Physics-Constrained Random Forests for Turbulence Model Uncertainty Estimation
Keywords: Machine Learning, turbulence modeling, RANS, CFD, Random Forest, Uncertainty Quantification
TL;DR: We present a hybrid framework that combines a physics-based UQ methodology with data-driven ML.
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.
Submission Number: 32
Loading