Journal article · 2026 · Open access

Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods

Haseeb ur Rehman, Felix Norman Teferle

Geoscientific model development, 19(19), 9831–9855 · Published 13 October 2026 · DOI 10.5194/gmd-19-9831-2026

Open PDFView at the publisherCite this paper

In brief

“Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods” is a 2026 journal article by Haseeb ur Rehman and Felix Norman Teferle, published in Geoscientific model development. OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at Geoscientific model development.

Citations
0
References
41
Authors
2

Abstract

Data-driven artificial intelligence (AI) weather models are increasingly positioned as alternatives or complements to physics-based numerical weather prediction (NWP) systems, yet systematic model evaluation studies that compare both paradigms under controlled experimental conditions remain limited. Here we present a structured model evaluation framework applying standardised verification metrics to assess a regional WRF configuration against three publicly available AI models – GraphCast, AIFS Single 1.0, and FuXi – over three high-impact flood events in Luxembourg and the Greater Region (2016, 2018, and 2021), comprising around 90 simulated days per configuration and 92 119 matched forecast–observation pairs at a four-country network of 259 to 280 stations per event, each screened to be independent of the observations assimilated in that event (Fig. 1). The WRF model employs a three-dimensional variational (3D-VAR) data assimilation scheme ingesting GNSS Zenith Total Delay and conventional observations on a 6-hourly Rapid Update Cycle. All systems draw their initial and boundary information from the same ERA5 reanalysis, although the effective initial states are not identical: WRF is cycled and, in the assimilated configuration, corrected by observations, and ERA5 lateral boundary forcing of a limited-area model differs structurally from a global rollout. Categorical precipitation scores evaluated at thresholds from 1 to 20 mm (6 h) −1 and continuous temperature metrics at surface stations serve as verification targets. Data assimilation raises WRF's categorical precipitation skill at the 1 mm threshold (Critical Success Index: 0.364 to 0.389, a difference not resolved by a block bootstrap over 24 h blocks) and brings the near-surface temperature bias close to zero, although this benefit does not extend to heavier rainfall: at 10 mm (6 h) −1 the assimilated run scores below the unassimilated one. The degradation appears in all three events and is not ordered by the density of the assimilated observing network, so we report it without attributing a cause. At the 1 mm threshold AIFS achieves the highest detection rate (POD 0.835) and GraphCast the highest net categorical skill (CSI 0.424, against 0.415 for AIFS and 0.389 for the assimilated WRF), and AIFS and GraphCast reduce temperature RMSE by 19.0 % and 17.6 % relative to assimilated WRF at the subset of stations that also report temperature. This ordering reverses as the rainfall threshold increases: at 20 mm (6 h) −1 WRF attains the highest skill (CSI 0.160), ahead of AIFS (0.141) and GraphCast (0.114), while FuXi produces no exceedances at all. A weather-radar comparison over 27 6 h periods shows the same reversal in space: AIFS holds the highest mean per-period Fractions…

Cite this paper

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

APA 7

Rehman, H. U., & Teferle, F. N. (2026). Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods. Geoscientific model development, 19(19), 9831–9855. https://doi.org/10.5194/gmd-19-9831-2026

MLA 9

Rehman, Haseeb ur, and Felix Norman Teferle. “Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods.” Geoscientific model development, vol. 19, no. 19, 2026, pp. 9831–9855. https://doi.org/10.5194/gmd-19-9831-2026.

Chicago

Rehman, Haseeb ur and Felix Norman Teferle. 2026. “Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods.” Geoscientific model development 19 (19): 9831–9855. https://doi.org/10.5194/gmd-19-9831-2026.

Harvard

Rehman, H. U. and Teferle, F. N. (2026) ‘Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods’, Geoscientific model development, 19(19), pp. 9831–9855. doi:10.5194/gmd-19-9831-2026.

IEEE

H. U. Rehman and F. N. Teferle, “Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods,” Geoscientific model development, vol. 19, no. 19, pp. 9831–9855, 2026, doi: 10.5194/gmd-19-9831-2026.

BibTeX

@article{rehman2026physics,
  title     = {{Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods}},
  author    = {Rehman, Haseeb ur and Teferle, Felix Norman},
  journal   = {Geoscientific model development},
  year      = {2026},
  volume    = {19},
  number    = {19},
  pages     = {9831--9855},
  doi       = {10.5194/gmd-19-9831-2026},
  url       = {https://doi.org/10.5194/gmd-19-9831-2026}
}

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

  • GraphCast
  • AIFS
  • Fuxi
  • WRF model evaluation
  • flash floods
  • precipitation forecasting
  • 3D-Var data assimilation
  • GNSS zenith total delay

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?

Rehman, H. U., & Teferle, F. N. (2026). Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods. Geoscientific model development, 19(19), 9831–9855. https://doi.org/10.5194/gmd-19-9831-2026

How many times has this paper been cited?

0 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 Geoscientific model development: sign in and open the PDF from this page.

Who wrote this paper?

Haseeb ur Rehman, Felix Norman Teferle.

What is the DOI of this paper?

10.5194/gmd-19-9831-2026, permanently at https://doi.org/10.5194/gmd-19-9831-2026. 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.