Applying corrective machine learning in the  E3SM atmosphere model in C+ +  (EAMxx)

Donahue, Aaron S.; Wu, Elynn; Perkins, W. Andre; Caldwell, Peter M.; Bretherton, Christopher S.; Rebassoo, Finn; Golaz, Jean-Christophe

doi:10.5194/gmd-19-4763-2026

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.

https://doi.org/10.5194/gmd-19-4763-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 19, issue 11

Development and technical paper

|

03 Jun 2026

Development and technical paper |

| 03 Jun 2026

Applying corrective machine learning in the E3SM atmosphere model in C+ + (EAMxx)

Aaron S. Donahue, Elynn Wu, W. Andre Perkins, Peter M. Caldwell, Christopher S. Bretherton, Finn Rebassoo, and Jean-Christophe Golaz

Data sets

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 1 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18191405

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 2 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18202660

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 3 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18202837

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 4 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18226680

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 5 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18225295

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 6 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18225633

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 7 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18225841

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 8 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18225985

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 9 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18226245

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 10 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18226448

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 11 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18226541

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset 12 of 12, Aaron Donahue https://doi.org/10.5281/zenodo.18226665

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) Dataset Aaron Donahue and Elynn Wu https://doi.org/10.5281/zenodo.17469234

Simulation output and input data from Cess-Potter experiments with SCREAMv1 C. Terai https://doi.org/10.5281/zenodo.14579433

Model code and software

Applying Corrective Machine Learning in the E3SM Atmosphere Model in C++ (EAMxx) - Software Aaron Donahue and Elynn Wu https://doi.org/10.5281/zenodo.17469329

Model code used for Cess-Potter experiments with SCREAMv1 C. Terai https://doi.org/10.5281/zenodo.14578966

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.