Skip to yearly menu bar Skip to main content


Poster
in
Workshop: The Synergy of Scientific and Machine Learning Modelling (SynS & ML) Workshop

Physics-Constrained Random Forests for Turbulence Model Uncertainty Estimation

Marcel Matha

Keywords: [ uncertainty quantification ] [ CFD ] [ RANS ] [ Turbulence modeling ] [ Machine Learning ] [ Random Forest ]


Abstract:

To achieve virtual certification for industrial design, quantifying the uncertainties in simulation-driven processes is crucial. We discuss a physics-constrained approach to account for epistemic uncertainty of turbulence models. In order to eliminate user input, we incorporate a data-driven machine learning strategy. In addition to it, our study focuses on developing an a priori estimation of prediction confidence when accurate data is scarce.

Chat is not available.