AI Model Performances Depend on Adequate Training Data Representing Diverse Physical Mechanisms
Geophysical Research Letters · 28.07.2026 · 53 (14)
DOI: 10.1029/2025gl121196 ↗Kurz gefasst
Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 26.07.2026. Verfasst von Mu Mu und 2 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, Shanghai Municipal Education Commission.
Abstract (Originalsprache)
The value of weather and climate AI models depends on their generalization beyond training data, yet the influence of data characteristics on this capability remains unclear. In this investigation, a fully controllable framework using a parameter‐tunable Burgers system is utilized to explore the role of data in model generalization. By varying nonlinear and diffusive coefficients, 600 distinct dynamical regimes are generated, and two experiments are performed using samples drawn from different parameter quadrant or their combinations. The results demonstrate generalization depends on adequate training data representation of underlying mechanisms of target regimes, including both effective Reynolds numbers and solution properties. Insufficient representation, either through missing mechanisms or low sample proportions of certain mechanisms, can lead to substantial performance degradation. These findings imply AI models trained on historical reanalysis may perform poorly in extremes and climate‐scale predictions, requiring a pressing need to supplement samples with physically consistent numerical simulations.
Förderung
- National Natural Science Foundation of China
- Shanghai Municipal Education Commission
Zitieren
APA
Mu, M., Qin, B., & Dai, G. (2026). AI Model Performances Depend on Adequate Training Data Representing Diverse Physical Mechanisms. Geophysical Research Letters, 53(14). https://doi.org/10.1029/2025gl121196
Vancouver
Mu M, Qin B, Dai G. AI Model Performances Depend on Adequate Training Data Representing Diverse Physical Mechanisms. Geophysical Research Letters. 2026;53(14). doi:10.1029/2025gl121196
BibTeX
@article{Mu2026,
author = {Mu, Mu and Qin, Bo and Dai, Guokun},
title = {AI Model Performances Depend on Adequate Training Data Representing Diverse Physical Mechanisms},
journal = {Geophysical Research Letters},
year = {2026},
volume = {53},
number = {14},
doi = {10.1029/2025gl121196}
}
EUVIMED