Pushing the Frontiers in Climate Modelling and Analysis with Machine Learning

Veronika Eyring; William Collins; Pierre Gentine; Elizabeth Barnes; Marcelo Barreiro; Tom Beucler; Marc Bocquet; Christopher Bretherton; Hannah Christensen; Katherine Dagon; David Gagne; David Hall; Dorit Hammerling; Stephan Hoyer; Fernando Iglesias-Suarez; Ignacio Lopez-Gomez; Marie McGraw; Gerald Meehl; Maria Molina; Claire Monteleoni; Juliane Mueller; Michael Pritchard; David Rolnick; Jakob Runge; Philip Stier; Oliver Watt-Meyer; Katja Weigel; Rose Yu; Laure Zanna

doi:10.1038/s41558-024-02095-y

Pushing the Frontiers in Climate Modelling and Analysis with Machine Learning

Veronika Eyring, William Collins, Pierre Gentine, Elizabeth Barnes, Marcelo Barreiro, Tom Beucler, Marc Bocquet, Christopher Bretherton, Hannah Christensen, Katherine Dagon, David Gagne, David Hall, Dorit Hammerling, Stephan Hoyer, Fernando Iglesias-Suarez, Ignacio Lopez-Gomez, Marie McGraw, Gerald Meehl, Maria Molina, Claire MonteleoniJuliane Mueller, Michael Pritchard, David Rolnick, Jakob Runge, Philip Stier, Oliver Watt-Meyer, Katja Weigel, Rose Yu, Laure Zanna

Computational Science

Research output: Contribution to journal › Article › peer-review

1 Scopus Citations

Abstract

Climate modelling and analysis are facing new demands to enhance projections and climate information. Here we argue that now is the time to push the frontiers of machine learning beyond state-of-the-art approaches, not only by developing machine-learning-based Earth system models with greater fidelity, but also by providing new capabilities through emulators for extreme event projections with large ensembles, enhanced detection and attribution methods for extreme events, and advanced climate model analysis and benchmarking. Utilizing this potential requires key machine learning challenges to be addressed, in particular generalization, uncertainty quantification, explainable artificial intelligence and causality. This interdisciplinary effort requires bringing together machine learning and climate scientists, while also leveraging the private sector, to accelerate progress towards actionable climate science.

Original language	American English
Pages (from-to)	916-928
Number of pages	13
Journal	Nature Climate Change
Volume	14
DOIs	https://doi.org/10.1038/s41558-024-02095-y
State	Published - 2024

NREL Publication Number

NREL/JA-2C00-88119

Keywords

causal inference
climate change
climate modeling and analysis
explainable AI
extreme events
generalization
machine learning
uncertainty quantification

Access to Document

10.1038/s41558-024-02095-y

Cite this

Eyring, V., Collins, W., Gentine, P., Barnes, E., Barreiro, M., Beucler, T., Bocquet, M., Bretherton, C., Christensen, H., Dagon, K., Gagne, D., Hall, D., Hammerling, D., Hoyer, S., Iglesias-Suarez, F., Lopez-Gomez, I., McGraw, M., Meehl, G., Molina, M., ... Zanna, L. (2024). Pushing the Frontiers in Climate Modelling and Analysis with Machine Learning. Nature Climate Change, 14, 916-928. https://doi.org/10.1038/s41558-024-02095-y

@article{ca431554e96a411a9f0efc0b11021e84,

title = "Pushing the Frontiers in Climate Modelling and Analysis with Machine Learning",

abstract = "Climate modelling and analysis are facing new demands to enhance projections and climate information. Here we argue that now is the time to push the frontiers of machine learning beyond state-of-the-art approaches, not only by developing machine-learning-based Earth system models with greater fidelity, but also by providing new capabilities through emulators for extreme event projections with large ensembles, enhanced detection and attribution methods for extreme events, and advanced climate model analysis and benchmarking. Utilizing this potential requires key machine learning challenges to be addressed, in particular generalization, uncertainty quantification, explainable artificial intelligence and causality. This interdisciplinary effort requires bringing together machine learning and climate scientists, while also leveraging the private sector, to accelerate progress towards actionable climate science.",

keywords = "causal inference, climate change, climate modeling and analysis, explainable AI, extreme events, generalization, machine learning, uncertainty quantification",

author = "Veronika Eyring and William Collins and Pierre Gentine and Elizabeth Barnes and Marcelo Barreiro and Tom Beucler and Marc Bocquet and Christopher Bretherton and Hannah Christensen and Katherine Dagon and David Gagne and David Hall and Dorit Hammerling and Stephan Hoyer and Fernando Iglesias-Suarez and Ignacio Lopez-Gomez and Marie McGraw and Gerald Meehl and Maria Molina and Claire Monteleoni and Juliane Mueller and Michael Pritchard and David Rolnick and Jakob Runge and Philip Stier and Oliver Watt-Meyer and Katja Weigel and Rose Yu and Laure Zanna",

year = "2024",

doi = "10.1038/s41558-024-02095-y",

language = "American English",

volume = "14",

pages = "916--928",

journal = "Nature Climate Change",

issn = "1758-678X",

publisher = "Nature Publishing Group",

}

Eyring, V, Collins, W, Gentine, P, Barnes, E, Barreiro, M, Beucler, T, Bocquet, M, Bretherton, C, Christensen, H, Dagon, K, Gagne, D, Hall, D, Hammerling, D, Hoyer, S, Iglesias-Suarez, F, Lopez-Gomez, I, McGraw, M, Meehl, G, Molina, M, Monteleoni, C, Mueller, J, Pritchard, M, Rolnick, D, Runge, J, Stier, P, Watt-Meyer, O, Weigel, K, Yu, R & Zanna, L 2024, 'Pushing the Frontiers in Climate Modelling and Analysis with Machine Learning', Nature Climate Change, vol. 14, pp. 916-928. https://doi.org/10.1038/s41558-024-02095-y

TY - JOUR

T1 - Pushing the Frontiers in Climate Modelling and Analysis with Machine Learning

AU - Eyring, Veronika

AU - Collins, William

AU - Gentine, Pierre

AU - Barnes, Elizabeth

AU - Barreiro, Marcelo

AU - Beucler, Tom

AU - Bocquet, Marc

AU - Bretherton, Christopher

AU - Christensen, Hannah

AU - Dagon, Katherine

AU - Gagne, David

AU - Hall, David

AU - Hammerling, Dorit

AU - Hoyer, Stephan

AU - Iglesias-Suarez, Fernando

AU - Lopez-Gomez, Ignacio

AU - McGraw, Marie

AU - Meehl, Gerald

AU - Molina, Maria

AU - Monteleoni, Claire

AU - Mueller, Juliane

AU - Pritchard, Michael

AU - Rolnick, David

AU - Runge, Jakob

AU - Stier, Philip

AU - Watt-Meyer, Oliver

AU - Weigel, Katja

AU - Yu, Rose

AU - Zanna, Laure

PY - 2024

Y1 - 2024

N2 - Climate modelling and analysis are facing new demands to enhance projections and climate information. Here we argue that now is the time to push the frontiers of machine learning beyond state-of-the-art approaches, not only by developing machine-learning-based Earth system models with greater fidelity, but also by providing new capabilities through emulators for extreme event projections with large ensembles, enhanced detection and attribution methods for extreme events, and advanced climate model analysis and benchmarking. Utilizing this potential requires key machine learning challenges to be addressed, in particular generalization, uncertainty quantification, explainable artificial intelligence and causality. This interdisciplinary effort requires bringing together machine learning and climate scientists, while also leveraging the private sector, to accelerate progress towards actionable climate science.

AB - Climate modelling and analysis are facing new demands to enhance projections and climate information. Here we argue that now is the time to push the frontiers of machine learning beyond state-of-the-art approaches, not only by developing machine-learning-based Earth system models with greater fidelity, but also by providing new capabilities through emulators for extreme event projections with large ensembles, enhanced detection and attribution methods for extreme events, and advanced climate model analysis and benchmarking. Utilizing this potential requires key machine learning challenges to be addressed, in particular generalization, uncertainty quantification, explainable artificial intelligence and causality. This interdisciplinary effort requires bringing together machine learning and climate scientists, while also leveraging the private sector, to accelerate progress towards actionable climate science.

KW - causal inference

KW - climate change

KW - climate modeling and analysis

KW - explainable AI

KW - extreme events

KW - generalization

KW - machine learning

KW - uncertainty quantification

U2 - 10.1038/s41558-024-02095-y

DO - 10.1038/s41558-024-02095-y

M3 - Article

SN - 1758-678X

VL - 14

SP - 916

EP - 928

JO - Nature Climate Change

JF - Nature Climate Change

ER -

Pushing the Frontiers in Climate Modelling and Analysis with Machine Learning

Abstract

NREL Publication Number

Keywords

Access to Document

Fingerprint

Cite this