A19: Deep learning bridge framework for AI-based parameterizations in E3SM

A Fortran-C-Python deep learning bridge framework for AI-based parameterizations in E3SM

• Tao Zhang

• tzhang@bnl.gov

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

‘Atmosphere', 'AI/ML'

E3SM

Parameterizations in Earth System Models (ESMs) are subject to 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 problems has spawned numerous interest in climate science applications. Specifically, the ML-based parameterizations have been developed to represent convection, radiation and microphysics processes in ESMs by learning from observations or high-resolution simulations, which can alleviate such uncertainties. Previous works have developed some surrogate models for these processes using ML. These surrogate models need to coupled with the dynamical core of ESMs, making it difficult to investigate their performance in a coupled system. In this study, we develop a Fortran-C-Python deep learning bridge framework embedded in the E3SM to support online AI-based parameterizations. While there are other online frameworks available, they either rely on file-based variable passing between Fotran and Python, or just binding specific ML frameworks, such as Keras, to provide corresponding interface layers to the neural networks. Our framework is designed to be both efficient, allowing variable passing by memory with resident python sessions throughout simulations; and flexible, supporting any Python package, especially Keras/Tensorflow, Scikit-learn and Pytorch. This framework has been successfully applied in E3SM, to incorporate the ML trigger function and closure in deep convection scheme, as well as wildfire models.

yes