David Fuchs: Plugging Pytorch to an atmospheric model the TorchClim way
Climate models are hindered by the need to conceptualize and then parameterize complex physical processes that are not explicitly numerically resolved and for which no rigorous theory exists. Machine learning and artificial intelligence methods (ML and AI) offer a promising paradigm that can augment or replace the traditional parameterized approach with models trained on empirical process data. This work promotes the creation of an ACCESS variant that can interface machine learning frameworks such as Pytorch, and present an approach to do so using the TorchClim plugin. A reference implementation is presented for the Community Earth System Model (CESM), where moist physics and radiation parameterizations of the Community Atmospheric Model (CAM) are replaced with such a surrogate. We present a set of best-practice principles for doing this with minimal changes to the general circulation model (GCM), exposing the surrogate model as any other parameterization module, and discuss how to accommodate the requirements of physics surrogates such as the need to avoid unphysical values and supply information needed by other GCM components. This work concerns both the ML/AI and general ACCESS communities, offering the community the potential for a new set of tools to advance their work.
Coauthors:
David Fuchs, Steven C. Sherwood, Abhnil Prasad