Reliable coarse-grained turbulent simulations through combined offline learning and neural emulation

Christian Pedersen, Laure Zanna, Joan Bruna, Pavel Perezhogin

Keywords: Machine learning, closure modelling, parameterizations, turbulence

TL;DR: We use a neural emulator to construct more stable ML models of subgrid dynamics in simulations of turbulent fluids

Abstract: Integration of machine learning (ML) models of unresolved dynamics into numerical simulations of fluid dynamics has been demonstrated to improve the accuracy of coarse resolution simulations. However, when trained in a purely offline mode, integrating ML models into the numerical scheme can lead to instabilities. In the context of a 2D, quasi-geostrophic turbulent system, we demonstrate that including an additional network in the loss function, which emulates the state of the system into the future, produces offline-trained ML models that capture important subgrid processes, with improved stability properties.

Submission Number: 78