Articles | Volume 19, issue 11
https://doi.org/10.5194/gmd-19-4763-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-19-4763-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
03 Jun 2026
Development and technical paper |
| 03 Jun 2026
| 03 Jun 2026
Applying corrective machine learning in the E3SM atmosphere model in C+ + (EAMxx)
Aaron S. Donahue
CORRESPONDING AUTHOR
Lawrence Livermore National Laboratory, Livermore, CA, USA
Elynn Wu
Allen Institute for Artificial Intelligence, Seattle, WA, USA
W. Andre Perkins
Allen Institute for Artificial Intelligence, Seattle, WA, USA
Peter M. Caldwell
Lawrence Livermore National Laboratory, Livermore, CA, USA
Christopher S. Bretherton
Allen Institute for Artificial Intelligence, Seattle, WA, USA
Finn Rebassoo
Lawrence Livermore National Laboratory, Livermore, CA, USA
Jean-Christophe Golaz
Lawrence Livermore National Laboratory, Livermore, CA, USA
Related authors
Naser Mahfouz, Hassan Beydoun, Johannes Mülmenstädt, Noel Keen, Adam C. Varble, Luca Bertagna, Peter Bogenschutz, Andrew Bradley, Matthew W. Christensen, T. Conrad Clevenger, Aaron Donahue, Jerome Fast, James Foucar, Jean-Christophe Golaz, Oksana Guba, Walter Hannah, Benjamin Hillman, Robert Jacob, Wuyin Lin, Po-Lun Ma, Yun Qian, Balwinder Singh, Christopher Terai, Hailong Wang, Mingxuan Wu, Kai Zhang, Andrew Gettelman, Mark Taylor, L. Ruby Leung, Peter Caldwell, and Susannah Burrows
Atmos. Chem. Phys., 25, 15105–15120, https://doi.org/10.5194/acp-25-15105-2025, https://doi.org/10.5194/acp-25-15105-2025, 2025
Short summary
Short summary
Our study assesses the aerosol effective radiative forcing in a global cloud-resolving atmosphere model at ultra-high resolution. We demonstrate that global aerosol forcing signal can be robustly reproduced across resolutions when aerosol activation processes are carefully parameterized. Further, we argue that simplified prescribed aerosol schemes will open the door for further process/mechanism studies under controlled conditions.
Brian Henn, Christopher S. Bretherton, Nikolay Koldunov, Christian Lessig, Maria J. Molina, Troy Arcomano, Oliver Watt-Meyer, Guillaume Couairon, Renu Singh, Robert Brunstein, Yana Hasson, Antonia Jost, Noah Brenowitz, Peter Manshausen, Nathaniel Cresswell-Clay, Dale Durran, Kyle Joseph Chen Hall, Janni Yuval, Dmitrii Kochkov, Stephan Hoyer, and Ignacio Lopez-Gomez
EGUsphere, https://doi.org/10.48550/arXiv.2605.06944, https://doi.org/10.48550/arXiv.2605.06944, 2026
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
AIMIP (AI Model Intercomparison Project) is a community effort to rigorously evaluate AI weather and climate models, which simulate Earth's climate with extraordinary efficiency compared to traditional systems. Phase 1 is an atmosphere-only standardized experiment, showing that AI models are competitive on average historical patterns but may struggle with long-term warming trends and generalizing to unseen scenarios. The AIMIP Phase 1 dataset is publicly available for open model evaluation.
Jishi Zhang, Jean-Christophe Golaz, Matthew Vincent Signorotti, Hsiang-He Lee, Peter Bogenschutz, Minda Monteagudo, Paul Aaron Ullrich, Robert S. Arthur, Stephen Po-Chedley, Philip Cameron-Smith, and Jean-Paul Watson
Geosci. Model Dev., 19, 4513–4545, https://doi.org/10.5194/gmd-19-4513-2026, https://doi.org/10.5194/gmd-19-4513-2026, 2026
Short summary
Short summary
We ran a convection-permitting model with regional mesh refinement (3.25 km and 800 m) to simulate present-day wind and solar capacity factors over California, coupling it to an energy generation model. The high-resolution models captured realistic seasonal and diurnal cycles, with wind markedly better than a 25 km model and solar outperforming a 3 km operational forecast. We highlight the critical role of resolution, modeling assumptions, and data reliability in renewable energy assessment.
Naser Mahfouz, Hassan Beydoun, Johannes Mülmenstädt, Noel Keen, Adam C. Varble, Luca Bertagna, Peter Bogenschutz, Andrew Bradley, Matthew W. Christensen, T. Conrad Clevenger, Aaron Donahue, Jerome Fast, James Foucar, Jean-Christophe Golaz, Oksana Guba, Walter Hannah, Benjamin Hillman, Robert Jacob, Wuyin Lin, Po-Lun Ma, Yun Qian, Balwinder Singh, Christopher Terai, Hailong Wang, Mingxuan Wu, Kai Zhang, Andrew Gettelman, Mark Taylor, L. Ruby Leung, Peter Caldwell, and Susannah Burrows
Atmos. Chem. Phys., 25, 15105–15120, https://doi.org/10.5194/acp-25-15105-2025, https://doi.org/10.5194/acp-25-15105-2025, 2025
Short summary
Short summary
Our study assesses the aerosol effective radiative forcing in a global cloud-resolving atmosphere model at ultra-high resolution. We demonstrate that global aerosol forcing signal can be robustly reproduced across resolutions when aerosol activation processes are carefully parameterized. Further, we argue that simplified prescribed aerosol schemes will open the door for further process/mechanism studies under controlled conditions.
Ziming Ke, Qi Tang, Jean-Christophe Golaz, Xiaohong Liu, and Hailong Wang
Geosci. Model Dev., 18, 4137–4153, https://doi.org/10.5194/gmd-18-4137-2025, https://doi.org/10.5194/gmd-18-4137-2025, 2025
Short summary
Short summary
This study assesses volcanic aerosol representation in E3SM (Energy Exascale Earth System Model), showing that an emission-based approach moderately improves temperature variability and cloud responses compared to a prescribed forcing approach, yet significant bias persists.
Katherine M. Smith, Alice M. Barthel, LeAnn M. Conlon, Luke P. Van Roekel, Anthony Bartoletti, Jean-Christophe Golaz, Chengzhu Zhang, Carolyn Branecky Begeman, James J. Benedict, Gautam Bisht, Yan Feng, Walter Hannah, Bryce E. Harrop, Nicole Jeffery, Wuyin Lin, Po-Lun Ma, Mathew E. Maltrud, Mark R. Petersen, Balwinder Singh, Qi Tang, Teklu Tesfa, Jonathan D. Wolfe, Shaocheng Xie, Xue Zheng, Karthik Balaguru, Oluwayemi Garuba, Peter Gleckler, Aixue Hu, Jiwoo Lee, Ben Moore-Maley, and Ana C. Ordoñez
Geosci. Model Dev., 18, 1613–1633, https://doi.org/10.5194/gmd-18-1613-2025, https://doi.org/10.5194/gmd-18-1613-2025, 2025
Short summary
Short summary
Version 2.1 of the U.S. Department of Energy's Energy Exascale Earth System Model (E3SM) adds the Fox-Kemper et al. (2011) mixed-layer eddy parameterization, which restratifies the ocean surface layer through an overturning streamfunction. Results include surface layer bias reduction in temperature, salinity, and sea ice extent in the North Atlantic; a small strengthening of the Atlantic meridional overturning circulation; and improvements to many atmospheric climatological variables.
Feng Zhu, Julien Emile-Geay, Gregory J. Hakim, Dominique Guillot, Deborah Khider, Robert Tardif, and Walter A. Perkins
Geosci. Model Dev., 17, 3409–3431, https://doi.org/10.5194/gmd-17-3409-2024, https://doi.org/10.5194/gmd-17-3409-2024, 2024
Short summary
Short summary
Climate field reconstruction encompasses methods that estimate the evolution of climate in space and time based on natural archives. It is useful to investigate climate variations and validate climate models, but its implementation and use can be difficult for non-experts. This paper introduces a user-friendly Python package called cfr to make these methods more accessible, thanks to the computational and visualization tools that facilitate efficient and reproducible research on past climates.
John T. Fasullo, Jean-Christophe Golaz, Julie M. Caron, Nan Rosenbloom, Gerald A. Meehl, Warren Strand, Sasha Glanville, Samantha Stevenson, Maria Molina, Christine A. Shields, Chengzhu Zhang, James Benedict, Hailong Wang, and Tony Bartoletti
Earth Syst. Dynam., 15, 367–386, https://doi.org/10.5194/esd-15-367-2024, https://doi.org/10.5194/esd-15-367-2024, 2024
Short summary
Short summary
Climate model large ensembles provide a unique and invaluable means for estimating the climate response to external forcing agents and quantify contrasts in model structure. Here, an overview of the Energy Exascale Earth System Model (E3SM) version 2 large ensemble is given along with comparisons to large ensembles from E3SM version 1 and versions 1 and 2 of the Community Earth System Model. The paper provides broad and important context for users of these ensembles.
Yuying Zhang, Shaocheng Xie, Yi Qin, Wuyin Lin, Jean-Christophe Golaz, Xue Zheng, Po-Lun Ma, Yun Qian, Qi Tang, Christopher R. Terai, and Meng Zhang
Geosci. Model Dev., 17, 169–189, https://doi.org/10.5194/gmd-17-169-2024, https://doi.org/10.5194/gmd-17-169-2024, 2024
Short summary
Short summary
We performed systematic evaluation of clouds simulated in the Energy
Exascale Earth System Model (E3SMv2) to document model performance and understand what updates in E3SMv2 have caused changes in clouds from E3SMv1 to E3SMv2. We find that stratocumulus clouds along the subtropical west coast of continents are dramatically improved, primarily due to the retuning done in CLUBB. This study offers additional insights into clouds simulated in E3SMv2 and will benefit future E3SM developments.
Exascale Earth System Model (E3SMv2) to document model performance and understand what updates in E3SMv2 have caused changes in clouds from E3SMv1 to E3SMv2. We find that stratocumulus clouds along the subtropical west coast of continents are dramatically improved, primarily due to the retuning done in CLUBB. This study offers additional insights into clouds simulated in E3SMv2 and will benefit future E3SM developments.
Qi Tang, Jean-Christophe Golaz, Luke P. Van Roekel, Mark A. Taylor, Wuyin Lin, Benjamin R. Hillman, Paul A. Ullrich, Andrew M. Bradley, Oksana Guba, Jonathan D. Wolfe, Tian Zhou, Kai Zhang, Xue Zheng, Yunyan Zhang, Meng Zhang, Mingxuan Wu, Hailong Wang, Cheng Tao, Balwinder Singh, Alan M. Rhoades, Yi Qin, Hong-Yi Li, Yan Feng, Yuying Zhang, Chengzhu Zhang, Charles S. Zender, Shaocheng Xie, Erika L. Roesler, Andrew F. Roberts, Azamat Mametjanov, Mathew E. Maltrud, Noel D. Keen, Robert L. Jacob, Christiane Jablonowski, Owen K. Hughes, Ryan M. Forsyth, Alan V. Di Vittorio, Peter M. Caldwell, Gautam Bisht, Renata B. McCoy, L. Ruby Leung, and David C. Bader
Geosci. Model Dev., 16, 3953–3995, https://doi.org/10.5194/gmd-16-3953-2023, https://doi.org/10.5194/gmd-16-3953-2023, 2023
Short summary
Short summary
High-resolution simulations are superior to low-resolution ones in capturing regional climate changes and climate extremes. However, uniformly reducing the grid size of a global Earth system model is too computationally expensive. We provide an overview of the fully coupled regionally refined model (RRM) of E3SMv2 and document a first-of-its-kind set of climate production simulations using RRM at an economic cost. The key to this success is our innovative hybrid time step method.
Hyein Jeong, Adrian K. Turner, Andrew F. Roberts, Milena Veneziani, Stephen F. Price, Xylar S. Asay-Davis, Luke P. Van Roekel, Wuyin Lin, Peter M. Caldwell, Hyo-Seok Park, Jonathan D. Wolfe, and Azamat Mametjanov
The Cryosphere, 17, 2681–2700, https://doi.org/10.5194/tc-17-2681-2023, https://doi.org/10.5194/tc-17-2681-2023, 2023
Short summary
Short summary
We find that E3SM-HR reproduces the main features of the Antarctic coastal polynyas. Despite the high amount of coastal sea ice production, the densest water masses are formed in the open ocean. Biases related to the lack of dense water formation are associated with overly strong atmospheric polar easterlies. Our results indicate that the large-scale polar atmospheric circulation must be accurately simulated in models to properly reproduce Antarctic dense water formation.
Johann Dahm, Eddie Davis, Florian Deconinck, Oliver Elbert, Rhea George, Jeremy McGibbon, Tobias Wicky, Elynn Wu, Christopher Kung, Tal Ben-Nun, Lucas Harris, Linus Groner, and Oliver Fuhrer
Geosci. Model Dev., 16, 2719–2736, https://doi.org/10.5194/gmd-16-2719-2023, https://doi.org/10.5194/gmd-16-2719-2023, 2023
Short summary
Short summary
It is hard for scientists to write code which is efficient on different kinds of supercomputers. Python is popular for its user-friendliness. We converted a Fortran code, simulating Earth's atmosphere, into Python. This new code auto-converts to a faster language for processors or graphic cards. Our code runs 3.5–4 times faster on graphic cards than the original on processors in a specific supercomputer system.
Rachel Atlas and Christopher S. Bretherton
Atmos. Chem. Phys., 23, 4009–4030, https://doi.org/10.5194/acp-23-4009-2023, https://doi.org/10.5194/acp-23-4009-2023, 2023
Short summary
Short summary
The tropical tropopause layer exists between the troposphere and the stratosphere in the tropics. Very thin cirrus clouds cool Earth's surface by scrubbing water vapor (a greenhouse gas) out of air parcels as they ascend through the tropical tropopause layer on their way to the stratosphere. We show observational evidence from aircraft that small-scale (< 100 km) gravity waves and turbulence increase the amount of ice in these clouds and may allow them to remove more water vapor from the air.
Chengzhu Zhang, Jean-Christophe Golaz, Ryan Forsyth, Tom Vo, Shaocheng Xie, Zeshawn Shaheen, Gerald L. Potter, Xylar S. Asay-Davis, Charles S. Zender, Wuyin Lin, Chih-Chieh Chen, Chris R. Terai, Salil Mahajan, Tian Zhou, Karthik Balaguru, Qi Tang, Cheng Tao, Yuying Zhang, Todd Emmenegger, Susannah Burrows, and Paul A. Ullrich
Geosci. Model Dev., 15, 9031–9056, https://doi.org/10.5194/gmd-15-9031-2022, https://doi.org/10.5194/gmd-15-9031-2022, 2022
Short summary
Short summary
Earth system model (ESM) developers run automated analysis tools on data from candidate models to inform model development. This paper introduces a new Python package, E3SM Diags, that has been developed to support ESM development and use routinely in the development of DOE's Energy Exascale Earth System Model. This tool covers a set of essential diagnostics to evaluate the mean physical climate from simulations, as well as several process-oriented and phenomenon-based evaluation diagnostics.
Kai Zhang, Wentao Zhang, Hui Wan, Philip J. Rasch, Steven J. Ghan, Richard C. Easter, Xiangjun Shi, Yong Wang, Hailong Wang, Po-Lun Ma, Shixuan Zhang, Jian Sun, Susannah M. Burrows, Manish Shrivastava, Balwinder Singh, Yun Qian, Xiaohong Liu, Jean-Christophe Golaz, Qi Tang, Xue Zheng, Shaocheng Xie, Wuyin Lin, Yan Feng, Minghuai Wang, Jin-Ho Yoon, and L. Ruby Leung
Atmos. Chem. Phys., 22, 9129–9160, https://doi.org/10.5194/acp-22-9129-2022, https://doi.org/10.5194/acp-22-9129-2022, 2022
Short summary
Short summary
Here we analyze the effective aerosol forcing simulated by E3SM version 1 using both century-long free-running and short nudged simulations. The aerosol forcing in E3SMv1 is relatively large compared to other models, mainly due to the large indirect aerosol effect. Aerosol-induced changes in liquid and ice cloud properties in E3SMv1 have a strong correlation. The aerosol forcing estimates in E3SMv1 are sensitive to the parameterization changes in both liquid and ice cloud processes.
Xue Zheng, Qing Li, Tian Zhou, Qi Tang, Luke P. Van Roekel, Jean-Christophe Golaz, Hailong Wang, and Philip Cameron-Smith
Geosci. Model Dev., 15, 3941–3967, https://doi.org/10.5194/gmd-15-3941-2022, https://doi.org/10.5194/gmd-15-3941-2022, 2022
Short summary
Short summary
We document the model experiments for the future climate projection by E3SMv1.0. At the highest future emission scenario, E3SMv1.0 projects a strong surface warming with rapid changes in the atmosphere, ocean, sea ice, and land runoff. Specifically, we detect a significant polar amplification and accelerated warming linked to the unmasking of the aerosol effects. The impact of greenhouse gas forcing is examined in different climate components.
Po-Lun Ma, Bryce E. Harrop, Vincent E. Larson, Richard B. Neale, Andrew Gettelman, Hugh Morrison, Hailong Wang, Kai Zhang, Stephen A. Klein, Mark D. Zelinka, Yuying Zhang, Yun Qian, Jin-Ho Yoon, Christopher R. Jones, Meng Huang, Sheng-Lun Tai, Balwinder Singh, Peter A. Bogenschutz, Xue Zheng, Wuyin Lin, Johannes Quaas, Hélène Chepfer, Michael A. Brunke, Xubin Zeng, Johannes Mülmenstädt, Samson Hagos, Zhibo Zhang, Hua Song, Xiaohong Liu, Michael S. Pritchard, Hui Wan, Jingyu Wang, Qi Tang, Peter M. Caldwell, Jiwen Fan, Larry K. Berg, Jerome D. Fast, Mark A. Taylor, Jean-Christophe Golaz, Shaocheng Xie, Philip J. Rasch, and L. Ruby Leung
Geosci. Model Dev., 15, 2881–2916, https://doi.org/10.5194/gmd-15-2881-2022, https://doi.org/10.5194/gmd-15-2881-2022, 2022
Short summary
Short summary
An alternative set of parameters for E3SM Atmospheric Model version 1 has been developed based on a tuning strategy that focuses on clouds. When clouds in every regime are improved, other aspects of the model are also improved, even though they are not the direct targets for calibration. The recalibrated model shows a lower sensitivity to anthropogenic aerosols and surface warming, suggesting potential improvements to the simulated climate in the past and future.
Cited articles
Bogenschutz, P. and Krueger, S. K.: A simplified PDF parameterization of subgrid-scale clouds and turbulence for cloud-resolving models, J. Adv. Model. Earth Sy., 5, 195–211, https://doi.org/10.1002/jame.20018, 2013. a
Bogenschutz, P. A., Clevenger, T. C., Bradley, A. M., Caldwell, P. M., Beydoun, H., Mahfouz, N., Keen, N. D., Guba, O., Bertagna, L., Foucar, J., Zhang, J., and Donahue, A. S.: High Performance, High Fidelity: A GPU-Accelerated Doubly-Periodic Configuration of the Simple Cloud-Resolving E3SM Atmosphere Model Version 1 (DP-SCREAMv1), J. Adv. Model. Earth Sy., 17, e2025MS005127, https://doi.org/10.1029/2025MS005127, 2025. a
Bretherton, C. S., Henn, B., Kwa, A., Brenowitz, N. D., Watt-Meyer, O., McGibbon, J., Perkins, W. A., Clark, S. K., and Harris, L.: Correcting Coarse-Grid Weather and Climate Models by Machine Learning From Global Storm-Resolving Simulations, J. Adv. Model. Earth Sy., 14, e2021MS002794, https://doi.org/10.1029/2021MS002794, 2022. a, b, c, d, e, f, g, h, i
Caldwell, P. M., Terai, C. R., Hillman, B., Keen, N. D., Bogenschutz, P., Lin, W., Beydoun, H., Taylor, M., Bertagna, L., Bradley, A. M., Clevenger, T. C., Donahue, A. S., Eldred, C., Foucar, J., Golaz, J.-C., Guba, O., Jacob, R., Johnson, J., Krishna, J., Liu, W., Pressel, K., Salinger, A. G., Singh, B., Steyer, A., Ullrich, P., Wu, D., Yuan, X., Shpund, J., Ma, H.-Y., and Zender, C. S.: Convection-Permitting Simulations With the E3SM Global Atmosphere Model, J. Adv. Model. Earth Sy., 13, e2021MS002544, https://doi.org/10.1029/2021MS002544, 2021. a, b
Carter-Edwards, H., Trott, C. R., and Sunderland, D.: Kokkos: Enabling manycore performance portability through polymorphic memory access patterns, J. Parallel Dist. Comp., 74, 3202–3216, 2014. a
Chen, K., Han, T., Gong, J., Bai, L., Ling, F., Luo, J.-J., Chen, X., Ma, L., Zhang, T., Su, R., Ci, Y., Li, B., Yang, X., and Ouyang, W.: FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead, arXiv [physics], https://doi.org/10.48550/arXiv.2304.02948, 2023. a
Clark, S. K., Brenowitz, N. D., Henn, B., Kwa, A., McGibbon, J., Perkins, W. A., Watt-Meyer, O., Bretherton, C. S., and Harris, L. M.: Correcting a 200 km Resolution Climate Model in Multiple Climates by Machine Learning From 25 km Resolution Simulations, J. Adv. Model. Earth Sy., 14, e2022MS003219, https://doi.org/10.1029/2022MS003219, 2022. a
Dennis, J., Fournier, A., Spotz, W. F., St-Cyr, A., Taylor, M. A., Thomas, S. J., and Tufo, H.: High-resolution mesh convergence properties and parallel efficiency of a spectral element atmospheric dynamical core, Int. J. High Perform. Comput. Appl., 19, 225–235, 2005. a
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A. and Wu, E.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A. and Wu, E.: Applying Corrective Machine Learning in the E3SM Atmosphere Model in C
Donahue, A. S., Caldwell, P. M., Bertagna, L., Beydoun, H., Bogenschutz, P. A., Bradley, A. M., Clevenger, T. C., Foucar, J., Golaz, C., Guba, O., Hannah, W., Hillman, B. R., Johnson, J. N., Keen, N., Lin, W., Singh, B., Sreepathi, S., Taylor, M. A., Tian, J., Terai, C. R., Ullrich, P. A., Yuan, X., and Zhang, Y.: To Exascale and Beyond—The Simple Cloud-Resolving E3SM Atmosphere Model (SCREAM), a Performance Portable Global Atmosphere Model for Cloud-Resolving Scales, J. Adv. Model. Earth Sy., 16, e2024MS004314, https://doi.org/10.1029/2024MS004314, 2024. a, b, c, d
Eyring, V., Collins, W. D., Gentine, P., Barnes, E. A., Barreiro, M., Beucler, T., Bocquet, M., Bretherton, C. S., Christensen, H. M., Dagon, K., Gagne, D. J., Hall, D., Hammerling, D., Hoyer, S., Iglesias-Suarez, F., Lopez-Gomez, I., McGraw, M. C., Meehl, G. A., Molina, M. J., Monteleoni, C., Mueller, J., Pritchard, M. S., Rolnick, D., Runge, J., Stier, P., Watt-Meyer, O., Weigel, K., Yu, R., and Zanna, L.: Pushing the frontiers in climate modelling and analysis with machine learning, Nat. Clim. Change, 14, 916–928, https://doi.org/10.1038/s41558-024-02095-y, 2024. a
Henn, B., Jauregui, Y. R., Clark, S. K., Brenowitz, N. D., McGibbon, J., Watt-Meyer, O., Pauling, A. G., and Bretherton, C. S.: A Machine Learning Parameterization of Clouds in a Coarse-Resolution Climate Model for Unbiased Radiation, J. Adv. Model. Earth Sy., 16, e2023MS003949, https://doi.org/10.1029/2023MS003949, 2024. a
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons, A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati, G., Bidlot, J., Bonavita, M., De Chiara, G., Dahlgren, P., Dee, D., Diamantakis, M., Dragani, R., Flemming, J., Forbes, R., Fuentes, M., Geer, A., Haimberger, L., Healy, S., Hogan, R. J., Hólm, E., Janisková, M., Keeley, S., Laloyaux, P., Lopez, P., Lupu, C., Radnoti, G., de Rosnay, P., Rozum, I., Vamborg, F., Villaume, S., and Thépaut, J.-N.: The ERA5 global reanalysis, Q. J. Roy. Meteor. Soc., 146, 1999–2049, https://doi.org/10.1002/qj.3803, 2020. a
Hohenegger, C., Korn, P., Linardakis, L., Redler, R., Schnur, R., Adamidis, P., Bao, J., Bastin, S., Behravesh, M., Bergemann, M., Biercamp, J., Bockelmann, H., Brokopf, R., Brüggemann, N., Casaroli, L., Chegini, F., Datseris, G., Esch, M., George, G., Giorgetta, M., Gutjahr, O., Haak, H., Hanke, M., Ilyina, T., Jahns, T., Jungclaus, J., Kern, M., Klocke, D., Kluft, L., Kölling, T., Kornblueh, L., Kosukhin, S., Kroll, C., Lee, J., Mauritsen, T., Mehlmann, C., Mieslinger, T., Naumann, A. K., Paccini, L., Peinado, A., Praturi, D. S., Putrasahan, D., Rast, S., Riddick, T., Roeber, N., Schmidt, H., Schulzweida, U., Schütte, F., Segura, H., Shevchenko, R., Singh, V., Specht, M., Stephan, C. C., von Storch, J.-S., Vogel, R., Wengel, C., Winkler, M., Ziemen, F., Marotzke, J., and Stevens, B.: ICON-Sapphire: simulating the components of the Earth system and their interactions at kilometer and subkilometer scales, Geosci. Model Dev., 16, 779–811, https://doi.org/10.5194/gmd-16-779-2023, 2023. a
Hu, Z., Subramaniam, A., Kuang, Z., Lin, J., Yu, S., Hannah, W. M., Brenowitz, N. D., Romero, J., and Pritchard, M. S.: Stable Machine-Learning Parameterization of Subgrid Processes in a Comprehensive Atmospheric Model Learned From Embedded Convection-Permitting Simulations, J. Adv. Model. Earth Sy., 17, e2024MS004618, https://doi.org/10.1029/2024MS004618, 2025. a
Jakob, W., Rhinelander, J., Moldovan, D., Adler, J., Burns, L. A., Corlay, S., Cousineau, E., Gokaslan, A., Grosse-Kunstleve, R., Houliston, T., Huebl, A., @hulucc, Jadoul, Y., Lyskov, S., Mabille, J., Miąsko, T., Moldovan, D., Pritchard, B., Rhinelander, J., Schäling, B., Schellart, P., Schreiner, H., Smirnov, I., Spicuzza, D., Staletic, B., Steinberg, E., Stewart, P., Wanders, I., and Wang, X.: pybind11 – Seamless operability between C
Keisler, R.: Forecasting Global Weather with Graph Neural Networks, https://doi.org/10.48550/arXiv.2202.07575, 2022. a
Kochkov, D., Yuval, J., Langmore, I., Norgaard, P., Smith, J., Mooers, G., Lottes, J., Rasp, S., Düben, P., Klöwer, M., Hatfield, S., Battaglia, P., Sanchez-Gonzalez, A., Willson, M., Brenner, M. P., and Hoyer, S.: Neural General Circulation Models, arXiv [physics], https://doi.org/10.48550/arXiv.2311.07222, 2023. a
Kochkov, D., Yuval, J., Langmore, I., Norgaard, P., Smith, J., Mooers, G., Klöwer, M., Lottes, J., Rasp, S., Düben, P., Hatfield, S., Battaglia, P., Sanchez-Gonzalez, A., Willson, M., Brenner, M. P., and Hoyer, S.: Neural general circulation models for weather and climate, Nature, 632, 1060–1066, https://doi.org/10.1038/s41586-024-07744-y, 2024. a
Kwa, A., Clark, S. K., Henn, B., Brenowitz, N. D., McGibbon, J., Watt-Meyer, O., Perkins, W. A., Harris, L., and Bretherton, C. S.: Machine-Learned Climate Model Corrections From a Global Storm-Resolving Model: Performance Across the Annual Cycle, J. Adv. Model. Earth Sy., 15, e2022MS003400, https://doi.org/10.1029/2022MS003400, 2023. a, b, c
Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., Hu, W., Merose, A., Hoyer, S., Holland, G., Vinyals, O., Stott, J., Pritzel, A., Mohamed, S., and Battaglia, P.: GraphCast: Learning skillful medium-range global weather forecasting, arXiv [physics], https://doi.org/10.48550/arXiv.2212.12794, 2023. a
Morrison, H. and Milbrandt, J. A.: Parameterization of cloud microphysics based on the prediction of the bulk ice particle properties. Part I: Scheme description and idealized tests, J. Atmos. Sci., 72, 287–311, 2015. a
Okuta, R., Unno, Y., Nishino, D., Hido, S., and Loomis, C.: CuPy: A NumPy-Compatible Library for NVIDIA GPU Calculations, in: Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Thirty-first Annual Conference on Neural Information Processing Systems (NIPS), http://learningsys.org/nips17/assets/papers/paper_16.pdf (last access: 24 June 2024), 2017. a
Pincus, R., Mlawer, E. J., and Delamere, J. S.: Balancing Accuracy, Efficiency, and Flexibility in Radiation Calculations for Dynamical Models, J. Adv. Model. Earth Sy., 11, 3074–3089, https://doi.org/10.1029/2019MS001621, 2019. a
Price, I., Sanchez-Gonzalez, A., Alet, F., Ewalds, T., El-Kadi, A., Stott, J., Mohamed, S., Battaglia, P. W., Lam, R., and Willson, M.: GenCast: Diffusion-based ensemble forecasting for medium-range weather, https://www.semanticscholar.org/paper/f6e7e8b96b8ce1f32973318b3b88bc54f6eb4ab7 (last access: 24 June 2024), 2023. a
Sanford, C., Kwa, A., Watt-Meyer, O., Clark, S. K., Brenowitz, N., McGibbon, J., and Bretherton, C.: Improving the Reliability of ML-Corrected Climate Models With Novelty Detection, J. Adv. Model. Earth Sy., 15, e2023MS003809, https://doi.org/10.1029/2023MS003809, 2023. a, b
Satoh, M., Stevens, B., Judt, F., Khairoutdinov, M., Lin, S.-J., Putman, W. M., and Düben, P.: Global cloud-resolving models, Current Climate Change Reports, 5, 172–184, https://doi.org/10.1007/s40641-019-00131-0, 2019. a
Taylor, M., Caldwell, P. M., Bertagna, L., Clevenger, C., Donahue, A., Foucar, J., Guba, O., Hillman, B., Keen, N., Krishna, J., Norman, M., Sreepathi, S., Terai, C., White, J. B., Salinger, A. G., McCoy, R. B., Leung, L.-y. R., Bader, D. C., and Wu, D.: The Simple Cloud-Resolving E3SM Atmosphere Model Running on the Frontier Exascale System, in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC '23, Association for Computing Machinery, New York, NY, USA, https://dl.acm.org/doi/abs/10.1145/3581784.3627044 (last access: 24 June 2024), 2023. a
Taylor, M. A., Guba, O., Steyer, A., Ullrich, P. A., Hall, D. M., and Eldrid, C.: An Energy Consistent Discretization of the Nonhydrostatic Equations in Primitive Variables, J. Adv. Model. Earth Sy., 12, https://doi.org/10.1029/2019MS001783, 2020. a
Terai, C.: Model code used for Cess-Potter experiments with SCREAMv1, Zenodo [code], https://doi.org/10.5281/zenodo.14578966, 2024a. a
Terai, C.: Simulation output and input data from Cess-Potter experiments with SCREAMv1, Zenodo [data set], https://doi.org/10.5281/zenodo.14579433, 2024b. a
Terai, C. R., Keen, N. D., Caldwell, P. M., Beydoun, H., Bogenschutz, P. A., Chao, L.-W., Hillman, B. R., Ma, H.-Y., Zelinka, M. D., Bertagna, L., Bradley, A., Clevenger, T. C., Donahue, A. S., Foucar, J. G., Golaz, J.-C., Guba, O., Hannah, W. M., Lee, J., Lin, W., Mahfouz, N. G. A., Mülmenstädt, J., Salinger, A. G., Singh, B., Sreepathi, S., Qin, Y., Taylor, M. A., Ullrich, P. A., Wu, W.-Y., Yuan, X., Zender, C. S., and Zhang, Y.: Climate response to warming in Cess-Potter simulations using the global 3-km SCREAM, ESS Open Archive, https://doi.org/10.22541/essoar.173655643.33295443/v1, 2025. a, b
Ullrich, P. A. and Taylor, M. A.: Arbitrary-Order Conservative and Consistent Remapping and a Theory of Linear Maps: Part I, Mon. Weather Rev., 143, 2419–2440, https://doi.org/10.1175/MWR-D-14-00343.1, 2015. a
Ullrich, P. A., Devendran, D., and Johansen, H.: Arbitrary-Order Conservative and Consistent Remapping and a Theory of Linear Maps: Part II, Mon. Weather Rev., 144, 1529–1549, https://doi.org/10.1175/MWR-D-15-0301.1, 2016. a
Zhou, L., Lin, S.-J., Chen, J.-H., Harris, L. M., Chen, X., and Rees, S. L.: Toward Convective-Scale Prediction within the Next Generation Global Prediction System, B. Am. Meteorol. Soc., 100, 1225–1243, https://doi.org/10.1175/BAMS-D-17-0246.1, 2019. a
Short summary
This study tested using machine learning to speed up detailed simulations in the SCREAM (Simple Cloud-Resolving E3SM Atmosphere Model) model. By training ML (machine learning) models to correct a simpler version of SCREAM, some results improved, but others did not. Technical challenges were addressed, and new tools were developed. The work shows promise for making simulations more efficient, though further improvements are needed.
This study tested using machine learning to speed up detailed simulations in the SCREAM (Simple...
