Conference paper · 2026 · Open access

Does AI Learn Physics? Assessing the Physical Fidelity of Data-Driven Tropical Cyclone Forecasts

Pankaj Lal Sahu, S. Sandeep, Hariprasad Kodamana

EGU General Assembly Conference Abstracts · Published 13 March 2026 · DOI 10.5194/egusphere-egu26-719

Read the free full textCite this paper

In brief

“Does AI Learn Physics? Assessing the Physical Fidelity of Data-Driven Tropical Cyclone Forecasts” is a 2026 conference paper by Pankaj Lal Sahu and 2 co-authors, published in EGU General Assembly Conference Abstracts. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at EGU General Assembly Conference Abstracts.

Citations
0
Authors
3

Abstract

Machine Learning Weather Prediction (MLWP) models—specifically GraphCast, PanguWeather, Aurora, and FourCastNet—show great promise for competing with physics-based Numerical Weather Prediction (NWP) models by providing global forecasts at a low computational cost. However, a thorough physical evaluation is needed before they can be used in place of NWP models. Our comprehensive study comparing these four leading MLWP models with NWP and observations in Tropical Cyclone (TC) forecasting across all tropical basins uncovers a significant duality: MLWP models are very good at predicting the TC track (with an average error of less than 200 km at a 96-hour lead time) because they accurately capture the underlying dynamics. However, they always underestimate the maximum sustained wind speeds (intensity). This systematic low intensity bias is directly related to biases that come from their ERA5 training data and are made worse by penalties. Even with this limitation, the models accurately depict important physical structures, such as low-level convergence and the vertical warm core, while also keeping different physical fields consistent. This suggests that the models learn how different dynamical and thermodynamical processes are related to each other in a way that makes sense. Ultimately, although MLWPs, especially Aurora, exhibit an implicit comprehension of TC dynamics, their enduring intensity bias requires additional refinement prior to their complete substitution of NWP models.

Cite this paper

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

APA 7

Sahu, P. L., Sandeep, S., & Kodamana, H. (2026). Does AI Learn Physics? Assessing the Physical Fidelity of Data-Driven Tropical Cyclone Forecasts. EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu26-719

MLA 9

Sahu, Pankaj Lal, et al. “Does AI Learn Physics? Assessing the Physical Fidelity of Data-Driven Tropical Cyclone Forecasts.” EGU General Assembly Conference Abstracts, 2026. https://doi.org/10.5194/egusphere-egu26-719.

Chicago

Sahu, Pankaj Lal, S. Sandeep, and Hariprasad Kodamana. 2026. “Does AI Learn Physics? Assessing the Physical Fidelity of Data-Driven Tropical Cyclone Forecasts.” EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu26-719.

Harvard

Sahu, P. L., Sandeep, S. and Kodamana, H. (2026) ‘Does AI Learn Physics? Assessing the Physical Fidelity of Data-Driven Tropical Cyclone Forecasts’, EGU General Assembly Conference Abstracts. doi:10.5194/egusphere-egu26-719.

IEEE

P. L. Sahu, S. Sandeep, and H. Kodamana, “Does AI Learn Physics? Assessing the Physical Fidelity of Data-Driven Tropical Cyclone Forecasts,” EGU General Assembly Conference Abstracts, 2026, doi: 10.5194/egusphere-egu26-719.

BibTeX

@inproceedings{sahu2026does,
  title     = {{Does AI Learn Physics? Assessing the Physical Fidelity of Data-Driven Tropical Cyclone Forecasts}},
  author    = {Sahu, Pankaj Lal and Sandeep, S. and Kodamana, Hariprasad},
  booktitle = {EGU General Assembly Conference Abstracts},
  year      = {2026},
  doi       = {10.5194/egusphere-egu26-719},
  url       = {https://doi.org/10.5194/egusphere-egu26-719}
}

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

  • machine learning weather prediction
  • tropical cyclone forecasting
  • GraphCast
  • aurora
  • FourCastNet
  • numerical weather prediction
  • tropical cyclone track forecasting
  • maximum sustained wind speed

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?

Sahu, P. L., Sandeep, S., & Kodamana, H. (2026). Does AI Learn Physics? Assessing the Physical Fidelity of Data-Driven Tropical Cyclone Forecasts. EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu26-719

How many times has this paper been cited?

0 times, according to OpenAlex on 15 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: read the free full text at EGU General Assembly Conference Abstracts.

Who wrote this paper?

Pankaj Lal Sahu, S. Sandeep, Hariprasad Kodamana.

What is the DOI of this paper?

10.5194/egusphere-egu26-719. The permanent link is https://doi.org/10.5194/egusphere-egu26-719.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.