Sub-grid scale model classification and blending through deep learning

Abstract

In this article we detail the use of machine learning for spatiotemporally dynamic turbulence model classification and hybridization for the large eddy simulations (LES) of turbulence. Our predictive framework is devised around the determination of local conditional probabilities for turbulence models that have varying underlying hypotheses. As a first deployment of this learning, we classify a point on our computational grid as that which requires the functional hypothesis, the structural hypothesis or no modeling at all. This ensures that the appropriate model is specified from \emph{a priori} knowledge and an efficient balance of model characteristics is obtained in a particular flow computation. In addition, we also utilize the conditional probability predictions of the same machine learning to blend turbulence models for another hybrid closure. Our test-case for the demonstration of this concept is given by Kraichnan turbulence which exhibits a strong interplay of enstrophy and energy cascades in the wave number domain. Our results indicate that the proposed methods lead to robust and stable closure and may potentially be used to combine the strengths of various models for complex flow phenomena prediction.

References in corpus (15)

• Turbulence Modeling in the Age of Data
• Super-resolution reconstruction of turbulent flows with machine learning
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• Deep Neural Networks for Data-Driven Turbulence Models
• Quantifying and Reducing Model-Form Uncertainties in Reynolds-Averaged Navier-Stokes Simulations: A Data-Driven, Physics-Based Bayesian Approach
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Searching for turbulence models by artificial neural network
• Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates
• A neural network approach for the blind deconvolution of turbulent flows
• Approximate deconvolution large eddy simulation of a barotropic ocean circulation model
• Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks
• High-order methods for decaying two-dimensional homogeneous isotropic turbulence
• A coupled approximate deconvolution and dynamic mixed scale model for large-eddy simulation
• From Deep to Physics-Informed Learning of Turbulence: Diagnostics
• Data-driven deconvolution for large eddy simulations of Kraichnan turbulence

Cited by in corpus (26)

• A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• Physics-guided deep learning framework for predictive modeling of the Reynolds stress anisotropy
• Physics guided machine learning using simplified theories
• Optimal eddy viscosity for resolvent-based models of coherent structures in turbulent jets
• Generalization techniques of neural networks for fluid flow estimation
• Deconvolutional artificial neural network models for large eddy simulation of turbulence
• Feature engineering and symbolic regression methods for detecting hidden physics from sparse sensors
• Turbulent scalar flux in inclined jets in crossflow: counter gradient transport and deep learning modelling
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Interpreting neural network models of residual scalar flux
• Deep learning of the spanwise-averaged Navier-Stokes equations
• Invariant Data-Driven Subgrid Stress Modeling in the Strain-Rate Eigenframe for Large Eddy Simulation
• Log-law recovery through reinforcement-learning wall model for large-eddy simulation
• Frame invariant neural network closures for Kraichnan turbulence
• Data augmentation and feature selection for automatic model recommendation in computational physics
• Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows
• Interface learning of multiphysics and multiscale systems
• Large Language Model Driven Development of Turbulence Models
• A unified understanding of scale-resolving simulations and near-wall modeling of turbulent flows using optimal finite element projections
• Model order reduction with neural networks: Application to laminar and turbulent flows
• A turbulent eddy-viscosity surrogate modeling framework for Reynolds-Averaged Navier-Stokes simulations
• Turbulence closure modeling with data-driven techniques: Investigation of generalizable deep neural networks
• Modelling of Flow Past Long Cylindrical Structures