Turbulence Modeling in the Age of Data

Abstract

Data from experiments and direct simulations of turbulence have historically been used to calibrate simple engineering models such as those based on the Reynolds-averaged Navier--Stokes (RANS) equations. In the past few years, with the availability of large and diverse datasets, researchers have begun to explore methods to systematically inform turbulence models with data, with the goal of quantifying and reducing model uncertainties. This review surveys recent developments in bounding uncertainties in RANS models via physical constraints, in adopting statistical inference to characterize model coefficients and estimate discrepancy, and in using machine learning to improve turbulence models. Key principles, achievements and challenges are discussed. A central perspective advocated in this review is that by exploiting foundational knowledge in turbulence modeling and physical constraints, data-driven approaches can yield useful predictive models.

References in corpus (5)

• A public turbulence database cluster and applications to study Lagrangian evolution of velocity increments in turbulence
• The Ensemble Kalman Filter for Inverse Problems
• A neural network approach for the blind deconvolution of turbulent flows
• Representation of Reynolds Stress Perturbations with Application in Machine-Learning-Assisted Turbulence Modeling
• Quantification of Model Uncertainty in RANS Simulations: A Review

Cited by in corpus (280)

• Machine Learning for Fluid Mechanics
• NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
• Machine learning accelerated computational fluid dynamics
• Data-driven discovery of coordinates and governing equations
• Super-resolution reconstruction of turbulent flows with machine learning
• Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
• Enhancing Computational Fluid Dynamics with Machine Learning
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• Physics-informed neural networks for solving Reynolds-averaged Navier$\unicode{x2013}$Stokes equations
• Machine Learning in Aerodynamic Shape Optimization
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Flow over an espresso cup: Inferring 3D velocity and pressure fields from tomographic background oriented schlieren videos via physics-informed neural networks
• Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics
• RANS Turbulence Model Development using CFD-Driven 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
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression
• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• Assessment of supervised machine learning methods for fluid flows
• DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks
• Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flows
• Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates
• Improving aircraft performance using machine learning: a review
• Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
• Robust flow field reconstruction from limited measurements via sparse representation
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM
• Deep Learning in Deterministic Computational Mechanics
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• PFNN: A Penalty-Free Neural Network Method for Solving a Class of Second-Order Boundary-Value Problems on Complex Geometries
• A Perspective on Machine Learning Methods in Turbulence Modelling
• Physics-guided deep learning framework for predictive modeling of the Reynolds stress anisotropy
• Data-Driven Modelling of the Reynolds Stress Tensor using Random Forests with Invariance
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
• Hybrid FEM-NN models: Combining artificial neural networks with the finite element method
• From bypass transition to flow control and data-driven turbulence modeling: An input-output viewpoint
• JAX-FLUIDS: A fully-differentiable high-order computational fluid dynamics solver for compressible two-phase flows
• Hamiltonian neural networks for solving equations of motion
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• Data-driven Tissue Mechanics with Polyconvex Neural Ordinary Differential Equations
• Optimal eddy viscosity for resolvent-based models of coherent structures in turbulent jets
• Reinforcement-learning-based control of confined cylinder wakes with stability analyses
• High-fidelity reconstruction of turbulent flow from spatially limited data using enhanced super-resolution generative adversarial network
• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• Formulating turbulence closures using sparse regression with embedded form invariance
• Experimental velocity data estimation for imperfect particle images using machine learning
• Physics-constrained, low-dimensional models for MHD: First-principles and data-driven approaches
• Feature selection and processing of turbulence modeling based on an artificial neural network
• Generalization techniques of neural networks for fluid flow estimation
• Machine learning active-nematic hydrodynamics
• Learning dominant physical processes with data-driven balance models
• Data-driven resolvent analysis
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• A non-intrusive reduced order modeling framework for quasi-geostrophic turbulence
• A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers
• 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
• 2022 Review of Data-Driven Plasma Science
• Machine learning building-block-flow wall model for large-eddy simulation
• Explore missing flow dynamics by physics-informed deep learning: the parameterised governing systems
• Super-resolution reconstruction of turbulent flow at various Reynolds numbers based on generative adversarial networks
• Long-term predictions of turbulence by implicit U-Net enhanced Fourier neural operator
• Data-driven cardiovascular flow modeling: examples and opportunities
• Similarity of wake characteristics for yawed wind turbines of utility-scale
• Confronting Grand Challenges in Environmental Fluid Mechanics
• Learned Turbulence Modelling with Differentiable Fluid Solvers: Physics-based Loss-functions and Optimisation Horizons
• Learned discretizations for passive scalar advection in a 2-D turbulent flow
• Reservoir computing model of two-dimensional turbulent convection
• Turbulent scalar flux in inclined jets in crossflow: counter gradient transport and deep learning modelling
• Prediction of Reynolds Stresses in High-Mach-Number Turbulent Boundary Layers using Physics-Informed Machine Learning
• Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning
• Physics-informed data based neural networks for two-dimensional turbulence
• A long short-term memory embedding for hybrid uplifted reduced order models
• Attention-Enhanced Neural Network Models for Turbulence Simulation
• Multi-Objective CFD-Driven Development of Coupled Turbulence Closure Models
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• Neural Network Models for the Anisotropic Reynolds Stress Tensor in Turbulent Channel Flow
• Synthetic Lagrangian Turbulence by Generative Diffusion Models
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• Mean-flow Data Assimilation based on minimal correction of turbulence models: application to turbulent high-Reynolds number backward-facing step
• Model fusion with physics-guided machine learning
• Turbulence closure modeling with data-driven techniques: physical compatibility and consistency considerations
• Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence
• Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows
• Learning nonlocal constitutive models with neural networks
• Machine Learning for Physics-Informed Generation of Dispersed Multiphase Flow Using Generative Adversarial Networks
• Turbulence Enrichment using Physics-informed Generative Adversarial Networks
• Physics-Informed Echo State Networks
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• An Iterative Machine-Learning Framework for RANS Turbulence Modeling
• Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning
• Data-driven turbulence modeling in separated flows considering physical mechanism analysis
• CFD-driven Symbolic Identification of Algebraic Reynolds-Stress Models
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Data-assisted combustion simulations with dynamic submodel assignment using random forests
• Deep-learning assisted reduced order model for high-dimensional flow prediction from sparse data
• Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models
• Physical invariance in neural networks for subgrid-scale scalar flux modeling
• OpenFOAMGPT: a RAG-Augmented LLM Agent for OpenFOAM-Based Computational Fluid Dynamics
• Dimensionality Reduction and Reduced Order Modeling for Traveling Wave Physics
• Single-snapshot machine learning for super-resolution of turbulence
• Deep Learning Closure Models for Large-Eddy Simulation of Flows around Bluff Bodies
• Forecasting small scale dynamics of fluid turbulence using deep neural networks
• Transfer learning for nonlinear dynamics and its application to fluid turbulence
• Deep Structured Neural Networks for Turbulence Closure Modelling
• Development of a Generalizable Data-driven Turbulence Model: Conditioned Field Inversion and Symbolic Regression
• Climbing down Charney's ladder: Machine Learning and the post-Dennard era of computational climate science
• Data augmented turbulence modeling for three-dimensional separation flows
• Reinforcement-learning-based actuator selection method for active flow control
• Deep learning of the spanwise-averaged Navier-Stokes equations
• Physics-driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks
• Parameter uncertainty quantification in an idealized GCM with a seasonal cycle
• Invariant Data-Driven Subgrid Stress Modeling in the Strain-Rate Eigenframe for Large Eddy Simulation
• Interpreted machine learning in fluid dynamics: Explaining relaminarisation events in wall-bounded shear flows
• Physically Interpretable Feature Learning and Inverse Design of Supercritical Airfoils
• An iterative data-driven turbulence modeling framework based on Reynolds stress representation
• Spontaneous Self-Constraint in Active Nematic Flows
• Reconstruction of three-dimensional turbulent flow structures using surface measurements for free-surface flows based on a convolutional neural network
• Identifying key differences between linear stochastic estimation and neural networks for fluid flow regressions
• Machine Learning to Predict Aerodynamic Stall
• Physics-aware deep neural networks for surrogate modeling of turbulent natural convection
• Frozen propagation of Reynolds force vector from high-fidelity data into Reynolds-averaged simulations of secondary flows
• Influence of adversarial training on super-resolution turbulence reconstruction
• Adaptive Model Refinement Approach for Bayesian Uncertainty Quantification in Turbulence Model
• Data-driven Modeling of Rotating Detonation Waves
• Discovering explicit Reynolds-averaged turbulence closures for turbulent separated flows through deep learning-based symbolic regression with non-linear corrections
• Combining direct and indirect sparse data for learning generalizable turbulence models
• Log-law recovery through reinforcement-learning wall model for large-eddy simulation
• A data-driven approach for the closure of RANS models by the divergence of the Reynolds Stress Tensor
• Modal Analysis of Fluid Flows: Applications and Outlook
• Convolutional-network models to predict wall-bounded turbulence from wall quantities
• Physics-Informed Echo State Networks for Chaotic Systems Forecasting
• Self-critical machine-learning wall-modeled LES for external aerodynamics
• Customized data-driven RANS closures for bi-fidelity LES-RANS optimization
• Calibrating hypersonic turbulence flow models with the HIFiRE-1 experiment using data-driven machine-learned models
• Robust training approach of neural networks for fluid flow state estimations
• Compressing fluid flows with nonlinear machine learning: mode decomposition, latent modeling, and flow control
• A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks
• Frame invariant neural network closures for Kraichnan turbulence
• Towards learning Lattice Boltzmann collision operators
• Deep learning reduces sensor requirements for gust rejection on a small uncrewed aerial vehicle morphing wing
• A variational data assimilation approach for sparse velocity reference data in coarse RANS simulations through a corrective forcing term
• Echo State Network for two-dimensional turbulent moist Rayleigh-Bénard convection
• Space-dependent Aggregation of Stochastic Data-driven Turbulence Models
• Uncertainty Quantification for Data-driven Turbulence Modelling with Mondrian Forests
• Data-driven algebraic models of the turbulent Prandtl number for buoyancy-affected flow near a vertical surface
• Nonequilibrium Statistical Mechanics and Optimal Prediction of Partially-Observed Complex Systems
• Discretize first, filter next: learning divergence-consistent closure models for large-eddy simulation
• On the generalizability of machine-learning-assisted anisotropy mappings for predictive turbulence modelling
• Variational assimilation of sparse time-averaged data for efficient adjoint-based optimization of unsteady RANS simulations
• Enforcing Boundary Conditions on Physical Fields in Bayesian Inversion
• Revisiting Tensor Basis Neural Networks for Reynolds stress modeling: application to plane channel and square duct flows
• Assessment of Neural Network Augmented Reynolds Averaged Navier Stokes Turbulence Model in Extrapolation Modes
• Image-based flow decomposition using empirical wavelet transform
• Progressive augmentation of Reynolds stress tensor models for secondary flow prediction by computational fluid dynamics driven surrogate optimisation
• Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows
• A Divide-and-Conquer Machine Learning Approach for Modelling Turbulent Flows
• Deep Learning of Conjugate Mappings
• Automating Turbulence Modeling by Multi-Agent Reinforcement Learning
• Reynolds-Averaged Turbulence Modeling Using Type I and Type II Machine Learning Frameworks with Deep Learning
• Generalizability of reservoir computing for flux-driven two-dimensional convection
• Robust deep learning for emulating turbulent viscosities
• Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings
• Temporally sparse data assimilation for the small-scale reconstruction of turbulence
• Filtered Partial Differential Equations: a robust surrogate constraint in physics-informed deep learning framework
• Neural Dynamical Operator: Continuous Spatial-Temporal Model with Gradient-Based and Derivative-Free Optimization Methods
• Training neural networks under physical constraints using a stochastic augmented Lagrangian approach
• Predicting the wall-shear stress and wall pressure through convolutional neural networks
• Ensemble data assimilation-based mixed subgrid-scale model for large-eddy simulations
• Synchronization of Low Reynolds Number Plane Couette Turbulence
• Explicit physics-informed neural networks for non-linear upscaling closure: the case of transport in tissues
• A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
• Physics-agnostic and Physics-infused machine learning for thin films flows: modeling, and predictions from small data
• On the use of recurrent neural networks for predictions of turbulent flows
• CGNSDE: Conditional Gaussian Neural Stochastic Differential Equation for Modeling Complex Systems and Data Assimilation
• Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
• A Machine Learning approach to enhance the SUPG stabilization method for advection-dominated differential problems
• turbo-RANS: Straightforward and Efficient Bayesian Optimization of Turbulence Model Coefficients
• Neural Networks for Nuclear Reactions in MAESTROeX
• CGKN: A Deep Learning Framework for Modeling Complex Dynamical Systems and Efficient Data Assimilation
• Evaluation of physics constrained data-driven methods for turbulence model uncertainty quantification
• Two-point stress-strain rate correlation structure and non-local eddy viscosity in turbulent flows
• Machine learning methods for turbulence modeling in subsonic flows over airfoils
• Data assimilation empowered neural network parameterizations for subgrid processes in geophysical flows
• Generative Adversarial Networks with Physical Evaluators for Spray Simulation of Pintle Injector
• Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Network
• A Numerical Proof of Shell Model Turbulence Closure
• Flow control by a hybrid use of machine learning and control theory
• Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow
• Data-driven approach for modeling Reynolds stress tensor with invariance preservation
• Pedestrian Wind Factor Estimation in Complex Urban Environments
• Promoting global stability in data-driven models of quadratic nonlinear dynamics
• Learning the Tangent Space of Dynamical Instabilities from Data
• Adjoint-based variational optimal mixed models for large-eddy simulation of turbulence
• Real-time forecasting of chaotic dynamics from sparse data and autoencoders
• Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection
• Optimized Flow Control based on Automatic Differentiation in Compressible Turbulent Channel Flows
• A Parallel Integrated Computational-Statistical Platform for Turbulent Transport Phenomena
• Improving accuracy of turbulence models by neural network
• Physically constrained eigenspace perturbation for turbulence model uncertainty estimation
• Optimal Closures in a Simple Model for Turbulent Flows
• How neural networks learn to classify chaotic time series
• Neural network-augmented eddy viscosity closures for turbulent premixed jet flames
• Input-output framework for actuated boundary layers
• Improved self-consistency of the Reynolds stress tensor eigenspace perturbation for uncertainty quantification
• Kinetic data-driven approach to turbulence subgrid modeling
• Data-driven Hi2Lo for Coarse-grid System Thermal Hydraulic Modeling
• Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils
• A unified understanding of scale-resolving simulations and near-wall modeling of turbulent flows using optimal finite element projections
• Artificial neural network approach for turbulence models: A local framework
• Adjoint-Based Enforcement of State Constraints in PDE Optimization Problems
• A Priori Uncertainty Quantification of Reacting Turbulence Closure Models using Bayesian Neural Networks
• Reducing Spatial Discretization Error on Coarse CFD Simulations Using an OpenFOAM-Embedded Deep Learning Framework
• Data-driven Selection of Coarse-Grained Models of Coupled Oscillators
• Data-driven Turbulence Modeling for Separated Flows Considering Non-Local Effect
• Large Language Model Driven Development of Turbulence Models
• A wall model based on neural networks for LES of turbulent flows over periodic hills
• Pressure scrambling effects and the quantification of turbulent scalar flux model uncertainties
• Reduced order modeling of fluid flows: Machine learning, Kolmogorov barrier, closure modeling, and partitioning
• Deep Learning parameterization of subgrid scales in wall-bounded turbulent flows
• Extracting self-similarity from data
• Model order reduction with neural networks: Application to laminar and turbulent flows
• Spectral adjoint-based assimilation of sparse data in unsteady simulations of turbulent flows
• A progressive data-augmented RANS model for enhanced wind-farm simulations
• Active learning of data-assimilation closures using Graph Neural Networks
• Physics-Based Machine Learning Closures and Wall Models for Hypersonic Transition-Continuum Boundary Layer Predictions
• Machine-learning-based simulation of turbulent flows over periodic hills using a hybrid U-Net and Fourier neural operator framework
• Convolutional Neural Network Models and Interpretability for the Anisotropic Reynolds Stress Tensor in Turbulent One-dimensional Flows
• Active Learning of Model Discrepancy with Bayesian Experimental Design
• Neural Network Complexity of Chaos and Turbulence
• Quantum Iterative Methods for Solving Differential Equations with Application to Computational Fluid Dynamics
• Progressive Mixture-of-Experts with autoencoder routing for continual RANS turbulence modelling
• Bayesian Experimental Design for Model Discrepancy Calibration: A Rivalry between Kullback--Leibler Divergence and Wasserstein Distance
• Study of Nonlinear Interaction between Waves and Ocean Currents Using High-Fidelity Simulation and Machine Learning
• Review and Examination of Input Feature Preparation Methods and Machine Learning Models for Turbulence Modeling
• Improving CFD simulations by local machine-learned correction
• Interpretable data-driven turbulence modeling for separated flows using symbolic regression with unit constraints
• Data-Driven RANS Closures Using a Relative Importance Term Analysis Based Classifier for 2D and 3D Separated Flows
• PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics
• Finding Closure Terms Directly from Coarse Data for 2D Turbulent Flow
• A turbulent eddy-viscosity surrogate modeling framework for Reynolds-Averaged Navier-Stokes simulations
• A data-driven approach to viscous fluid mechanics -- the stationary case
• Numerical Simulation of Three-dimensional High-Lift Configurations Using Data-Driven Turbulence Model
• Quantification of Model Uncertainty in RANS Simulations: A Review
• Revealing essential dynamics from high-dimensional fluid flow data and operators
• Uncertainty Quantification of Locally Nonlinear Dynamical Systems using Neural Networks
• Bayesian Experimental Design for Model Discrepancy Calibration: An Auto-Differentiable Ensemble Kalman Inversion Approach
• Data-driven nonlinear aerodynamics models with certifiably optimal boundedness properties
• Enhancing Data-Assimilation in CFD using Graph Neural Networks
• Data-driven detached-eddy simulations based on explicit algebraic stress expressions for turbulent flows
• Turbulence closure modeling with data-driven techniques: Investigation of generalizable deep neural networks
• Rotational and Reflectional Equivariant Convolutional Neural Network for data-limited applications: Multiphase Flow demonstration
• Helicity dynamics, inverse and bi-directional cascades in fluid and MHD turbulence: A brief review
• Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control
• Model-form uncertainty quantification in RANS simulations of wakes and power losses in wind farms
• Normalizing Flows as a Novel PDF Turbulence Model
• Mean- and unsteady-flow reconstruction with one or two time-resolved measurements
• Modeling compressed turbulent plasma with rapid viscosity variations
• Sparse data assimilation for under-resolved large-eddy simulations
• Excited state fluid mechanics and mathematical principles of separation and transition
• Data-driven quantification of model-form uncertainty in Reynolds-averaged simulations of wind farms
• Optimal Eddy Viscosity in Closure Models for 2D Turbulent Flows
• Physics-Informed Machine Learning of the Lagrangian Dynamics of Velocity Gradient Tensor
• Recurrent Neural Network for End-to-End Modeling of Laminar-Turbulent Transition
• Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection
• Vortex Detection from Quantum Data
• An evolve-then-correct reduced order model for hidden fluid dynamics
• An Initial Attempt of Converged Machine-Learning Assisted Turbulence Modeling in RANS Simulations with Eddy-Viscosity Hypothesis
• A Deep Learning Framework for Hydrogen-fueled Turbulent Combustion Simulation
• Reynolds Stress Modeling Using Data Driven Machine Learning Algorithms
• A block-random algorithm for learning on distributed, heterogeneous data
• Data-driven Augmentation of a Turbulence Model in Three dimensional Separated Flows
• Cause-and-effect approach to turbulence forecasting
• CFDagent: A Language-Guided, Zero-Shot Multi-Agent System for Complex Flow Simulation
• Network Compression for Machine-Learnt Fluid Simulations
• Ensemble gradient for learning turbulence models from indirect observations