Physics-Constrained Random Forests for Turbulence Model Uncertainty Estimation

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.

Cite

Text

Matha. "Physics-Constrained Random Forests for Turbulence Model Uncertainty Estimation." ICML 2023 Workshops: SynS_and_ML, 2023.

Markdown

[Matha. "Physics-Constrained Random Forests for Turbulence Model Uncertainty Estimation." ICML 2023 Workshops: SynS_and_ML, 2023.](https://mlanthology.org/icmlw/2023/matha2023icmlw-physicsconstrained/)

BibTeX

@inproceedings{matha2023icmlw-physicsconstrained,
  title     = {{Physics-Constrained Random Forests for Turbulence Model Uncertainty Estimation}},
  author    = {Matha, Marcel},
  booktitle = {ICML 2023 Workshops: SynS_and_ML},
  year      = {2023},
  url       = {https://mlanthology.org/icmlw/2023/matha2023icmlw-physicsconstrained/}
}