Application of the AI2 Climate Emulator to E3SMv2's Global Atmosphere Model, With a Focus on Precipitation Fidelity

Duncan, James P. C.; Wu, Elynn; Golaz, Jean‐Christophe; Caldwell, Peter M.; Watt‐Meyer, Oliver; Clark, Spencer K.; McGibbon, Jeremy; Dresdner, Gideon; Kashinath, Karthik; Bonev, Boris; Pritchard, Michael S.; Bretherton, Christopher S.

doi:10.1029/2024JH000136

Title: Application of the AI2 Climate Emulator to E3SMv2's Global Atmosphere Model, With a Focus on Precipitation Fidelity

Journal Article · 12 September 2024 · Journal of Geophysical Research. Machine Learning and Computation (Online)

DOI: https://doi.org/10.1029/2024JH000136 · OSTI ID:2440891

^[1]; Wu, Elynn ^[2];

^[3];

^[2];

^[4]; McGibbon, Jeremy ^[2]; Dresdner, Gideon ^[2]; Kashinath, Karthik ^[5];

^[5];

^[2]

University of California Berkeley CA USA
Allen Institute for Artificial Intelligence (AI2) Seattle WA USA
Lawrence Livermore National Laboratory Livermore CA USA
Allen Institute for Artificial Intelligence (AI2) Seattle WA USA, Geophysical Fluid Dynamics Laboratory NOAA Princeton NJ USA
NVIDIA Santa Clara CA USA

Abstract Can the current successes of global machine learning‐based weather simulators be generalized beyond 2‐week forecasts to stable and accurate multiyear runs? The recently developed AI2 Climate Emulator (ACE) suggests this is feasible, based upon 10‐year simulations with a network trained on output from a physics‐based global atmosphere model using a grid spacing of approximately 110 km and forced by a repeating annual cycle of sea‐surface temperature. Here we show that ACE, without modification, can be trained to emulate another major atmospheric model, EAMv2, run at a comparable grid spacing for at least 10 years with similarly small climate biases—a prerequisite to wider applicability. With an analysis that combines multiple temporal, spatial, and frequency domain perspectives, we show that ACE faithfully represents the spatiotemporal structure of EAMv2 precipitation and related variables. Finally, we show that a pretrained ACE network is able to adapt to a new global climate model simulation data set with 10 fewer training steps than when starting from random initialization, all while still maintaining low levels of climate bias. Further analysis of these fine‐tuning experiments reveal ACE's intriguing ability to interpolate between distinct global climate models.

View Journal Article

Cite

Export

Save

Sponsoring Organization:: USDOE

OSTI ID:: 2440891

Journal Information:: Journal of Geophysical Research. Machine Learning and Computation (Online), Journal Name: Journal of Geophysical Research. Machine Learning and Computation (Online) Journal Issue: 3 Vol. 1; ISSN 2993-5210

Publisher:: American Geophysical Union (AGU)Copyright Statement

Country of Publication:: United States

Language:: English

References (19)

Analyzing the dependence of global cloud feedback on the spatial pattern of sea surface temperature change with a G reen's function approach Zhou, Chen; Zelinka, Mark D.; Klein, Stephen A. Journal of Advances in Modeling Earth Systems, Vol. 9, Issue 5 https://doi.org/10.1002/2017ms001096	journal	September 2017
Madden-Julian Oscillation Zhang, Chidong Reviews of Geophysics, Vol. 43, Issue 2 https://doi.org/10.1029/2004RG000158	journal	January 2005
Four Theories of the Madden‐Julian Oscillation Zhang, C.; Adames, Á. F.; Khouider, B. Reviews of Geophysics, Vol. 58, Issue 3 https://doi.org/10.1029/2019RG000685	journal	July 2020
Separating Physics and Dynamics Grids for Improved Computational Efficiency in Spectral Element Earth System Models Hannah, Walter M.; Bradley, Andrew M.; Guba, Oksana Journal of Advances in Modeling Earth Systems, Vol. 13, Issue 7 https://doi.org/10.1029/2020MS002419	journal	June 2021
Convection‐Permitting Simulations With the E3SM Global Atmosphere Model Caldwell, P. M.; Terai, C. R.; Hillman, B. Journal of Advances in Modeling Earth Systems, Vol. 13, Issue 11 https://doi.org/10.1029/2021MS002544	journal	November 2021
Improving Seasonal Forecast Using Probabilistic Deep Learning Pan, Baoxiang; Anderson, Gemma J.; Goncalves, André Journal of Advances in Modeling Earth Systems, Vol. 14, Issue 3 https://doi.org/10.1029/2021MS002766	journal	March 2022
The DOE E3SM Model Version 2: Overview of the Physical Model and Initial Model Evaluation Golaz, Jean‐Christophe; Van Roekel, Luke P.; Zheng, Xue Journal of Advances in Modeling Earth Systems, Vol. 14, Issue 12 https://doi.org/10.1029/2022MS003156	journal	December 2022
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation Girshick, Ross; Donahue, Jeff; Darrell, Trevor 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2014.81	conference	June 2014
MJO Simulation Diagnostics Journal of Climate, Vol. 22, Issue 11, p. 3006-3030 https://doi.org/10.1175/2008JCLI2731.1	journal	June 2009
Understanding the CMIP3 Multimodel Ensemble Annan, J. D.; Hargreaves, J. C. Journal of Climate, Vol. 24, Issue 16 https://doi.org/10.1175/2011JCLI3873.1	journal	August 2011
Adam: A Method for Stochastic Optimization Kingma, Diederik P.; Ba, Jimmy arXiv https://doi.org/10.48550/arXiv.1412.6980	preprint	January 2014
FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators Pathak, Jaideep; Subramanian, Shashank; Harrington, Peter arXiv https://doi.org/10.48550/arXiv.2202.11214	preprint	January 2022
Editing Models with Task Arithmetic Ilharco, Gabriel; Ribeiro, Marco Tulio; Wortsman, Mitchell arXiv https://doi.org/10.48550/arXiv.2212.04089	preprint	January 2022
GraphCast: Learning skillful medium-range global weather forecasting Lam, Remi; Sanchez-Gonzalez, Alvaro; Willson, Matthew arXiv https://doi.org/10.48550/arXiv.2212.12794	preprint	January 2022
ClimaX: A foundation model for weather and climate Nguyen, Tung; Brandstetter, Johannes; Kapoor, Ashish arXiv https://doi.org/10.48550/arXiv.2301.10343	preprint	January 2023
Improving medium-range ensemble weather forecasts with hierarchical ensemble transformers Ben-Bouallegue, Zied; Weyn, Jonathan A.; Clare, Mariana C. A. arXiv https://doi.org/10.48550/arXiv.2303.17195	preprint	January 2023
Editing Large Language Models: Problems, Methods, and Opportunities Yao, Yunzhi; Wang, Peng; Tian, Bozhong arXiv https://doi.org/10.48550/arXiv.2305.13172	preprint	January 2023
ACE: A fast, skillful learned global atmospheric model for climate prediction Watt-Meyer, Oliver; Dresdner, Gideon; McGibbon, Jeremy arXiv https://doi.org/10.48550/arXiv.2310.02074	preprint	January 2023
In-Context Learning Creates Task Vectors Hendel, Roee; Geva, Mor; Globerson, Amir arXiv https://doi.org/10.48550/arXiv.2310.15916	preprint	January 2023

Similar Records

A practical extension of the recursive multi-fidelity model for the emulation of hole closure experiments

Journal Article · 2021 · Statistical Analysis and Data Mining · OSTI ID:1860801

Muyskens, Amanda L.; Schmidt, Kathleen L.; Nelms, Matthew D.; +4 more

The GGCMI Phase 2 emulators: global gridded crop model responses to changes in CO₂, temperature, water, and nitrogen (version 1.0)

Journal Article · 2020 · Geoscientific Model Development (Online) · OSTI ID:1770073

Franke, James A.; Müller, Christoph; Elliott, Joshua; +21 more

Emulation of seismic-phase traveltimes with machine learning

Journal Article · 2023 · Geophysical Journal International · OSTI ID:2204304

Anderson, Gemma J.; Myers, Stephen C.; Simmons, Nathan

Title: Application of the AI2 Climate Emulator to E3SMv2's Global Atmosphere Model, With a Focus on Precipitation Fidelity

Citation Formats

References (19)

Similar Records

Related Subjects