Journal article · 2026 · Open access

Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models

Milton S. Gomez, Louis Poulain--Auzéau, Alexis Berne, Tom Beucler

Artificial Intelligence for the Earth Systems, 5(2) · Published 6 March 2026 · DOI 10.1175/aies-d-25-0073.1

Open PDFView at the publisherCite this paper

In brief

“Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models” is a 2026 journal article by Milton S. Gomez and 3 co-authors, published in Artificial Intelligence for the Earth Systems. OpenAlex counts 8 citations as of 20 November 2026, which puts it in the top 2% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
8
Most cited in
2026 (8)
Field-weighted impact
11.39
References
71
Authors
4

Abstract

Numerical weather prediction (NWP) models that integrate coupled physical equations forward in time are the traditional tools for simulating atmospheric processes and forecasting weather. With recent advancements in deep learning, artificial intelligence (AI)-based weather prediction models that rely on neural network architectures—neural weather models (NeWMs)—have emerged as competent medium-range NWP emulators, with performances that compare favorably to state-of-the-art NWP models. However, they are commonly trained on reanalyses with limited spatial resolution (e.g., 0.25° horizontal grid spacing), which smooths out key features of weather systems. For example, tropical cyclones (TCs)—among the most impactful weather events due to their devastating effects on human activities—are challenging to forecast, as extrema are smoothed in deterministic forecasts at 0.25° resolution. To address this, we use our best observational estimates of wind gusts and minimum sea level pressure to train a hierarchy of postprocessing models on NeWM outputs. Applied to Pangu-Weather and FourCastNet v2, the postprocessing models produce accurate and reliable forecasts of TC intensity up to 5 days ahead. Our postprocessing algorithm is tracking independent, preventing full misses, and we demonstrate that even linear models extract predictive information from NeWM outputs beyond what is encoded in their initial conditions. While spatial masking improves probabilistic forecast consistency, we do not find clear advantages of convolutional architectures over simple multilayer perceptrons for our NeWM postprocessing purposes. Overall, by combining the efficiency of NeWMs with a lightweight, tracking-independent postprocessing framework, our approach improves the accessibility of global TC intensity forecasts, marking a step toward their democratization. Significance Statement Forecasting tropical cyclone intensity via purely data-driven methods is limited to short lead times without large-scale atmospheric context. Artificial intelligence (AI) global weather models predict this context but at resolutions too coarse to resolve extremes such as those associated with tropical cyclones. We show that postprocessing these global models with neural networks yields well-calibrated probabilistic forecasts of tropical cyclone intensity up to 5 days ahead. This work furthers end-to-end, fully data-driven forecasting of weather extremes.

Cite this paper

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

APA 7

Gomez, M. S., Poulain--Auzéau, L., Berne, A., & Beucler, T. (2026). Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models. Artificial Intelligence for the Earth Systems, 5(2). https://doi.org/10.1175/aies-d-25-0073.1

MLA 9

Gomez, Milton S., et al. “Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models.” Artificial Intelligence for the Earth Systems, vol. 5, no. 2, 2026. https://doi.org/10.1175/aies-d-25-0073.1.

Chicago

Gomez, Milton S., Louis Poulain--Auzéau, Alexis Berne, and Tom Beucler. 2026. “Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models.” Artificial Intelligence for the Earth Systems 5 (2). https://doi.org/10.1175/aies-d-25-0073.1.

Harvard

Gomez, M. S. et al. (2026) ‘Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models’, Artificial Intelligence for the Earth Systems, 5(2). doi:10.1175/aies-d-25-0073.1.

IEEE

M. S. Gomez, L. Poulain--Auzéau, A. Berne, and T. Beucler, “Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models,” Artificial Intelligence for the Earth Systems, vol. 5, no. 2, 2026, doi: 10.1175/aies-d-25-0073.1.

BibTeX

@article{gomez2026global,
  title     = {{Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models}},
  author    = {Gomez, Milton S. and Poulain--Auzéau, Louis and Berne, Alexis and Beucler, Tom},
  journal   = {Artificial Intelligence for the Earth Systems},
  year      = {2026},
  volume    = {5},
  number    = {2},
  doi       = {10.1175/aies-d-25-0073.1},
  url       = {https://doi.org/10.1175/aies-d-25-0073.1}
}

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 intensity forecasting
  • post-processing
  • probabilistic forecasting
  • Pangu-Weather
  • wind gusts
  • minimum sea level pressure
  • tropical cyclone tracking
  • spatial masking

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?

Gomez, M. S., Poulain--Auzéau, L., Berne, A., & Beucler, T. (2026). Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models. Artificial Intelligence for the Earth Systems, 5(2). https://doi.org/10.1175/aies-d-25-0073.1

How many times has this paper been cited?

8 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?

Milton S. Gomez, Louis Poulain--Auzéau, Alexis Berne, Tom Beucler.

What is the DOI of this paper?

10.1175/aies-d-25-0073.1, permanently at https://doi.org/10.1175/aies-d-25-0073.1. 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.