Ensemble Kalman method for learning turbulence models from indirect observation data
From MaRDI portal
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.
Recommendations
- Ensemble Gradient for Learning Turbulence Models from Indirect Observations
- Ensemble Kalman filters for dynamical systems with unresolved turbulence
- Ensemble averaging in turbulence modelling
- Combining direct and indirect sparse data for learning generalizable turbulence models
- Ensemble Kalman filter
- Forecasting turbulent modes with nonparametric diffusion models: learning from noisy data
- A Multiscale Data Assimilation with the Ensemble Kalman Filter
- A multigrid/ensemble Kalman filter strategy for assimilation of unsteady flows
- Learning nonlinear turbulent dynamics from partial observations via analytically solvable conditional statistics
- A reduced order model based on Kalman filtering for sequential data assimilation of turbulent flows
Cites work
- A continuous adjoint formulation for the computation of topological and surface sensitivities of ducted flows
- A more general effective-viscosity hypothesis
- A novel evolutionary algorithm applied to algebraic modifications of the RANS stress-strain relationship
- An explicit algebraic Reynolds stress model for incompressible and compressible turbulent flows
- Analysis of iterative ensemble smoothers for solving inverse problems
- CFD-driven symbolic identification of algebraic Reynolds-stress models
- Closure Strategies for Turbulent and Transitional Flows
- Conditioning and accurate solutions of Reynolds average Navier–Stokes equations with data-driven turbulence closures
- DAFI: An Open-Source Framework for Ensemble-Based Data Assimilation and Field Inversion
- Ensemble Gradient for Learning Turbulence Models from Indirect Observations
- Ensemble Kalman inversion for sparse learning of dynamical systems from time-averaged data
- Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
- Evaluation of ensemble methods for quantifying uncertainties in steady-state CFD applications with small ensemble sizes
- Flows over periodic hills of parameterized geometries: a dataset for data-driven turbulence modeling from direct simulations
- Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Learning nonlocal constitutive models with neural networks
- Levenberg-Marquardt forms of the iterative ensemble smoother for efficient history matching and uncertainty quantification
- Modelling the pressure–strain correlation of turbulence: an invariant dynamical systems approach
- Multi-objective CFD-driven development of coupled turbulence closure models
- Novel iterative ensemble smoothers derived from a class of generalized cost functions
- Online adjoint methods for optimization of PDEs
- Physics-informed covariance kernel for model-form uncertainty quantification with application to turbulent flows
- Progress in the development of a Reynolds-stress turbulence closure
- RANS turbulence model development using CFD-driven machine learning
- Regularized ensemble Kalman methods for inverse problems
- Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- Reynolds-averaged Navier–Stokes equations with explicit data-driven Reynolds stress closure can be ill-conditioned
- The ensemble Kalman filter for combined state and parameter estimation
- The use of the Reynolds force vector in a physics informed machine learning approach for predictive turbulence modeling
- Toward neural-network-based large eddy simulation: application to turbulent channel flow
- Turbulence modeling using body force potentials
- Turbulent Flows
Cited in
(23)- Dynamic calibration of differential equations using machine learning, with application to turbulence models
- Ensemble averaging in turbulence modelling
- Ensemble Gradient for Learning Turbulence Models from Indirect Observations
- Combining direct and indirect sparse data for learning generalizable turbulence models
- An equivariant neural operator for developing nonlocal tensorial constitutive models
- A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty
- Efficient Bayesian physics informed neural networks for inverse problems via ensemble Kalman inversion
- Data-driven approach for modeling Reynolds stress tensor with invariance preservation
- Learning about structural errors in models of complex dynamical systems
- Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping
- On the origin of counter-gradient transport in turbulent scalar flux: physics interpretation and adjoint data assimilation
- A data-driven turbulence modeling for the Reynolds stress tensor transport equation
- Large-eddy simulation-based shape optimization for mitigating turbulent wakes of a bluff body using the regularized ensemble Kalman method
- Differentiability in unrolled training of neural physics simulators on transient dynamics
- Neural differentiable modeling with diffusion-based super-resolution for two-dimensional spatiotemporal turbulence
- A wall model for separated flows: embedded learning to improve \textit{a posteriori} performance
- Time integration schemes based on neural networks for solving partial differential equations on coarse grids
- Neural operator-based stochastic forcing for resolvent prediction of space-time turbulence statistics in channel flows
- Enhancement of large-eddy simulations for the prediction of an intake flow rig using sequential data assimilation
- Uncertainty and error quantification for data-driven Reynolds-averaged turbulence modelling with mean-variance estimation networks
- A framework for learning symbolic turbulence models from indirect observation data via neural networks and feature importance analysis
- Parallel ensemble Kalman method with total variation regularization for large-scale field inversion
- Neural ensemble Kalman filter: data assimilation for compressible flows with shocks
This page was built for publication: Ensemble Kalman method for learning turbulence models from indirect observation data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5038553)
