A Deep Learning Approach For Epistemic Uncertainty Quantification Of Turbulent Flow Simulations

TL;DR

This paper introduces a deep learning method to quantify epistemic uncertainty in turbulent flow simulations, improving upon existing physics-based approaches by providing more realistic uncertainty bounds through CNN-based predictions.

Contribution

It presents a novel deep learning framework that predicts perturbations to Reynolds stresses, enhancing uncertainty quantification in turbulence modeling beyond traditional physics-based methods.

Findings

Deep learning models outperform the Eigenspace Perturbation Method in uncertainty estimation.

CNNs effectively learn the difference between model predictions and high-fidelity data.

The approach results in more realistic and less conservative uncertainty bounds.

Abstract

Simulations of complex turbulent flow are part and parcel of the engineering design process. Eddy viscosity based turbulence models represent the workhorse for these simulations. The underlying simplifications in eddy viscosity models make them computationally inexpensive but also introduce structural uncertainties in their predictions. Currently the Eigenspace Perturbation Method is the only approach to predict these uncertainties. Due to its purely physics based nature this method often leads to unrealistically large uncertainty bounds that lead to exceedingly conservative designs. We use a Deep Learning based approach to address this issue. We control the perturbations using trained deep learning models that predict how much to perturb the modeled Reynolds stresses. This is executed using a Convolutional Neural Network that learns the difference between eddy viscosity based model predictions and high fidelity data as a mapping of flow features. We show that this approach leads to improvements over the Eigenspace Perturbation Method.