Transferring climate change physical knowledge

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.

Authors

Institutions

Publication Details

Journal
Proceedings of the National Academy of Sciences
Published
2025-04-08
DOI
https://doi.org/10.1073/pnas.2413503122
Citations
8
Primary Topic
Climate variability and models
Type
article
Field-Weighted Citation Impact
8.84

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Transferring climate change physical knowledge

Gabriele Accarino, Veronika Eyring, Stephan Mandt, Donatello Elia et al.
8 citations
Proceedings of the National Academy of Sciences
Climate variability and models
8.84
article

Transferring climate change physical knowledge

Gabriele Accarino, Veronika Eyring, Stephan Mandt, Donatello Elia, Pierre Gentine, Giovanni Aloisio, Francesco Immorlano, Thomas le Monnier de Gouville
article en
8 citations

Abstract

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.

Proceedings of the National Academy of SciencesVol. 122(15)
École Polytechnique (FR), University of Salento (IT), University of Bremen (DE), Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR) (DE), CMCC Foundation - Euro-Mediterranean Center on Climate Change (IT), Environmental Earth Sciences (AU), Columbia University (US)
European Research Council, HORIZON EUROPE Marie Sklodowska-Curie Actions
Climate action
Openalex Percentile: Top 2%
Climate variability and models
8.84
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Transferring climate change physical knowledge — Gabriele Accarino, Veronika Eyring, et al. · Proceedings of the National Academy of Sciences (2025) | TGRS Research Map | TGRS