Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data

We show that the discrepancies in Reynolds-averaged Navier-Stokes (RANS) modeled Reynolds stresses can be explained by mean flow features. A physics-informed machine learning framework is proposed to improve the predictive capabilities of RANS models by leveraging existing direct numerical simulations databases.

• Publication year

  2016

• Venue

  arXiv: Fluid Dynamics

• Publication date

  2016-06-26

• Fields of study

  Physics, Computer Science

• Identifiers
  DOI 10.1103/PhysRevFluids.2.034603arXiv 1606.07987
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• An introduction to neural networks

  2018cited by this paper
• Visualization of High Dimensional Turbulence Simulation Data using t-SNE.

  2017cited by this paper
• Using field inversion to quantify functional errors in turbulence closures

  2016cited by this paper
• The chips are down for Moore’s law

  2016cited by this paper
• A paradigm for data-driven predictive modeling using field inversion and machine learning

  2016cited by this paper
• Data-Driven CFD Modeling of Turbulent Flows Through Complex Structures

  2016cited by this paper
• Quantifying Model Form Uncertainty in RANS Simulation of Wing-Body Junction Flow

  2016cited by this paper
• Physics-Informed Machine Learning for Predictive Turbulence Modeling: A Priori Assessment of Prediction Confidence

  2016cited by this paper
• UNCERTAINTY ANALYSIS AND DATA-DRIVEN MODEL ADVANCES FOR A JET-IN-CROSSFLOW

  2016cited by this paper
• Machine learning strategies for systems with invariance properties

  2016cited by this paper
• Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty

  2015influential reference
• Data-driven RANS for simulations of large wind farms

  2015cited by this paper
• New Approaches in Turbulence and Transition Modeling Using Data-driven Techniques

  2015cited by this paper
• A Bayesian Calibration–Prediction Method for Reducing Model-Form Uncertainties with Application in RANS Simulations

  2015influential reference
• Fundamental Limits to Moore's Law

  2015cited by this paper
• Componentality-based wall-blocking for RANS models

  2015cited by this paper
• Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: A data-driven, physics-informed Bayesian approach

  2015cited by this paper
• The deviation from parallel shear flow as an indicator of linear eddy-viscosity model inaccuracy

  2014cited by this paper
• Application of supervised learning to quantify uncertainties in turbulence and combustion modeling

  2013cited by this paper
• Classification and regression trees

  2012cited by this paper
• Development of a robust elliptic-blending turbulence model for near-wall, separated and buoyant flows

  2012cited by this paper
• Large-eddy simulation of turbulent boundary layer separation from a rounded step

  2012cited by this paper
• RANS modeling of turbulent mixing for a jet in supersonic cross flow: model evaluation and uncertainty quantification

  2012cited by this paper
• Modeling Structural Uncertainties in Reynolds-Averaged Computations of Shock/Boundary Layer Interactions

  2011cited by this paper
• Quantification of structural uncertainties in the k − ω turbulence model

  2010influential reference
• Permutation importance: a corrected feature importance measure

  2010cited by this paper
• Reynolds number dependence of mean flow structure in square duct turbulence

  2010cited by this paper
• UNCERTAINTY QUANTIFICATION FOR RANS TURBULENCE MODEL PREDICTIONS

  2009cited by this paper
• Eddies

  2009cited by this paper
• Flow over periodic hills – Numerical and experimental study in a wide range of Reynolds numbers

  2009cited by this paper
• A Bias Correction Algorithm for the Gini Variable Importance Measure in Classification Trees

  2008cited by this paper
• BMC Bioinformatics BioMed Central Methodology article

  2007cited by this paper
• Presentation of anisotropy properties of turbulence, invariants versus eigenvalue approaches

  2007cited by this paper
• On the relationships between local vortex identification schemes

  2005cited by this paper
• The Elements of Statistical Learning

  2003cited by this paper
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction

  2001influential reference
• An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods

  2001cited by this paper
• Bias Correction in Classification Tree Construction

  2001cited by this paper
• Random Forests

  2001influential reference
• An explicit algebraic Reynolds stress model for incompressible and compressible turbulent flows

  2000cited by this paper
• Strategies for turbulence modelling and simulations

  2000cited by this paper
• Turbulent Flows

  2000cited by this paper
• An Introduction to Support Vector Machines and Other Kernel-based Learning Methods

  2000cited by this paper
• The Random Subspace Method for Constructing Decision Forests

  1998cited by this paper
• A tensorial approach to computational continuum mechanics using object-oriented techniques

  1998cited by this paper
• Direct Numerical Simulation of Separated Turbulent Flow over a Wavy Boundary

  1996cited by this paper
• Two-equation eddy-viscosity turbulence models for engineering applications

  1994cited by this paper
• Turbulence modeling for CFD

  1993cited by this paper
• A One-Equation Turbulence Model for Aerodynamic Flows

  1992cited by this paper
• An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression

  1992cited by this paper
• Eddies, streams, and convergence zones in turbulent flows

  1988cited by this paper
• Reassessment of the scale-determining equation for advanced turbulence models

  1988cited by this paper
• Turbulent secondary flows

  1987cited by this paper
• Ground effects on pressure fluctuations in the atmospheric boundary layer

  1978influential reference
• The return to isotropy of homogeneous turbulence

  1977cited by this paper
• Progress in the development of a Reynolds-stress turbulence closure

  1975cited by this paper
• Application of the energy-dissipation model of turbulence to the calculation of flow near a spinning disc

  1974cited by this paper
• The prediction of laminarization with a two-equation model of turbulence

  1972cited by this paper

• AI-enhanced large-eddy simulation for urban wind flows: accelerating spin-up with Fourier neural operator initialization

  2026cites this paper
• Synergizing Transport-Based Generative Models and Latent Geometry for Stochastic Closure Modeling

  2026cites this paper
• Constructing a Reynolds Stress Model of Decaying Homogeneous Isotropic Turbulence Using Physics Informed Neural Network

  2026cites this paper
• Fluid drag reduction assisted by machine learning: A review

  2026cites this paper
• Development of a fast and accurate two-level machine learning framework for thermal striping prediction in parallel five jets of lead bismuth eutectic

  2026cites this paper
• Review of the development of turbulence models for low Prandtl number fluid flows and heat transfer based on machine learning techniques

  2026cites this paper
• Computational and physical considerations for the development of machine learning augmented turbulence models

  2026cites this paper
• Comparative Analysis of Nonlinear Data-Driven Modeling of Inlet Distortion for Nacelle Air-Intake System

  2026cites this paper
• A divide-and-conquer machine learning transition model for airfoil flows: from steady linear-lift to unsteady stall stage

  2026cites this paper
• Reynolds-averaged Navier-Stokes equations solution based on turbulence closure model of Reynolds stresses from direct numerical simulation in compressor cascade

  2026cites this paper
• Progressive Mixture-of-Experts with autoencoder routing for continual RANS turbulence modelling

  2026cites this paper
• Physics-Informed Machine Learning for Predicting IMC Growth in SAC305 Solder Joints Under Thermal-Humidity Stress

  2026cites this paper
• Constraints on constitutive relations in turbulence modeling

  2026influential citation
• Development of explicit algebraic LES wall models using consistent CFD-driven Machine Learning

  2026cites this paper
• Diff-FlowFSI: A GPU-optimized differentiable CFD platform for high-fidelity turbulence and FSI simulations

  2026cites this paper
• Machine learning integrated higher-order model application for critical heat flux investigations in pressurised water reactors

  2026cites this paper
• 物理和数据模型串行驱动的化学激光数值技术

  2026cites this paper
• Continental-Scale Mapping of Soil Nickel: Integration of Spectral Preprocessing and Machine Learning Approaches

  2026cites this paper
• Enhancing generalizability of machine learning general effective-viscosity turbulence model via tensor basis normalization

  2026cites this paper
• Research on the modeling method of unsteady aerodynamics for composite configuration based on the physics-embedded long short-term memory neural network

  2026cites this paper
• Monotone peridynamic neural operator for nonlinear material modeling with conditionally unique solutions

  2026cites this paper
• Large language model driven development of turbulence models

  2025cites this paper
• An interpretable machine learning-based model of turbulent Prandtl number for supercritical CO2 under buoyancy

  2025cites this paper
• Invariance-embedded Machine Learning Sub-grid-scale Stress Models for Meso-scale Hurricane Boundary Layer Flow Simulation I: Model Development and $\textit{a priori}$ Studies

  2025cites this paper
• Node Assigned physics-informed neural networks for thermal-hydraulic system simulation: CVH/FL module

  2025cites this paper
• Machine-learning-based simulation of turbulent flows over periodic hills using a hybrid U-Net and Fourier neural operator framework

  2025cites this paper
• A random forest machine learning in turbulence closure modeling for complex flows and heat transfer based on the non-equilibrium turbulence assumption

  2025cites this paper
• Bearing prognostics and health management based on hybrid physical mechanism and data models: a systematic review

  2025cites this paper
• Deep Learning-Based Multi-Scale Framework for Navier-Stokes Flow Characterization via Physics-Informed Neural Networks and Tensor Invariant Analysis

  2025cites this paper
• Monotone Peridynamic Neural Operator for Nonlinear Material Modeling with Conditionally Unique Solutions

  2025cites this paper
• A generalisable data-augmented turbulence model with progressive and interpretable corrections for incompressible wall-bounded flows

  2025cites this paper
• Bayesian Experimental Design for Model Discrepancy Calibration: An Auto-Differentiable Ensemble Kalman Inversion Approach

  2025cites this paper
• Data-Driven Turbulence Modelling for Magnetohydrodynamic Flows in Annular Pipes

  2025cites this paper
• Vector-based neural network turbulent heat flux closures in near-wall cooling jet flows

  2025cites this paper
• An Implicit Adaptive Fourier Neural Operator for Long-term Predictions of Three-dimensional Turbulence

  2025cites this paper
• Assessment of non-intrusive sensing in wall-bounded turbulence through explainable deep learning

  2025cites this paper
• An Optimized Deep Learning Framework for Turbulence Modeling

  2025cites this paper
• Fluid Intelligence: A Forward Look on AI Foundation Models in Computational Fluid Dynamics

  2025cites this paper
• Data-driven modelling of spray flows: Current status and future direction

  2025cites this paper
• Improvement of the SST model for streamline curvature effect based on field inversion and symbolic regression

  2025cites this paper
• Sparse-sensor reconstruction of oblique detonation-wave temperature fields using a diffusion-guided residual coordinate-attention U-shaped network

  2025cites this paper
• A Deep Learning-Based Mapping Model for Three-Dimensional Propeller RANS and LES Flow Fields

  2025cites this paper
• Deep Learning Method for Airfoil Flow Field Simulation Based on Unet++

  2025cites this paper
• Active Learning of Model Discrepancy with Bayesian Experimental Design

  2025cites this paper
• Using Physics-Informed neural networks for solving Navier-Stokes equations in fluid dynamic complex scenarios

  2025cites this paper
• Data-driven and knowledge-driven prediction methods for ventilated cavities based on Gaussian process

  2025cites this paper
• An artificial neural network-based quadratic constitutive Reynolds stress model for separated turbulent flows using data-augmented field inversion and machine learning

  2025cites this paper
• Flow field reconstruction and prediction of the two-dimensional cylinder flow using data-driven physics-informed neural network combined with long short-term memory

  2025cites this paper
• Integrating neural networks with numerical schemes for dynamical systems: A review

  2025cites this paper
• Data-Driven RANS Closures Using a Relative Importance Term Analysis Based Classifier for 2D and 3D Separated Flows

  2025cites this paper
• Data-driven detached-eddy simulations based on explicit algebraic stress expressions for turbulent flows

  2025cites this paper
• Turbulence Closure in RANS and Flow Inference around a Cylinder using PINNs and Sparse Experimental Data

  2025cites this paper
• Adverse-Pressure-Gradient Turbulence Model Improvement via Mixing-Length and Symbolic Regression

  2025cites this paper
• Mitigating ill-conditioning of Reynolds-averaged Navier–Stokes equations for experimental data-driven turbulence closures

  2025cites this paper
• From Flow Physics to Machine Learning: A Comprehensive Review and Future Perspectives on Axial Flow and Centrifugal Compressors

  2025cites this paper
• Design of an Experimental Teaching Platform for Flow-Around Structures and AI-Driven Modeling in Marine Engineering

  2025cites this paper
• Turbulence modeling in CFD with Bayesian uncertainty quantification: A comparative study of finite volume and high-order discontinuous Galerkin methods

  2025cites this paper
• A proposal for automated turbulence modelling

  2025cites this paper
• Artificial intelligence in fluid dynamics and thermal transport: A comprehensive review of methods, challenges, and emerging applications

  2025cites this paper
• An Extension to the Grid-Induced Machine Learning CFD Framework for Turbulent Flows

  2025cites this paper
• A Comprehensive Multi-Source Uncertainty Quantification Method for RANS-CFD Based on Sparse Multi-Task Deep Active Learning

  2025cites this paper
• A framework for learning symbolic turbulence models from indirect observation data via neural networks and feature importance analysis

  2025cites this paper
• Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Network

  2025cites this paper
• Surrogate modeling for flow simulations using design variable-coded deep learning networks

  2025cites this paper
• Kolmogorov–Arnold networks for turbulence anisotropy mapping

  2025cites this paper
• Source Term Estimation for Puff Releases Using Machine Learning: A Case Study

  2025cites this paper
• Using Delayed Detached Eddy Simulation to create datasets for data-driven turbulence modeling: A periodic hills with parameterized geometry case

  2025cites this paper
• Research on multi-channel adaptive coupling prediction system of fusing physical information for spatio-temporal correlation heterogeneity of methane concentration

  2025cites this paper
• A Scientometric Investigation of Artificial Intelligence for Fluid Mechanics: Emerging Topics and Active Groups

  2025cites this paper
• Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Score-based Generative Models

  2025cites this paper
• Data-driven quantum Koopman method for simulating nonlinear dynamics

  2025cites this paper
• LVM-GP: Uncertainty-Aware PDE Solver via coupling latent variable model and Gaussian process

  2025cites this paper
• Prediction of coal and gas outbursts based on physics informed neural networks and traditional machine learning models

  2025cites this paper
• A polar turbulence invariant map with applicability to realisable machine learning turbulence models

  2025cites this paper
• Physics-Informed Machine Learning Approach in Augmenting RANS Models Using DNS Data and DeepInsight Method on FDA Nozzle

  2025cites this paper
• oRANS: Online optimisation of RANS machine learning models with embedded DNS data generation

  2025cites this paper
• Enhancing Computational Fluid Dynamics Simulations with Machine Learning: Techniques, Challenges, and Future Prospects

  2025cites this paper
• Machine Learning enhanced parametric Reynolds-averaged Navier-Stokes equations at the full and reduced order levels

  2025cites this paper
• Three-dimensional seepage analysis for the tunnel in nonhomogeneous porous media with physics-informed deep learning

  2025cites this paper
• Uncertainty and error quantification for data-driven Reynolds-averaged turbulence modelling with mean-variance estimation networks

  2025influential citation
• WF-PINNs: solving forward and inverse problems of burgers equation with steep gradients using weak-form physics-informed neural networks

  2025cites this paper
• Physics-enhanced data-driven turbulence model for flow around submerged bodies

  2025cites this paper
• Global Navigation Satellite System (GNSS) radio occultation climatologies mapped by machine learning and Bayesian interpolation

  2025cites this paper
• Bayesian Neural Networks With Physics-Informed Priors With Application to Boundary Layer Velocity

  2025cites this paper
• Utilizing physics-informed neural networks to advance daylighting simulations in buildings

  2025cites this paper
• A physics-informed neural network for turbulent wake simulations behind wind turbines

  2025cites this paper
• Improved State Estimation for turbulent flows combining Ensemble Data Assimilation and Machine Learning

  2025cites this paper
• AutoTurb: Using large language models for automatic algebraic turbulence model discovery

  2025cites this paper
• Augmentation of predictive turbulence modeling applied to low pressure turbines using adaptive field inversion

  2025cites this paper
• A multiscale Pseudo-DNS approach for solving turbulent boundary-layer problems

  2025cites this paper
• A review on full-, zero-, and partial-knowledge based predictive models for industrial applications

  2025cites this paper
• Lagrangian Attention Tensor Networks for Velocity Gradient Statistical Modeling

  2025cites this paper
• Interpreting tensor basis neural networks with symbolic transcendental Reynolds stress models for transonic axial compressor flows

  2025cites this paper
• Exploring the Potential and the Practical Usability of a Machine Learning Approach for Improving Wall Friction Predictions of RANS Wall Functions in Non-equilibrium Turbulent Flows

  2024cites this paper
• A data‐driven turbulence modeling for the Reynolds stress tensor transport equation

  2024cites this paper
• Ensemble variational method with adaptive covariance inflation for learning neural network-based turbulence models

  2024cites this paper
• Mixing artificial and natural intelligence: from statistical mechanics to AI and back to turbulence

  2024cites this paper
• Data-driven RANS closures for improving mean field calculation of separated flows

  2024cites this paper
• A machine learning model for reconstructing skin-friction drag over ocean surface waves

  2024cites this paper
• CoNFiLD: Conditional Neural Field Latent Diffusion Model Generating Spatiotemporal Turbulence

  2024cites this paper