Journal article · 2026 · Open access

Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models

Jingchen Pu, Mu Mu, Jie Feng, Hao Li

Quarterly Journal of the Royal Meteorological Society, 152(780) · Published 1 July 2026 · DOI 10.1002/qj.70257

Open PDFView at the publisherCite this paper

In brief

“Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models” is a 2026 journal article by Jingchen Pu and 3 co-authors, published in Quarterly Journal of the Royal Meteorological Society. OpenAlex counts 2 citations as of 20 November 2026, which puts it in the top 6% of works published in 2026 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
2
Most cited in
2026 (2)
Field-weighted impact
2.80
References
71
Authors
4

Abstract

Predictability analysis, which focuses on perturbation growth dynamics, is a key problem in both weather and climate prediction. Among all perturbations, the conditional nonlinear optimal perturbation (CNOP) explores maximum uncertainties in forecasts, which is fundamentally important for theoretical studies and applications. Traditionally, CNOPs are solved through iterative optimization of numerical weather prediction (NWP) systems. Their large computational demands pose significant challenges to long‐term predictability analysis. In our study, using a fast and accurate Artificial Intelligence (AI) model, i.e. FuXi, a low‐cost optimization framework for solving five‐day tropical cyclone (TC) CNOP is developed. For the first time, CNOPs that achieve the optimal (i.e., fastest) nonlinear development of long‐term TC forecast errors are solved, with their optimality and physical explainability verified. Results demonstrate that perturbations with specific spatial structures undergo significant development. In both AI and NWP models, AI‐based CNOPs exhibit rapid and physically consistent error growth across diverse TC cases, faster compared to random and lagged forecast perturbations. Furthermore, sensitivity analysis reveals that far‐environment systems and processes are more crucial for long‐term TC forecasts. Structural analyses of the CNOP emphasize the interactions between TC internal and external processes for rapid perturbation growth. The successful derivation of AI‐based CNOPs, with their rapid growth and physical explainability verified in both AI and NWP models, suggests that AI models can capture the most rapidly growing perturbation patterns and their subsequent nonlinear evolution. Thus, the potential of AI models is highlighted for advancing atmospheric predictability studies, including theoretical analysis, targeting observations and ensemble forecasts.

Cite this paper

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

APA 7

Pu, J., Mu, M., Feng, J., & Li, H. (2026). Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models. Quarterly Journal of the Royal Meteorological Society, 152(780). https://doi.org/10.1002/qj.70257

MLA 9

Pu, Jingchen, et al. “Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models.” Quarterly Journal of the Royal Meteorological Society, vol. 152, no. 780, 2026. https://doi.org/10.1002/qj.70257.

Chicago

Pu, Jingchen, Mu Mu, Jie Feng, and Hao Li. 2026. “Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models.” Quarterly Journal of the Royal Meteorological Society 152 (780). https://doi.org/10.1002/qj.70257.

Harvard

Pu, J. et al. (2026) ‘Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models’, Quarterly Journal of the Royal Meteorological Society, 152(780). doi:10.1002/qj.70257.

IEEE

J. Pu, M. Mu, J. Feng, and H. Li, “Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models,” Quarterly Journal of the Royal Meteorological Society, vol. 152, no. 780, 2026, doi: 10.1002/qj.70257.

BibTeX

@article{pu2026error,
  title     = {{Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models}},
  author    = {Pu, Jingchen and Mu, Mu and Feng, Jie and Li, Hao},
  journal   = {Quarterly Journal of the Royal Meteorological Society},
  year      = {2026},
  volume    = {152},
  number    = {780},
  doi       = {10.1002/qj.70257},
  url       = {https://doi.org/10.1002/qj.70257}
}

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 cyclones
  • conditional nonlinear optimal perturbation
  • predictability
  • error growth
  • machine learning
  • Fuxi
  • sensitivity analysis
  • atmospheric predictability

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?

Pu, J., Mu, M., Feng, J., & Li, H. (2026). Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models. Quarterly Journal of the Royal Meteorological Society, 152(780). https://doi.org/10.1002/qj.70257

How many times has this paper been cited?

2 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?

Jingchen Pu, Mu Mu, Jie Feng, Hao Li.

What is the DOI of this paper?

10.1002/qj.70257, permanently at https://doi.org/10.1002/qj.70257. 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.