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

2023/07/24 by Pedersen, Christian, Zanna, Laure, Bruna, Joan +1
#Atmospheric and Oceanic Physics (physics.ao-ph) #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn)

paper · doi:10.48550/arxiv.2307.13144

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.

Related

• Neural Network for Subgrid Turbulence Modeling for Large Eddy Simulations
• A posteriori learning of quasi-geostrophic turbulence parametrization: an experiment on integration steps
• Machine learning–accelerated computational fluid dynamics
• Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulations
• Perspectives on predicting and controlling turbulent flows through deep learning