A machine learning framework for LES closure terms
From MaRDI portal
Publication:2672196
Abstract: In the present work, we explore the capability of artificial neural networks (ANN) to predict the closure terms for large eddy simulations (LES) solely from coarse-scale data. To this end, we derive a consistent framework for LES closure models, with special emphasis laid upon the incorporation of implicit discretization-based filters and numerical approximation errors. We investigate implicit filter types, which are inspired by the solution representation of discontinuous Galerkin and finite volume schemes and mimic the behaviour of the discretization operator, and a global Fourier cutoff filter as a representative of a typical explicit LES filter. Within the perfect LES framework, we compute the exact closure terms for the different LES filter functions from direct numerical simulation results of decaying homogeneous isotropic turbulence. Multiple ANN with a multilayer perceptron (MLP) or a gated recurrent unit (GRU) architecture are trained to predict the computed closure terms solely from coarse-scale input data. For the given application, the GRU architecture clearly outperforms the MLP networks in terms of accuracy, whilst reaching up to 99.9% cross-correlation between the networks' predictions and the exact closure terms for all considered filter functions. The GRU networks are also shown to generalize well across different LES filters and resolutions. The present study can thus be seen as a starting point for the investigation of data-based modeling approaches for LES, which not only include the physical closure terms, but account for the discretization effects in implicitly filtered LES as well.
Recommendations
- Interpreting neural network models of residual scalar flux
- Subgrid-scale model for large-eddy simulation of isotropic turbulent flows using an artificial neural network
- A priori sub-grid modelling using artificial neural networks
- Toward neural-network-based large eddy simulation: application to turbulent channel flow
- Neural networks based subgrid scale modeling in large eddy simulations
Cites work
- A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
- A neural network approach for the blind deconvolution of turbulent flows
- Approximation by superpositions of a sigmoidal function
- FLEXI: a high order discontinuous Galerkin framework for hyperbolic-parabolic conservation laws
- Homogeneous Turbulence Dynamics
- Large Eddy Simulation for Compressible Flows
- Neural networks based subgrid scale modeling in large eddy simulations
- Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- Self-conditioned fields for large-eddy simulations of turbulent flows
- Statistical Properties of Subgrid-Scale Turbulence Models
- Subgrid modelling for two-dimensional turbulence using neural networks
- The decay of axisymmetric homogeneous turbulence
Cited in
(7)- Spatiotemporally dynamic implicit large eddy simulation using machine learning classifiers
- Data-driven fractional subgrid-scale modeling for scalar turbulence: a nonlocal LES approach
- Machine learning moment closure models for the radiative transfer equation. I: Directly learning a gradient based closure
- Interpreting neural network models of residual scalar flux
- Energy-conserving neural network for turbulence closure modeling
- Discretize first, filter next: learning divergence-consistent closure models for large-eddy simulation
- Scientific machine learning for closure models in multiscale problems: a review
This page was built for publication: A machine learning framework for LES closure terms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2672196)
