Physics-Guided Machine Learning for Uncertainty Quantification in Turbulence Models

2025/11/07 by Minghan Chu, Chu, Minghan, Weicheng Qian +1
Computer Science · Decision Sciences · Physics and Astronomy · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Probabilistic and Robust Engineering Design

paper · pdf · doi:10.48550/arxiv.2511.05633

openalex publication_date 2025/11/07 · openalex created_date 2025/11/12 · openalex updated_date 2026/07/28

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.

Citations

• Physics Constrained Unsupervised Deep Learning for Rapid, High Resolution Scanning Coherent Diffraction Reconstruction
• Multi-Fidelity modeling of Probabilistic Aerodynamic Databases for Use\n in Aerospace Engineering
• Machine Learning for Fluid Mechanics
• Turbulence Modeling in the Age of Data
• An uncertainty estimation module for turbulence model predictions in SU2
• Tackling Turbulence with Supercomputers

Related

• Uncertainty Quantification For Turbulent Flows with Machine Learning
• Multi-Fidelity Data Assimilation For Physics Inspired Machine Learning In Uncertainty Quantification Of Fluid Turbulence Simulations
• Towards Physics Constrained Deep Learning Based Turbulence Model Uncertainty Quantification
• Multi-fidelity Deep Learning-based methodology for epistemic uncertainty quantification of turbulence models
• Physics Constrained Deep Learning For Turbulence Model Uncertainty Quantification