A Priori Uncertainty Quantification of Reacting Turbulence Closure Models using Bayesian Neural Networks

Graham Pash, Malik Hassanaly, Shashank Yellapantula
2/28/2024
physics.flu-dyncs.LGphysics.data-an

No official code found. Best implementation: NatLabRockies/mluq-prop (2 stars, BSD-3-Clause-Clear, last commit 2025-12-10).

Abstract

While many physics-based closure model forms have been posited for the sub-filter scale (SFS) in large eddy simulation (LES), vast amounts of data available from direct numerical simulation (DNS) create opportunities to leverage data-driven modeling techniques. Albeit flexible, data-driven models still depend on the dataset and the functional form of the model chosen. Increased adoption of such models requires reliable uncertainty estimates both in the data-informed and out-of-distribution regimes. In this work, we employ Bayesian neural networks (BNNs) to capture both epistemic and aleatoric uncertainties in a reacting flow model. In particular, we model the filtered progress variable scalar dissipation rate which plays a key role in the dynamics of turbulent premixed flames. We demonstrate that BNN models can provide unique insights about the structure of uncertainty of the data-driven closure models. We also propose a method for the incorporation of out-of-distribution information in a BNN. The efficacy of the model is demonstrated by a priori evaluation on a dataset consisting of a variety of flame conditions and fuels.

View on arXivView PDF

Code Implementations(1)

NatLabRockies/mluq-propCommunity100%
BSD-3-Clause-Clear

Bayesian Neural Networks to enable Data-Driven Uncertainty Propagation

27Shell, PythonOct 23, 202310 months agoBSD-3-Clause-Clear

Similar Papers

Quantifying Out-of-Training Uncertainty of Neural-Network based Turbulence Closures

85% match2025

Evaluation of machine learning architectures on the quantification of epistemic and aleatoric uncertainties in complex dynamical systems

83% match2023

Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modeling

82% match2024

A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty

81% match1 repo12023

Physics-constrained Random Forests for Turbulence Model Uncertainty Estimation

81% match2023

Probabilistic transfer learning methodology to expedite high fidelity simulation of reactive flows

80% match2024

Cite this paper

@article{pash2024priori,
  title  = {A Priori Uncertainty Quantification of Reacting Turbulence Closure Models using Bayesian Neural Networks},
  author = {Graham Pash and Malik Hassanaly and Shashank Yellapantula},
  year   = {2024},
  eprint = {2402.18729},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.18729v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.18729.svg)](https://codeofpaper.com/paper/2402.18729)

Discussion