Forecasting the Future With Yesterday's Climate: Temperature Bias in AI Weather and Climate Models
Geophysical Research Letters · 28.03.2026 · 53 (6)
DOI: 10.1029/2025gl119740 ↗Kurz gefasst
Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 11.03.2026. Verfasst von Jacob B. Landsberg und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Oceanic and Atmospheric Administration, Heising-Simons Foundation.
Abstract (Originalsprache)
AI‐based climate and weather models provide fast, skillful forecasts yet face a key challenge: predicting future climates while being trained with historical data. We investigate this issue by analyzing boreal winter land temperature biases in AI weather (FourCastNet V2 Small and Pangu Weather) and climate (Ai2 Climate Emulator version 2) models. We evaluate these models during time periods that are significantly more recent than the bulk of their training data, allowing us to assess how well they generalize to more modern conditions. We find that all models produce cold‐biased mean temperatures, resembling climates from 15 to 20 years earlier than their prediction period. Furthermore, FourCastNet's and Pangu's cold bias is strongest for the hottest predicted temperatures, indicating limited training exposure to modern extreme heat events. In contrast, ACE2's bias is more evenly distributed but largest in regions, seasons, and parts of the temperature distribution where historic global warming is most pronounced.
Förderung
- National Oceanic and Atmospheric Administration
- Heising-Simons Foundation
Zitieren
APA
Landsberg, J. B., & Barnes, E. A. (2026). Forecasting the Future With Yesterday's Climate: Temperature Bias in AI Weather and Climate Models. Geophysical Research Letters, 53(6). https://doi.org/10.1029/2025gl119740
Vancouver
Landsberg JB, Barnes EA. Forecasting the Future With Yesterday's Climate: Temperature Bias in AI Weather and Climate Models. Geophysical Research Letters. 2026;53(6). doi:10.1029/2025gl119740
BibTeX
@article{Landsberg2026,
author = {Landsberg, Jacob B. and Barnes, Elizabeth A.},
title = {Forecasting the Future With Yesterday's Climate: Temperature Bias in AI Weather and Climate Models},
journal = {Geophysical Research Letters},
year = {2026},
volume = {53},
number = {6},
doi = {10.1029/2025gl119740}
}
EUVIMED