Turbulence closure modeling with data-driven techniques: Investigation of generalizable deep neural networks

Abstract

Generalizability of machine-learning (ML) based turbulence closures to accurately predict unseen practical flows remains an important challenge. At the Reynolds-averaged Navier-Stokes (RANS) level, NN-based turbulence closure modeling is rendered difficult due to two important reasons: inherent complexity of the constitutive relation arising from flow-dependent non-linearity and bifurcations; and, inordinate difficulty in obtaining high-fidelity data covering the entire parameter space of interest. In this context, the objective of the work is to investigate the approximation capabilities of standard moderate-sized fully-connected NNs. We seek to systematically investigate the effects of: (i) intrinsic complexity of the solution manifold; (ii) sampling procedure (interpolation vs. extrapolation) and (iii) optimization procedure. To overcome the data acquisition challenges, three proxy-physics turbulence surrogates of different degrees of complexity (yet significantly simpler than turbulence physics) are employed to generate the parameter-to-solution maps. Even for this simple proxy-physics system, it is demonstrated that feed-forward NNs require more degrees of freedom than the original proxy-physics model to accurately approximate the true model even when trained with data over the entire parameter space (interpolation). Additionally, if deep fully-connected NNs are trained with data only from part of the parameter space (extrapolation), their approximation capability reduces considerably and it is not straightforward to find an optimal architecture. Overall, the findings provide a realistic perspective on the utility of ML turbulence closures for practical applications and identify areas for improvement.

References in corpus (34)

• Machine Learning for Fluid Mechanics
• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Turbulence Modeling in the Age of Data
• NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• Deep Neural Networks for Data-Driven Turbulence Models
• RANS Turbulence Model Development using CFD-Driven Machine Learning
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression
• Searching for turbulence models by artificial neural network
• DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks
• Solving parametric PDE problems with artificial neural networks
• A neural network approach for the blind deconvolution of turbulent flows
• Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations
• A Perspective on Machine Learning Methods in Turbulence Modelling
• Physics-guided deep learning framework for predictive modeling of the Reynolds stress anisotropy
• Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks
• Data-Driven Modelling of the Reynolds Stress Tensor using Random Forests with Invariance
• Formulating turbulence closures using sparse regression with embedded form invariance
• Feature selection and processing of turbulence modeling based on an artificial neural network
• Sub-grid scale model classification and blending through deep learning
• Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networks
• A Priori Assessment of Prediction Confidence for Data-Driven Turbulence Modeling
• Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning
• Multi-Objective CFD-Driven Development of Coupled Turbulence Closure Models
• Neural Network Models for the Anisotropic Reynolds Stress Tensor in Turbulent Channel Flow
• Turbulence closure modeling with data-driven techniques: physical compatibility and consistency considerations
• Learning nonlocal constitutive models with neural networks
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• Customized data-driven RANS closures for bi-fidelity LES-RANS optimization