Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning
Published in Physics of Fluids, 2021
Recommended citation: Adam Subel, Ashesh Chattopadhyay, Yifei Guan, and Pedram Hassanzadeh. "Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning." Physics of Fluids 33, no. 3 (2021): 031702. https://doi.org/10.1063/5.0040286
Developing data-driven subgrid-scale (SGS) models for large eddy simulations (LESs) has received substantial attention recently. Despite some success, particularly in a priori (offline) tests, challenges have been identified that include numerical instabilities in a posteriori (online) tests and generalization (i.e., extrapolation) of trained data-driven SGS models, for example, to higher Reynolds numbers. Here, using the stochastically forced Burgers turbulence as the test-bed, we show that deep neural networks trained using properly pre-conditioned (augmented) data yield stable and accurate a posteriori LES models. Furthermore, we show that transfer learning enables accurate/stable generalization to a flow with 10× higher Reynolds number.
Recommended citation: Adam Subel, Ashesh Chattopadhyay, Yifei Guan, and Pedram Hassanzadeh. “Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning.” Physics of Fluids 33, no. 3 (2021): 031702.