# Physics-Guided Machine Learning for Uncertainty Quantification in Turbulence Models

arXiv: https://arxiv.org/abs/2511.05633 · HTML: https://mlsanity.com/paper/2511.05633/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 44 references that are in the map.
- First posted on arXiv 7 Nov 2025.

## Builds on (most cited first, 5 of 5)

- [Machine Learning for Fluid Mechanics](https://mlsanity.com/paper/1905.11075/) (2019)
- [Physics Constrained Unsupervised Deep Learning for Rapid, High Resolution Scanning Coherent Diffraction Reconstruction](https://mlsanity.com/paper/2306.11014/) (2023)
- [Data-assisted combustion simulations with dynamic submodel assignment using random forests](https://mlsanity.com/paper/2009.04023/) (2020)
- [Interpretable Data-driven Methods for Subgrid-scale Closure in LES for Transcritical LOX/GCH4 Combustion](https://mlsanity.com/paper/2103.06397/) (2021)
- [Evaluation of physics constrained data-driven methods for turbulence model uncertainty quantification](https://mlsanity.com/paper/2210.00002/) (2022)

## Abstract (arXiv)

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.