Transferring climate change physical knowledge
Proceedings of the National Academy of Sciences · 15.04.2025 · 122 (15)
DOI: 10.1073/pnas.2413503122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 08.04.2025. Verfasst von Francesco Immorlano und 7 weiteren Autor:innen. Beteiligte Einrichtung: Centro Euro-Mediterraneo sui Cambiamenti Climatici Foundation - Euro-Mediterranean Center on Climate Change, Lecce 73100, Italy. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 104 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EC | European Research Council (ERC), EC | Horizon Europe | Excellent Science | HORIZON EUROPE Marie Sklodowska-Curie Actions (MSCA).
Abstract (Originalsprache)
Precise and reliable climate projections are required for climate adaptation and mitigation, but Earth system models still exhibit great uncertainties. Several approaches have been developed to reduce the spread of climate projections and feedbacks, yet those methods cannot capture the nonlinear complexity inherent in the climate system. Using a Transfer Learning approach, we show that Machine Learning can be used to optimally leverage and merge the knowledge gained from global temperature maps simulated by Earth system models and observed in the historical period to reduce the spread of global surface air temperature fields projected in the 21st century. We reach an uncertainty reduction of more than 50% with respect to state-of-the-art approaches while giving evidence that our method provides improved regional temperature patterns together with narrower projections uncertainty, urgently required for climate adaptation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Centro Euro-Mediterraneo sui Cambiamenti Climatici Foundation - Euro-Mediterranean Center on Climate Change, Lecce 73100, Italy.
- Department of Computer Science, University of California, Irvine, CA 92697.
- Learning the Earth with AI and Physics, New York, NY 10027.
- Department of Earth System Model Evaluation and Analysis, Deutsches Zentrum für Luft- und Raumfahrt e.V., Institut für Physik der Atmosphäre, Oberpfaffenhofen, Wessling 82234, Germany.
- Department of Climate Modelling, University of Bremen, Institute of Environmental Physics, Bremen 28359, Germany.
- Department of Earth and Environmental Engineering, Columbia University, New York, NY 10027.
ORCID-Profile: Francesco Immorlano, Veronika Eyring, Gabriele Accarino, Donatello Elia, Stephan Mandt, Giovanni Aloisio, Pierre Gentine
Förderung
- EC | European Research Council (ERC)
- EC | Horizon Europe | Excellent Science | HORIZON EUROPE Marie Sklodowska-Curie Actions (MSCA)
Zitieren
APA
Immorlano, F., Eyring, V., le Monnier de Gouville, T., Accarino, G., Elia, D., Mandt, S., Aloisio, G., & Gentine, P. (2025). Transferring climate change physical knowledge. Proceedings of the National Academy of Sciences, 122(15). https://doi.org/10.1073/pnas.2413503122
Vancouver
Immorlano F, Eyring V, le Monnier de Gouville T, Accarino G, Elia D, Mandt S, et al. Transferring climate change physical knowledge. Proceedings of the National Academy of Sciences. 2025;122(15). doi:10.1073/pnas.2413503122
BibTeX
@article{Immorlano2025,
author = {Immorlano, Francesco and Eyring, Veronika and le Monnier de Gouville, Thomas and Accarino, Gabriele and Elia, Donatello and Mandt, Stephan and Aloisio, Giovanni and Gentine, Pierre},
title = {Transferring climate change physical knowledge},
journal = {Proceedings of the National Academy of Sciences},
year = {2025},
volume = {122},
number = {15},
doi = {10.1073/pnas.2413503122}
}
EUVIMED