Ensemble Kalman method for learning turbulence models from indirect observation data

Abstract

In this work, we propose using an ensemble Kalman method to learn a nonlinear eddy viscosity model, represented as a tensor basis neural network, from velocity data. Data-driven turbulence models have emerged as a promising alternative to traditional models for providing closure mapping from the mean velocities to Reynolds stresses. Most data-driven models in this category need full-field Reynolds stress data for training, which not only places stringent demand on the data generation but also makes the trained model ill-conditioned and lacks robustness. This difficulty can be alleviated by incorporating the Reynolds-averaged Navier-Stokes (RANS) solver in the training process. However, this would necessitate developing adjoint solvers of the RANS model, which requires extra effort in code development and maintenance. Given this difficulty, we present an ensemble Kalman method with an adaptive step size to train a neural network-based turbulence model by using indirect observation data. To our knowledge, this is the first such attempt in turbulence modelling. The ensemble method is first verified on the flow in a square duct, where it correctly learns the underlying turbulence models from velocity data. Then, the generalizability of the learned model is evaluated on a family of separated flows over periodic hills. It is demonstrated that the turbulence model learned in one flow can predict flows in similar configurations with varying slopes.

References in corpus (20)

• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• RANS Turbulence Model Development using CFD-Driven Machine Learning
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression
• Grid-point and time-step requirements for direct numerical simulation and large-eddy simulation
• RANS Equations with Explicit Data-Driven Reynolds Stress Closure Can Be Ill-Conditioned
• Scientific multi-agent reinforcement learning for wall-models of turbulent flows
• Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks
• Iterative ensemble smoother as an approximate solution to a regularized minimum-average-cost problem: theory and applications
• Regularized Ensemble Kalman Methods for Inverse Problems
• Efficient big data assimilation through sparse representation: A 3D benchmark case study in seismic history matching
• Embedded training of neural-network sub-grid-scale turbulence models
• Multi-Objective CFD-Driven Development of Coupled Turbulence Closure Models
• Ensemble Neural Networks (ENN): A gradient-free stochastic method
• Learning nonlocal constitutive models with neural networks
• CFD-driven Symbolic Identification of Algebraic Reynolds-Stress Models
• Evaluation of ensemble methods for quantifying uncertainties in steady-state CFD applications with small ensemble sizes
• Ensemble Kalman Inversion for Sparse Learning of Dynamical Systems from Time-Averaged Data

Cited by in corpus (14)

• Development of a Generalizable Data-driven Turbulence Model: Conditioned Field Inversion and Symbolic Regression
• Combining direct and indirect sparse data for learning generalizable turbulence models
• A wall model for separated flows: embedded learning to improve a posteriori performance
• Ensemble data assimilation-based mixed subgrid-scale model for large-eddy simulations
• CEBoosting: Online Sparse Identification of Dynamical Systems with Regime Switching by Causation Entropy Boosting
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• Data-driven approach for modeling Reynolds stress tensor with invariance preservation
• Adjoint-based variational optimal mixed models for large-eddy simulation of turbulence
• Real-time forecasting of chaotic dynamics from sparse data and autoencoders
• Turbulence Closure in RANS and Flow Inference around a Cylinder using PINNs and Sparse Experimental Data
• Progressive Mixture-of-Experts with autoencoder routing for continual RANS turbulence modelling
• Sparse data assimilation for under-resolved large-eddy simulations
• Data-driven detached-eddy simulations based on explicit algebraic stress expressions for turbulent flows
• New Metric Formulas that Include Measurement Errors in Machine Learning for Natural Sciences