The ROMES method for statistical modeling of reduced-order-model error
From MaRDI portal
Publication:2945141
Abstract: This work presents a technique for statistically modeling errors introduced by reduced-order models. The method employs Gaussian-process regression to construct a mapping from a small number of computationally inexpensive `error indicators' to a distribution over the true error. The variance of this distribution can be interpreted as the (epistemic) uncertainty introduced by the reduced-order model. To model normed errors, the method employs existing rigorous error bounds and residual norms as indicators; numerical experiments show that the method leads to a near-optimal expected effectivity in contrast to typical error bounds. To model errors in general outputs, the method uses dual-weighted residuals---which are amenable to uncertainty control---as indicators. Experiments illustrate that correcting the reduced-order-model output with this surrogate can improve prediction accuracy by an order of magnitude; this contrasts with existing `multifidelity correction' approaches, which often fail for reduced-order models and suffer from the curse of dimensionality. The proposed error surrogates also lead to a notion of `probabilistic rigor', i.e., the surrogate bounds the error with specified probability.
Recommendations
- Error Estimation for Reduced‐Order Models of Dynamical Systems
- Error Estimation for Reduced-Order Models of Dynamical Systems
- Probabilistic error estimation for non-intrusive reduced models learned from data of systems governed by linear parabolic partial differential equations
- Bayesian identification of a projection-based reduced order model for computational fluid dynamics
- Reduced modeling of unknown trajectories
Cites work
- scientific article; zbMATH DE number 3863589 (Why is no real title available?)
- scientific article; zbMATH DE number 1522825 (Why is no real title available?)
- 10.1162/15324430152748236
- A posteriorierror bounds for reduced-basis approximations of parametrized parabolic partial differential equations
- A Posteriori Error Bounds and Global Error Control for Approximation of Ordinary Differential Equations
- A posteriori error analysis of the reduced basis method for nonaffine parametrized nonlinear PDEs
- A posteriori error estimation for DEIM reduced nonlinear dynamical systems
- A priori hyperreduction method: an adaptive approach
- A space–time variational approach to hydrodynamic stability theory
- A successive constraint linear optimization method for lower bounds of parametric coercivity and inf-sup stability constants
- Adaptive \(h\)-refinement for reduced-order models
- Adjoint error estimation and grid adaptation for functional outputs: Application to quasi-one-dimensional flow
- An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
- An improved error bound for reduced basis approximation of linear parabolic problems
- Efficient model reduction in nonlinear dynamics using the Karhunen-Loève expansion and dual-weighted-residual methods
- Efficient non linear model reduction via a least-squares Petrov-Galerkin projection and compressive tensor approximations
- Efficient reduced-basis treatment of nonaffine and nonlinear partial differential equations
- Gaussian processes for machine learning.
- Missing Point Estimation in Models Described by Proper Orthogonal Decomposition
- Nonlinear model reduction for uncertainty quantification in large-scale inverse problems
- Nonlinear model reduction via discrete empirical interpolation
- Reduced basis approximation and a posteriori error estimation for affinely parametrized elliptic coercive partial differential equations. Application to transport and continuum mechanics.
- Reduced basis approximation and a posteriori error estimation for the time-dependent viscous Burgers' equation
- Reduced basis approximation for nonlinear parametrized evolution equations based on empirical operator interpolation
- The GNAT method for nonlinear model reduction: effective implementation and application to computational fluid dynamics and turbulent flows
- The post-processing approach in the finite element method—part 1: Calculation of displacements, stresses and other higher derivatives of the displacements
- Weighted a posteriori error control in FE methods
- \textit{A priori} convergence of the greedy algorithm for the parametrized reduced basis method
Cited in
(38)- Error modeling for surrogates of dynamical systems using machine learning
- Certified reduced basis VMS-Smagorinsky model for natural convection flow in a cavity with variable height
- Efficient state/parameter estimation in nonlinear unsteady PDEs by a reduced basis ensemble Kalman filter
- An adaptive local reduced basis method for solving PDEs with uncertain inputs and evaluating risk
- Model order reduction for large-scale structures with local nonlinearities
- Data-driven model order reduction for problems with parameter-dependent jump-discontinuities
- Adaptive reduced order modeling for nonlinear dynamical systems through a new a posteriori error estimator: application to uncertainty quantification
- Fast sampling of parameterised Gaussian random fields
- Limited-memory adaptive snapshot selection for proper orthogonal decomposition
- Reduced order modeling of random linear dynamical systems based on a new a posteriori error bound
- An adaptive and efficient greedy procedure for the optimal training of parametric reduced-order models
- Certification of projection-based reduced order modelling in computational homogenisation by the constitutive relation error
- An adaptive SVD-Krylov reduced order model for surrogate based structural shape optimization through isogeometric boundary element method
- A transport-based multifidelity preconditioner for Markov chain Monte Carlo
- Multivariate predictions of local reduced-order-model errors and dimensions
- Adaptive \(h\)-refinement for reduced-order models
- Accurate solution of Bayesian inverse uncertainty quantification problems combining reduced basis methods and reduction error models
- Machine-learning error models for approximate solutions to parameterized systems of nonlinear equations
- Correction of model reduction errors in simulations
- Parametric domain decomposition for accurate reduced order models: applications of MP-LROM methodology
- Output-based adaptive aerodynamic simulations using convolutional neural networks
- A discretize-then-map approach for the treatment of parameterized geometries in model order reduction
- A hierarchical a posteriori error estimator for the reduced basis method
- Time-series machine-learning error models for approximate solutions to parameterized dynamical systems
- Goal-oriented error estimation for parameter-dependent nonlinear problems
- Automatised selection of load paths to construct reduced-order models in computational damage micromechanics: from dissipation-driven random selection to Bayesian optimization
- 9 Kernel methods for surrogate modeling
- Randomized Residual-Based Error Estimators for Parametrized Equations
- A New Certified Hierarchical and Adaptive RB-ML-ROM Surrogate Model for Parametrized PDEs
- Machine-learning-based modeling of coarse-scale error, with application to uncertainty quantification
- Data-driven reduced order modeling for time-dependent problems
- Error estimation of the parametric non-intrusive reduced order model using machine learning
- Evaluation of dual-weighted residual and machine learning error estimation for projection-based reduced-order models of steady partial differential equations
- DynAMO: multi-agent reinforcement learning for dynamic anticipatory mesh optimization with applications to hyperbolic conservation laws
- A reduced basis Kalman filter for parametrized partial differential equations
- Multifidelity Monte Carlo Estimation with Adaptive Low-Fidelity Models
- Adaptive interpolatory MOR by learning the error estimator in the parameter domain
- Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling
This page was built for publication: The ROMES method for statistical modeling of reduced-order-model error
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2945141)
