Discretize first, filter next: learning divergence-consistent closure models for large-eddy simulation

Abstract

We propose a new neural network based large eddy simulation framework for the incompressible Navier-Stokes equations based on the paradigm "discretize first, filter and close next". This leads to full model-data consistency and allows for employing neural closure models in the same environment as where they have been trained. Since the LES discretization error is included in the learning process, the closure models can learn to account for the discretization. Furthermore, we employ a divergence-consistent discrete filter defined through face-averaging and provide novel theoretical and numerical filter analysis. This filter preserves the discrete divergence-free constraint by construction, unlike general discrete filters such as volume-averaging filters. We show that using a divergence-consistent LES formulation coupled with a convolutional neural closure model produces stable and accurate results for both a-priori and a-posteriori training, while a general (divergence-inconsistent) LES model requires a-posteriori training or other stability-enforcing measures.

53 pages

References in corpus (11)

• Turbulence Modeling in the Age of Data
• Deep Neural Networks for Data-Driven Turbulence Models
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• A neural network approach for the blind deconvolution of turbulent flows
• A Perspective on Machine Learning Methods in Turbulence Modelling
• Learned Turbulence Modelling with Differentiable Fluid Solvers: Physics-based Loss-functions and Optimisation Horizons
• High-order methods for decaying two-dimensional homogeneous isotropic turbulence
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement Learning
• Comparison of neural closure models for discretised PDEs
• A machine learning framework for LES closure terms

Cited by in corpus (3)

• PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics
• A Novel Explicit Filter for the Approximate Deconvolution in Large-Eddy Simulation on General Unstructured Grids: A posteriori tests on highly stretched grids
• A new data-driven energy-stable Evolve-Filter-Relax model for turbulent flow simulation