Uncertainty quantification and stability of neural operators for prediction of three-dimensional turbulence

Abstract

Turbulence poses challenges for numerical simulation due to its chaotic, multiscale nature and high computational cost. Traditional turbulence modeling often struggles with accuracy and long-term stability. Recent scientific machine learning (SciML) models, such as Fourier Neural Operators (FNO), show promise in solving PDEs, but are typically limited to one-step-ahead predictions and often fail over long time horizons, especially in 3D turbulence. This study proposes a framework to assess the reliability of neural operator models in turbulent flows. Using three-dimensional forced homogeneous isotropic turbulence (HIT) as a benchmark, we evaluate models in terms of uncertainty quantification (UQ), error propagation, and sensitivity to initial perturbations. Statistical tools such as error distribution analysis and autocorrelation functions (ACF) are used to assess predictive robustness and temporal coherence. Our proposed model, the factorized-implicit FNO (F-IFNO), improves long-term stability and accuracy by incorporating implicit factorization into the prediction process. It outperforms conventional LES and other FNO-based models in balancing accuracy, stability, and efficiency. The results highlight the importance of prediction constraints, time interval selection, and UQ in developing robust neural operator frameworks for turbulent systems.

References in corpus (15)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods
• NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• Enhancing Computational Fluid Dynamics with Machine Learning
• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
• Long-term predictions of turbulence by implicit U-Net enhanced Fourier neural operator
• Nonlocal Kernel Network (NKN): a Stable and Resolution-Independent Deep Neural Network
• A fast multi-fidelity method with uncertainty quantification for complex data correlations: Application to vortex-induced vibrations of marine risers
• Informative and non-informative decomposition of turbulent flow fields
• A physics-inspired alternative to spatial filtering for large-eddy simulations of turbulent flows
• L-HYDRA: Multi-Head Physics-Informed Neural Networks
• On the locality of local neural operator in learning fluid dynamics