Articles | Volume 18, issue 6
https://doi.org/10.5194/gmd-18-1917-2025
https://doi.org/10.5194/gmd-18-1917-2025
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

Related authors

Aerosol impacts on isolated deep convection: findings from TRACER
Dié Wang, Roni Kobrosly, Tao Zhang, Tamanna Subba, Susan van den Heever, Siddhant Gupta, and Michael Jensen
Atmos. Chem. Phys., 25, 9295–9314, https://doi.org/10.5194/acp-25-9295-2025,https://doi.org/10.5194/acp-25-9295-2025, 2025
Short summary
ELM2.1-XGBfire1.0: improving wildfire prediction by integrating a machine learning fire model in a land surface model
Ye Liu, Huilin Huang, Sing-Chun Wang, Tao Zhang, Donghui Xu, and Yang Chen
Geosci. Model Dev., 18, 4103–4117, https://doi.org/10.5194/gmd-18-4103-2025,https://doi.org/10.5194/gmd-18-4103-2025, 2025
Short summary

Cited articles

Bechtold, P., Chaboureau, J.-P., Beljaars, A., Betts, A. K., Köhler, M., Miller, M., and Redelsperger, J.-L.: The simulation of the diurnal cycle of convective precipitation over land in a global model, Q. J. Roy. Meteor. Soc., 130, 3119–3137, https://doi.org/10.1256/qj.03.103, 2004. 
Bogenschutz, P. A., Tang, S., Caldwell, P. M., Xie, S., Lin, W., and Chen, Y.-S.: The E3SM version 1 single-column model, Geosci. Model Dev., 13, 4443–4458, https://doi.org/10.5194/gmd-13-4443-2020, 2020. 
Brenowitz, N. D. and Bretherton, C. S.: Prognostic validation of a neural network unified physics parameterization, Geophys. Res. Lett., 45, 6289–6298, https://doi.org/10.1029/2018gl078510, 2018. 
Brenowitz, N. D. and Bretherton, C. S.: Spatially extended tests of a neural network parametrization trained by coarse-graining, J. Adv. Model. Earth Sy., 11, 2728–2744, https://doi.org/10.1029/2019ms001711, 2019. 
Download
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.
Share