Probabilistic machine learning to improve generalisation of data-driven turbulence modelling

DOI10.1016/J.COMPFLUID.2024.106443MaRDI QIDQ6989004zbMATH OpenFDO

Authors Joel Ho, Nick Pepper, Tim Dodwell

Publication date 30 April 2025

Published in Computers and Fluids (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.COMPFLUID.2024.106443

zbMATH Keywords

computational fluid dynamicsturbulence modellingfield inversionprobabilistic machine learningGaussian process emulatorsdeep ensembles

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Finite volume methods for initial value and initial-boundary value problems involving PDEs (65M08) Turbulence (76Fxx) Mathematical modeling or simulation for problems pertaining to fluid mechanics (76-10)

Cites work

• A more general effective-viscosity hypothesis
• A novel evolutionary algorithm applied to algebraic modifications of the RANS stress-strain relationship
• A paradigm for data-driven predictive modeling using field inversion and machine learning
• An aerodynamic design optimization framework using a discrete adjoint approach with OpenFOAM
• Gaussian processes for machine learning.
• Highly resolved large-eddy simulation of separated flow in a channel with streamwise periodic constrictions
• Hydrodynamic instabilities and turbulence. Rayleigh-Taylor, Richtmyer-Meshkov, and Kelvin-Helmholtz mixing (to appear)
• Large-eddy simulation of turbulent flow over a parametric set of bumps
• Machine learning strategies for systems with invariance properties
• On the Generalizability of Machine-Learning-Assisted Anisotropy Mappings for Predictive Turbulence Modelling
• Probabilistic machine learning. An introduction
• Random forests
• Rayleigh-Taylor and Richtmyer-Meshkov instability induced flow, turbulence, and mixing. II
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• The design and analysis of computer experiments.
• The law of the wake in the turbulent boundary layer
• Toward neural-network-based large eddy simulation: application to turbulent channel flow
• Turbulence modeling in the age of data

Cited in

(1)

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

This page was built for publication: Probabilistic machine learning to improve generalisation of data-driven turbulence modelling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6989004)