Truace
Subscribe
70/100

Moderate evidence

Trace: a gain and a problemPublished recordScienceThe Trace

Full story
More
Export record JSONEmailLinkedInX

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

Truvace record
TRV-2026-2525raw data (JSON)
Version
v1Published
First published
Evidence type
Controlled or validated comparison
Sources
1 sourcePeer-reviewed
sha256
74a23a0b93ed…check it

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 F…

58Gain side

How the two sides scoreClose call

59Problem side

The gain

In a hindcast study of three floods in Luxembourg and the Greater Region, AIFS and GraphCast cut temperature error by 19.0% and 17.6% against an observation-corrected physics model and led it on light-rain forecast skill.

The problem

In the same study, at 20 mm of rain per 6 hours the physics model scored highest (CSI 0.160 against 0.141 for AIFS and 0.114 for GraphCast), and FuXi forecast no such rainfall at all.

A fixed formula sets both scores from the evidence and its sources. Reader votes don’t move them.

What the scores mean

G is the gain side, out of 100. It goes up when the gain is specific, when it measurably helped people and when the sources behind it are strong.

P is the problem side, out of 100. It goes up when the problem is specific, when it measurably hurt people and when the sources behind it are strong.

What this doesn’t fix

Only three flood events were tested, and AIFS was fine-tuned on 2016–2022 data covering all of them, so its scores may be optimistic and cannot show generalisation.

Sources

1 on file
  1. Geoscientific Model Developmentdoi:10.5194/gmd-19-9831-2026
    Peer-reviewed2026-10-13

Cite this record

v1

Truvace Impact Record TRV-2026-2525, v1: “Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods.” Truvace, 2026-11-12. /record/TRV-2026-2525 (accessed on the day you copy it). sha256 74a23a0b93edc361…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv174a23a0b93ed…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2525 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.