC structure and intensity. Hybrid models combining physical processes with data‐driven approaches may enhance AIWP performance for severe weather forecasting.

Cite this paper

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

APA 7

Shi, Y., Hu, R., Wu, N., Zhang, H., Liu, X., Zeng, Z., Zhu, J., Han, P., Luo, C., Zhang, H., He, J., & Shi, X. (2025). Comparison of AI and NWP Models in Operational Severe Weather Forecasting: A Study on Tropical Cyclone Predictions. Journal of Geophysical Research Machine Learning and Computation, 2(2). https://doi.org/10.1029/2024jh000481

MLA 9

Shi, Yang, et al. “Comparison of AI and NWP Models in Operational Severe Weather Forecasting: A Study on Tropical Cyclone Predictions.” Journal of Geophysical Research Machine Learning and Computation, vol. 2, no. 2, 2025. https://doi.org/10.1029/2024jh000481.

Chicago

Shi, Yang, Rong Hu, Naigeng Wu, Hualong Zhang, Xinhang Liu, Zhilin Zeng, Jing Zhu, et al. 2025. “Comparison of AI and NWP Models in Operational Severe Weather Forecasting: A Study on Tropical Cyclone Predictions.” Journal of Geophysical Research Machine Learning and Computation 2 (2). https://doi.org/10.1029/2024jh000481.

Harvard

Shi, Y. et al. (2025) ‘Comparison of AI and NWP Models in Operational Severe Weather Forecasting: A Study on Tropical Cyclone Predictions’, Journal of Geophysical Research Machine Learning and Computation, 2(2). doi:10.1029/2024jh000481.

IEEE

Y. Shi et al., “Comparison of AI and NWP Models in Operational Severe Weather Forecasting: A Study on Tropical Cyclone Predictions,” Journal of Geophysical Research Machine Learning and Computation, vol. 2, no. 2, 2025, doi: 10.1029/2024jh000481.

BibTeX

@article{shi2025comparison,
  title     = {{Comparison of AI and NWP Models in Operational Severe Weather Forecasting: A Study on Tropical Cyclone Predictions}},
  author    = {Shi, Yang and Hu, Rong and Wu, Naigeng and Zhang, Hualong and Liu, Xinhang and Zeng, Zhilin and Zhu, Jing and Han, Pucheng and Luo, Cong and Zhang, Hongyan and He, Jie and Shi, Xiaoming},
  journal   = {Journal of Geophysical Research Machine Learning and Computation},
  year      = {2025},
  volume    = {2},
  number    = {2},
  doi       = {10.1029/2024jh000481},
  url       = {https://doi.org/10.1029/2024jh000481}
}

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

  • tropical cyclone forecasting
  • Pangu-Weather
  • numerical weather prediction
  • ECMWF
  • NCEP
  • sensitivity to initial conditions
  • tropical cyclone tracks
  • tropical cyclone intensity

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?

Shi, Y., Hu, R., Wu, N., Zhang, H., Liu, X., Zeng, Z., Zhu, J., Han, P., Luo, C., Zhang, H., He, J., & Shi, X. (2025). Comparison of AI and NWP Models in Operational Severe Weather Forecasting: A Study on Tropical Cyclone Predictions. Journal of Geophysical Research Machine Learning and Computation, 2(2). https://doi.org/10.1029/2024jh000481

How many times has this paper been cited?

23 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 Journal of Geophysical Research Machine Learning and Computation: sign in and open the PDF from this page.

Who wrote this paper?

Yang Shi, Rong Hu, Naigeng Wu, Hualong Zhang, Xinhang Liu, Zhilin Zeng, Jing Zhu, Pucheng Han, Cong Luo, Hongyan Zhang, Jie He, Xiaoming Shi.

What is the DOI of this paper?

10.1029/2024jh000481, permanently at https://doi.org/10.1029/2024jh000481. 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.