Physics-Guided Machine Learning for Uncertainty Quantification in Turbulence Models

Minghan Chu, Weicheng Qian
11/7/2025
cs.LGphysics.flu-dyn

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

Predicting the evolution of turbulent flows is central across science and engineering. Most studies rely on simulations with turbulence models, whose empirical simplifications introduce epistemic uncertainty. The Eigenspace Perturbation Method (EPM) is a widely used physics-based approach to quantify model-form uncertainty, but being purely physics-based it can overpredict uncertainty bounds. We propose a convolutional neural network (CNN)-based modulation of EPM perturbation magnitudes to improve calibration while preserving physical consistency. Across canonical cases, the hybrid ML-EPM framework yields substantially tighter, better-calibrated uncertainty estimates than baseline EPM alone.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Physics-constrained Random Forests for Turbulence Model Uncertainty Estimation

86% match2023

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

85% match2023

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

83% match2025

Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference

82% match2025

Neural Measures for learning distributions of Random PDEs

82% match2025

Physically consistent and uncertainty-aware learning of spatiotemporal dynamics

81% match1 repo52025

Cite this paper

@article{chu2025physicsguided,
  title  = {Physics-Guided Machine Learning for Uncertainty Quantification in Turbulence Models},
  author = {Minghan Chu and Weicheng Qian},
  year   = {2025},
  eprint = {2511.05633},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.05633v1}
}

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/2511.05633.svg)](https://codeofpaper.com/paper/2511.05633)

Discussion