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

• Published in: Geoscientific Model Development Vol. 18; no. 6; pp. 1917 - 1928
• Main Authors: Zhang, Tao, Morcrette, Cyril, Zhang, Meng, Lin, Wuyin, Xie, Shaocheng, Liu, Ye, Van Weverberg, Kwinten, Rodrigues, Joana
• Format: Journal Article
• Language: English
• Published: Katlenburg-Lindau Copernicus GmbH 24.03.2025; Copernicus Publications, EGU; Copernicus Publications
• Subjects: Algorithms; Analysis; artificial intelligence; Bridges; Case studies; Climate science; Convection; Deep learning; Earth; FORTRAN; Learning algorithms; Machine learning; Microphysics; Modularity; Neural networks; Observational learning; Parameterization; Python; Simulation; Technology application; Uncertainty; Variables; Wildfires

Parameterizations in earth system models (ESMs) are subject to biases and uncertainties arising from subjective empirical assumptions and incomplete understanding of the underlying physical processes. Recently, the growing representational capability of machine learning (ML) in solving complex probl...