Physics-Guided Machine Learning for Uncertainty Quantification in Turbulence Models

• URL: http://arxiv.org/abs/2511.05633v1
• Date: Fri, 07 Nov 2025 07:48:12 GMT
• Title: Physics-Guided Machine Learning for Uncertainty Quantification in Turbulence Models
• Abstract summary: Eigenspace Perturbation Method (EPM) is a widely used physics-based approach to quantify model-form uncertainty.<n>We propose a convolutional neural network (CNN)-based modulation of EPM magnitudes to improve calibration.<n>Across canonical cases, the hybrid ML-EPM framework yields substantially tighter, better-calibrated uncertainty estimates than baseline EPM alone.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Error Propagation Theory for Variational Non-Markovian Open Quantum Dynamics [10.049898018843265]
  Even minute errors in the time evolution can translate into substantial deviations in physical observables.<n>We develop a theoretical framework that characterizes error propagation in variational non-Markovian dynamics.<n>Our analysis uncovers an intrinsic error-backflow mechanism driven by long-lived environmental memory.
  arXiv  Detail & Related papers  (2026-08-23T13:17:46Z)
• Equivariant Evidential Deep Learning for Interatomic Potentials [55.6997213490859]
  Uncertainty quantification is critical for assessing the reliability of machine learning interatomic potentials in molecular dynamics simulations.<n>Existing UQ approaches for MLIPs are often limited by high computational cost or suboptimal performance.<n>We propose textitEquivariant Evidential Deep Learning for Interatomic Potentials ($texte2$IP), a backbone-agnostic framework that models atomic forces and their uncertainty jointly.
  arXiv  Detail & Related papers  (2026-02-11T02:00:25Z)
• From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures [12.68400434984463]
  MLIPs fail to reproduce the physical smoothness of the quantum potential energy surface.<n>Existing evaluations, such as microcanonical molecular dynamics, are computationally expensive and primarily probe near-equilibrium states.<n>We introduce the Bond Smoothness Characterization Test (BSCT) to improve evaluation metrics for MLIPs.
  arXiv  Detail & Related papers  (2026-02-04T18:50:10Z)
• Bridging the Gap Between Bayesian Deep Learning and Ensemble Weather Forecasts [100.26854618129039]
  Weather forecasting is fundamentally challenged by the chaotic nature of the atmosphere.<n>Recent advances in Bayesian Deep Learning (BDL) offer a promising but often disconnected alternative.<n>We bridge these paradigms through a unified hybrid BDL framework for ensemble weather forecasting.
  arXiv  Detail & Related papers  (2025-11-18T07:49:52Z)
• MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics [72.00014675808228]
  Instability in Large Language Models evaluation process obscures true learning dynamics.<n>We introduce textbfMaP, a framework that integrates underlineMerging underlineand the underlinePass@k metric.<n>Experiments show that MaP yields significantly smoother performance curves, reduces inter-run variance, and ensures more consistent rankings.
  arXiv  Detail & Related papers  (2025-10-10T11:40:27Z)
• Bayesian Physics Informed Neural Networks for Reliable Transformer Prognostics [1.53934570513443]
  This work introduces a Bayesian Physics-Informed Neural Network (B-PINN) framework for probabilistic prognostics estimation.<n>The framework is validated against a finite element model developed and tested with real measurements from a solar power plant.<n>Results, benchmarked against a dropout-PINN baseline, show that the proposed B-PINN delivers more reliable prognostic predictions by accurately quantifying predictive uncertainty.
  arXiv  Detail & Related papers  (2025-09-19T12:39:15Z)
• Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting [7.705860755153007]
  Molecular dynamics (MD) simulation is vital for understanding atomic-scale processes in materials science and biophysics.<n>Traditional density functional theory (DFT) methods are computationally expensive, which limits the feasibility of long-term simulations.<n>We propose a novel approach that formulates MD simulation as a time-series forecasting problem.
  arXiv  Detail & Related papers  (2025-09-16T02:00:52Z)
• BLIPs: Bayesian Learned Interatomic Potentials [47.73617239750485]
  Machine Learning Interatomic Potentials (MLIPs) are becoming a central tool in simulation-based chemistry.<n>MLIPs do not provide uncertainty estimates by construction, which are fundamental to guide active learning pipelines.<n>BLIP is a scalable, architecture-agnostic variational Bayesian framework for training or fine-tuning MLIPs.
  arXiv  Detail & Related papers  (2025-08-19T17:28:14Z)
• Modeling Membrane Degradation in PEM Electrolyzers with Physics-Informed Neural Networks [45.32169712547367]
  Proton exchange membrane (PEM) electrolyzers are pivotal for sustainable hydrogen production.<n>Their long-term performance is hindered by membrane degradation, which poses reliability and safety challenges.<n>Traditional physics-based models have been developed, offering interpretability but requiring numerous parameters that are often difficult to measure and calibrate.<n>This study presents the first application of Physics-Informed Neural Networks (PINNs) to model membrane degradation in PEM electrolyzers.
  arXiv  Detail & Related papers  (2025-06-19T15:46:49Z)
• SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing Flows [0.0]
  This paper introduces Symmetry-Enforcing Modulation (SESaMo)<n>SESaMo enables the incorporation of biases (e.g., symmetries) into normalizing flows through a novel technique called inductive modulation.<n>Our numerical experiments benchmark SESaMo in different scenarios, including an 8-Gaussian mixture model and physically relevant field theories.
  arXiv  Detail & Related papers  (2025-05-26T07:34:11Z)
• Spatiotemporal Field Generation Based on Hybrid Mamba-Transformer with Physics-informed Fine-tuning [46.67399627400437]
  This research confronts the challenge of substantial physical equation discrepancies in the generation of physical fields through trained models.<n>A physical field generation model, named HMT-PF, is developed based on the hybrid Mamba-Transformer architecture.
  arXiv  Detail & Related papers  (2025-05-16T14:40:56Z)
• BPINN-EM-Post: Bayesian Physics-Informed Neural Network based Stochastic Electromigration Damage Analysis in the Post-void Phase [1.5815043033726341]
  We introduce a novel machine learning-based framework, termed BPINN-EM-PostSpice, for efficient analysis of EM-induced post-voiding aging processes.<n>We show that BPINN-EM-PostSpice achieves over 240x and more than 67x speedup compared to Monte Carlo simulations.
  arXiv  Detail & Related papers  (2025-03-18T00:31:12Z)
• Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation [50.920911532133154]
  The intrinsic ill-posedness and ordinal-sensitive nature of monocular depth estimation (MDE) models pose major challenges to the estimation of uncertainty degree. We propose to model the uncertainty of MDE models from the perspective of the inherent probability distributions. By simply introducing additional training regularization terms, our model, with surprisingly simple formations and without requiring extra modules or multiple inferences, can provide uncertainty estimations with state-of-the-art reliability.
  arXiv  Detail & Related papers  (2023-07-19T12:11:15Z)
• Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
  empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
  arXiv  Detail & Related papers  (2020-06-11T09:58:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.