A Fortran–Python interface for integrating machine learning parameterization into earth system models

Zhang, Tao; Morcrette, Cyril; Zhang, Meng; Lin, Wuyin; Xie, Shaocheng; Liu, Ye; Van Weverberg, Kwinten; Rodrigues, Joana

doi:https://doi.org/10.5194/gmd-18-1917-2025

Articles | Volume 18, issue 6

https://doi.org/10.5194/gmd-18-1917-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-18-1917-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 6

Development and technical paper

|

24 Mar 2025

Development and technical paper |

| 24 Mar 2025

A Fortran–Python interface for integrating machine learning parameterization into earth system models

Tao Zhang, Cyril Morcrette, Meng Zhang, Wuyin Lin, Shaocheng Xie, Ye Liu, Kwinten Van Weverberg, and Joana Rodrigues

Data sets

dataset for machine learning trigger function Cyril Morcrette https://doi.org/10.5281/zenodo.12205917

dataset for machine learning wild fire Ye Liu https://doi.org/10.5281/zenodo.12212258

E3SMv2 for Fortran-Python interface T. Zhang https://doi.org/10.5281/zenodo.12175988

Model code and software

Fortran-Python Interface for Integrating Machine Learning Parameterization into Earth System Models Tao Zhang https://doi.org/10.5281/zenodo.11005103

E3SMv2 E3SM Project https://doi.org/10.11578/E3SM/dc.20230110.5

Short summary

Earth system models (ESMs) struggle with the uncertainties associated with parameterizing subgrid physics. Machine learning (ML) algorithms offer a solution by learning the important relationships and features from high-resolution models. To incorporate ML parameterizations into ESMs, we develop a Fortran–Python interface that allows for calling Python functions within Fortran-based ESMs. Through two case studies, this interface demonstrates its feasibility, modularity, and effectiveness.