Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework

We present a comprehensive framework for augmenting turbulence models with physics-informed machine learning, illustrating a complete workflow from identification of input/output to prediction of mean velocities. The learned model has Galilean invariance and coordinate rotational invariance.

Physics Computer Science

View graph Source

Paper

References (81)

01Turbulence Modeling in the Age of DataK. Duraisamy, G. Iaccarino, Heng Xiao2018 · Annual Review of Fluid Mechanics · 1.5k citations

02Reynolds-averaged Navier–Stokes equations with explicit data-driven Reynolds stress closure can be ill-conditionedJin-Long Wu, Heng Xiao, Rui Sun et al.2018 · Journal of Fluid Mechanics · 197 citations

03The development of algebraic stress models using a novel evolutionary algorithmJack Weatheritt, R. Sandberg2017 · 154 citations

04Data-Driven Integral Boundary-Layer Modeling for Airfoil Performance Prediction in Laminar RegimeA. Marques, Qiqi Wang, Y. Marzouk2017 · 5 citations

05Representation of Reynolds Stress Perturbations with Application in Machine-Learning-Assisted Turbulence ModelingJin-Long Wu, Rui Sun, S. Laizet et al.2017 · 9 citations In Library

06Subgrid-scale scalar flux modelling based on optimal estimation theory and machine-learning proceduresA. Vollant, G. Balarac, C. Corre2017 · 111 citations

07A neural network approach for the blind deconvolution of turbulent flowsR. Maulik, O. San2017 · Journal of Fluid Mechanics · 212 citations In Library

08Improved RANS Computations of Flow over the 25°-Slant-Angle Ahmed BodyR. Maduta, S. Jakirlic2017 · 6 citations

09A Priori Assessment of Prediction Confidence for Data-Driven Turbulence ModelingJin-Long Wu, Jian-Xun Wang, Heng Xiao et al.2017 · Flow Turbulence and Combustion · 19 citations

10On the accuracy of RANS simulations with DNS data.S. Poroseva, J. Colmenares F., S. Murman2016 · The Physics of Fluids · 64 citations

11A novel evolutionary algorithm applied to algebraic modifications of the RANS stress-strain relationshipJack Weatheritt, R. Sandberg2016 · Journal of Computational Physics · 313 citations

12Reynolds averaged turbulence modelling using deep neural networks with embedded invarianceJulia Ling, A. Kurzawski, J. Templeton2016 · Journal of Fluid Mechanics · 1.6k citations

Scroll for more · 38 remaining

Similar papers

Multi-Fidelity Data Assimilation For Physics Inspired Machine Learning In Uncertainty Quantification Of Fluid Turbulence SimulationsMinghan Chu, Weicheng Qian2023 · 0 citations In Library

Machine Learning for Turbulence Modeling and PredictionsS. Bhushan, G. Burgreen, D. Martínez et al.2020 · Volume 3: Computational Fluid Dynamics; Micro and Nano Fluid Dynamics · 4 citations In Library

Probabilistic Machine Learning to Improve Generalisation of Data-Driven Turbulence ModellingJ. Ho, Nick Pepper, T. Dodwell2023 · Social Science Research Network · 8 citations In Library

Physics Constrained Deep Learning For Turbulence Model Uncertainty QuantificationMinghan Chu, Weicheng Qian2024 · 1 citation In Library

Physics-Informed Machine Learning Approach in Augmenting RANS Models Using DNS Data and DeepInsight Method on FDA NozzleHossein Geshani, M. R. Dehkordi, M. Panahi2025 · arXiv.org · 0 citations In Library

Physics-informed Machine Learning for Modeling Turbulence in SupernovaeP. Karpov, Chengkun Huang, Iskandar Sitdikov et al.2022 · Astrophysical Journal · 16 citations In Library

Physics-guided deep learning framework for predictive modeling of Reynolds stress anisotropyChao Jiang2021 · 30 citations In Library

Physics-informed machine learning: case studies for weather and climate modellingK. Kashinath, M. Mustafa, A. Albert et al.2021 · Philosophical Transactions of the Royal Society A · 660 citations In Library

Applicability of machine learning in uncertainty quantification of turbulence modelsM. Matha, Karsten Kucharczyk2022 · 2 citations In Library

Physics-Guided Machine Learning for Uncertainty Quantification in Turbulence ModelsMinghan Chu, Weicheng Qian2025 · arXiv.org · 0 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal