Unsupervised machine-learning-based sub-grid scale modeling for coarse-grid LES

In this talk, we propose a machine-learning-based sub-grid scale (SGS) modeling for coarse-grid large-eddy simulation (LES). The machine learning model performs super-resolution of the LES flow field into a flow field of direct numerical simulation (DNS) quality. In other words, the model estimates the high-wavenumber components of flow that the coarse-grid LES does not resolve. By utilizing an unsupervised learning model (CycleGAN), the model is able to learn the correlation between poorly-resolved flows of coarse-grid LES and well-resolved flows of DNS, which is impossible with supervised learning methods. The resultant super-resolved flow is then used to calculate the SGS stress components. We show that the results agree well with the SGS stress derived from DNS data in a priori tests, including the strong anisotropies near the wall. The model is also tested in an a posteriori manner, and the results are discussed.