Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling
From MaRDI portal
Publication:6097872
autoencoderGalerkin projectionnonlinear proper orthogonal decompositionphysics guided machine learningreduced order modelingvariational multiscale method
Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Inference from stochastic processes and prediction (62M20) Neural nets and related approaches to inference from stochastic processes (62M45) Finite difference methods for initial value and initial-boundary value problems involving PDEs (65M06) Learning and adaptive systems in artificial intelligence (68T05) Dynamical systems approach to turbulence (76F20) Variational methods applied to problems in fluid mechanics (76M30)
Abstract: We propose a new physics guided machine learning (PGML) paradigm that leverages the variational multiscale (VMS) framework and available data to dramatically increase the accuracy of reduced order models (ROMs) at a modest computational cost. The hierarchical structure of the ROM basis and the VMS framework enable a natural separation of the resolved and unresolved ROM spatial scales. Modern PGML algorithms are used to construct novel models for the interaction among the resolved and unresolved ROM scales. Specifically, the new framework builds ROM operators that are closest to the true interaction terms in the VMS framework. Finally, machine learning is used to reduce the projection error and further increase the ROM accuracy. Our numerical experiments for a two-dimensional vorticity transport problem show that the novel PGML-VMS-ROM paradigm maintains the low computational cost of current ROMs, while significantly increasing the ROM accuracy.
Cites work
- \textit{A priori} estimation of memory effects in reduced-order models of nonlinear systems using the Mori-Zwanzig formalism
- A hierarchy of low-dimensional models for the transient and post-transient cylinder wake
- A long short-term memory embedding for hybrid uplifted reduced order models
- A model reduction approach for the variational estimation of vascular compliance by solving an inverse fluid-structure interaction problem
- A POD-Galerkin reduced order model for a LES filtering approach
- A reduced-order method for simulation and control of fluid flows
- A stabilized proper orthogonal decomposition reduced-order model for large scale quasigeostrophic ocean circulation
- Blending modified Gaussian closure and non-Gaussian reduced subspace methods for turbulent dynamical systems
- Breaking the Kolmogorov Barrier with Nonlinear Model Reduction
- Comparative numerical analysis using reduced-order modeling strategies for nonlinear large-scale systems
- Data-driven discovery of closure models
- Data-Driven Filtered Reduced Order Modeling of Fluid Flows
- Data-driven POD-Galerkin reduced order model for turbulent flows
- Data-driven variational multiscale reduced order models
- Efficient estimation of cardiac conductivities via POD-DEIM model order reduction
- Finite element methods for incompressible flow problems
- Galerkin v. least-squares Petrov-Galerkin projection in nonlinear model reduction
- Goal-oriented, model-constrained optimization for reduction of large-scale systems
- scientific article; zbMATH DE number 1849148 (Why is no real title available?)
- Interpolation among reduced-order matrices to obtain parameterized models for design, optimization and probabilistic analysis
- Large eddy simulation and the variational multiscale method
- Large eddy simulation of turbulent channel flows by the variational multiscale method
- Machine-learning error models for approximate solutions to parameterized systems of nonlinear equations
- Minimal subspace rotation on the Stiefel manifold for stabilization and enhancement of projection-based reduced order models for the compressible Navier-Stokes equations
- Model order reduction for PDE constrained optimization
- Model Reduction for Flow Analysis and Control
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- New POD error expressions, error bounds, and asymptotic results for reduced order models of parabolic PDEs
- Nonequilibrium statistical mechanics
- Nonlinear closure modeling in reduced order models for turbulent flows: a dynamical system approach
- On the stability and extension of reduced-order Galerkin models in incompressible flows. A numerical study of vortex shedding
- Optimal prediction and the Mori–Zwanzig representation of irreversible processes
- Optimal prediction with memory
- POD-Galerkin approximations in PDE-constrained optimization
- Progressive construction of a parametric reduced-order model for PDE-constrained optimization
- Projection-based model reduction: formulations for physics-based machine learning
- Proper orthogonal decomposition closure models for fluid flows: Burgers equation
- Proper orthogonal decomposition closure models for turbulent flows: a numerical comparison
- Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori-Zwanzig formalism
- Reduced-order adaptive controllers for fluid flows using POD
- Reduced-order modelling for flow control. Papers based on the presentations at the course, Udine, Italy, September 2008
- Renormalized Mori–Zwanzig-reduced models for systems without scale separation
- Stability properties of POD-Galerkin approximations for the compressible Navier-Stokes equations
- Stochastic Tools in Mathematics and Science
- Survey of multifidelity methods in uncertainty propagation, inference, and optimization
- The need for a pressure-term representation in empirical Galerkin models of incompressible shear flows
- The ROMES method for statistical modeling of reduced-order-model error
- The variational multiscale method -- a paradigm for computational mechanics
- Time-series machine-learning error models for approximate solutions to parameterized dynamical systems
- Transport, Collective Motion, and Brownian Motion
- Turbulence and the dynamics of coherent structures. I. Coherent structures
- Turbulence, coherent structures, dynamical systems and symmetry.
- Variational multiscale proper orthogonal decomposition: convection-dominated convection-diffusion-reaction equations
- Variational multiscale proper orthogonal decomposition: Navier-Stokes equations
- Verifiability of the data-driven variational multiscale reduced order model
Cited in
(5)- Machine learning augmented reduced-order models for FFR-prediction
- Reduced basis modelling of turbulence with well-developed inertial range
- Symbolic regression of data-driven reduced order model closures for under-resolved, convection-dominated flows
- Residual-based data-driven variational multiscale reduced order models for parameter-dependent problems
- Scientific machine learning for closure models in multiscale problems: a review
This page was built for publication: Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6097872)
