Sub-grid modelling for two-dimensional turbulence using neural networks

Abstract

In this investigation, a data-driven turbulence closure framework is introduced and deployed for the sub-grid modelling of Kraichnan turbulence. The novelty of the proposed method lies in the fact that snapshots from high-fidelity numerical data are used to inform artificial neural networks for predicting the turbulence source term through localized grid-resolved information. In particular, our proposed methodology successfully establishes a map between inputs given by stencils of the vorticity and the streamfunction along with information from two well-known eddy-viscosity kernels. Through this we predict the sub-grid vorticity forcing in a temporally and spatially dynamic fashion. Our study is both a-priori and a-posteriori in nature. In the former, we present an extensive hyper-parameter optimization analysis in addition to learning quantification through probability density function based validation of sub-grid predictions. In the latter, we analyse the performance of our framework for flow evolution in a classical decaying two-dimensional turbulence test case in the presence of errors related to temporal and spatial discretization. Statistical assessments in the form of angle-averaged kinetic energy spectra demonstrate the promise of the proposed methodology for sub-grid quantity inference. In addition, it is also observed that some measure of a-posteriori error must be considered during optimal model selection for greater accuracy. The results in this article thus represent a promising development in the formalization of a framework for generation of heuristic-free turbulence closures from data.

References in corpus (12)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• 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
• Quantifying and Reducing Model-Form Uncertainties in Reynolds-Averaged Navier-Stokes Simulations: A Data-Driven, Physics-Based Bayesian Approach
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Searching for turbulence models by artificial neural network
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• A neural network approach for the blind deconvolution of turbulent flows
• High-order methods for decaying two-dimensional homogeneous isotropic turbulence
• Approximate deconvolution large eddy simulation of a stratified two-layer quasigeostrophic ocean model

Cited by in corpus (80)

• Machine Learning for Fluid Mechanics
• Machine learning accelerated computational fluid dynamics
• Enhancing Computational Fluid Dynamics with Machine Learning
• Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Assessment of supervised machine learning methods for fluid flows
• A new prediction method of unsteady wake flow by the hybrid deep neural network
• RANS Equations with Explicit Data-Driven Reynolds Stress Closure Can Be Ill-Conditioned
• Deep Learning in Deterministic Computational Mechanics
• Physics guided machine learning using simplified theories
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• Experimental velocity data estimation for imperfect particle images using machine learning
• Generalization techniques of neural networks for fluid flow estimation
• Digital Twins in Wind Energy: Emerging Technologies and Industry-Informed Future Directions
• Deconvolutional artificial neural network models for large eddy simulation of turbulence
• Sub-grid scale model classification and blending through deep learning
• Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulations
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Feature engineering and symbolic regression methods for detecting hidden physics from sparse sensors
• Learned Turbulence Modelling with Differentiable Fluid Solvers: Physics-based Loss-functions and Optimisation Horizons
• Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning
• Attention-Enhanced Neural Network Models for Turbulence Simulation
• A posteriori learning for quasi-geostrophic turbulence parametrization
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• On the role of nonlinear correlations in reduced-order modeling
• Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systems
• Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence
• Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow
• Data-driven super-parameterization using deep learning: Experimentation with multi-scale Lorenz 96 systems and transfer-learning
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Deep-learning assisted reduced order model for high-dimensional flow prediction from sparse data
• Physical invariance in neural networks for subgrid-scale scalar flux modeling
• Theoretical tools for understanding the climate crisis from Hasselmann's program and beyond
• Interpreting neural network models of residual scalar flux
• Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model
• Neural-network-based mixed subgrid-scale model for turbulent flow
• Deep learning of the spanwise-averaged Navier-Stokes equations
• Investigation of nonlocal data-driven methods for subgrid-scale stress modelling in large eddy simulation
• Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges
• Data-Driven Multi-Grid Solver for Accelerated Pressure Projection
• Machine-learning accelerated turbulence modelling of transient flashing jets
• Discovery of interpretable structural model errors by combining Bayesian sparse regression and data assimilation: A chaotic Kuramoto-Sivashinsky test case
• Frame invariant neural network closures for Kraichnan turbulence
• A wall model for separated flows: embedded learning to improve a posteriori performance
• On the generalizability of machine-learning-assisted anisotropy mappings for predictive turbulence modelling
• Assessment of Neural Network Augmented Reynolds Averaged Navier Stokes Turbulence Model in Extrapolation Modes
• Resampling with neural networks for stochastic parameterization in multiscale systems
• Filtered Partial Differential Equations: a robust surrogate constraint in physics-informed deep learning framework
• Machine Learning-Based Statistical Closure Models for Turbulent Dynamical Systems
• Ensemble data assimilation-based mixed subgrid-scale model for large-eddy simulations
• A recursive neural-network-based subgrid-scale model for large eddy simulation: application to homogeneous isotropic turbulence
• Explicit physics-informed neural networks for non-linear upscaling closure: the case of transport in tissues
• Dimension Reduced Turbulent Flow Data From Deep Vector Quantizers
• turbo-RANS: Straightforward and Efficient Bayesian Optimization of Turbulence Model Coefficients
• A Data-Driven Statistical-Stochastic Surrogate Modeling Strategy for Complex Nonlinear Non-stationary Dynamics
• Bridging the Gap: Machine Learning to Resolve Improperly Modeled Dynamics
• Promoting global stability in data-driven models of quadratic nonlinear dynamics
• Adjoint-based variational optimal mixed models for large-eddy simulation of turbulence
• Deep Neural Networks to Correct Sub-Precision Errors in CFD
• Data-driven spectral turbulence modeling for Rayleigh-Bénard convection
• Data-driven dynamical coarse-graining for condensed matter systems
• Reduced Data-Driven Turbulence Closure for Capturing Long-Term Statistics
• A Priori Uncertainty Quantification of Reacting Turbulence Closure Models using Bayesian Neural Networks
• Kinetic data-driven approach to turbulence subgrid modeling
• Model order reduction with neural networks: Application to laminar and turbulent flows
• Mitigating distribution shift in machine learning-augmented hybrid simulation
• Spatiotemporal wall pressure forecast of a rectangular cylinder with physics-aware DeepU-Fourier neural network
• Finding Closure Terms Directly from Coarse Data for 2D Turbulent Flow
• A data-driven approach to viscous fluid mechanics -- the stationary case
• Turbulence closure modeling with data-driven techniques: Investigation of generalizable deep neural networks
• Adaptation of AI-accelerated CFD Simulations to the IPU platform
• Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
• Speed-direction description of turbulent flows
• A comparison of data-driven approaches to build low-dimensional ocean models
• A new data-driven energy-stable Evolve-Filter-Relax model for turbulent flow simulation
• Evaluation of Analytical Turbulence Closures for Quasi-Geostrophic Ocean Flows with Coastal Boundaries
• Assessment of jet inflow conditions on the development of supersonic jet flows
• Data-driven multiscale modeling for correcting dynamical systems