Machine-learning error models for approximate solutions to parameterized systems of nonlinear equations

DOI10.1016/j.cma.2019.01.024zbMath1440.65058arXiv1808.02097OpenAlexW2885611161WikidataQ115734528 ScholiaQ115734528MaRDI QIDQ1987897

Brian A. Freno, Kevin T. Carlberg

Publication date: 16 April 2020

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.02097

zbMATH Keywords

model reductionhigh-dimensional regressionsupervised machine learningerror modelingparameterized nonlinear equationsROMES method

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Numerical computation of solutions to systems of equations (65H10)

Related Items

Data-driven model reduction, Wiener projections, and the Koopman-Mori-Zwanzig formalism ⋮ A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs ⋮ A non-intrusive multifidelity method for the reduced order modeling of nonlinear problems ⋮ Time-series machine-learning error models for approximate solutions to parameterized dynamical systems ⋮ A framework for machine learning of model error in dynamical systems ⋮ Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling ⋮ Evaluation of dual-weighted residual and machine learning error estimation for projection-based reduced-order models of steady partial differential equations ⋮ Deep learning-based schemes for singularly perturbed convection-diffusion problems ⋮ Model reduction for the material point method via an implicit neural representation of the deformation map ⋮ Active-learning-driven surrogate modeling for efficient simulation of parametric nonlinear systems ⋮ Machine learning for fast and reliable solution of time-dependent differential equations ⋮ Output-based adaptive aerodynamic simulations using convolutional neural networks

Uses Software

• LIBSVM
• Scikit
• Albany

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The GNAT method for nonlinear model reduction: effective implementation and application to computational fluid dynamics and turbulent flows
• A natural-norm successive constraint method for inf-sup lower bounds
• High-order compact exponential finite difference methods for convection-diffusion type problems
• Reduced basis approximation and a posteriori error estimation for affinely parametrized elliptic coercive partial differential equations. Application to transport and continuum mechanics.
• A reduced-order method for simulation and control of fluid flows
• Jacobian-free Newton-Krylov methods: a survey of approaches and applications.
• Efficient model reduction in nonlinear dynamics using the Karhunen-Loève expansion and dual-weighted-residual methods
• Adjoint error estimation and grid adaptation for functional outputs: Application to quasi-one-dimensional flow
• Grid adaptation for functional outputs: application to two-dimensional inviscid flows
• Parametric domain decomposition for accurate reduced order models: applications of MP-LROM methodology
• Galerkin v. least-squares Petrov-Galerkin projection in nonlinear model reduction
• Decreasing the temporal complexity for nonlinear, implicit reduced-order models by forecasting
• An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
• A triangular cut-cell adaptive method for high-order discretizations of the compressible Navier-Stokes equations
• Unsteady flow sensing and estimation via the gappy proper orthogonal decomposition
• Bayesian Calibration of Computer Models
• Analysis of Inexact Trust-Region SQP Algorithms
• A New Selection Operator for the Discrete Empirical Interpolation Method---Improved A Priori Error Bound and Extensions
• A Posteriori Error Estimation for DEIM Reduced Nonlinear Dynamical Systems
• Efficient non-linear model reduction via a least-squares Petrov-Galerkin projection and compressive tensor approximations
• A low-cost, goal-oriented ‘compact proper orthogonal decomposition’ basis for model reduction of static systems
• The ROMES Method for Statistical Modeling of Reduced-Order-Model Error
• Progressive construction of a parametric reduced‐order model for PDE‐constrained optimization
• Adaptiveh-refinement for reduced-order models
• Adaptive training of local reduced bases for unsteady incompressible Navier-Stokes flows
• Nonlinear Model Reduction via Discrete Empirical Interpolation
• Residual based sampling in POD model order reduction of drift-diffusion equations in parametrized electrical networks
• The post-processing approach in the finite element method—part 1: Calculation of displacements, stresses and other higher derivatives of the displacements
• Model Reduction for Large-Scale Systems with High-Dimensional Parametric Input Space
• Turbulence and the dynamics of coherent structures. I. Coherent structures
• Turbulence, Coherent Structures, Dynamical Systems and Symmetry
• Randomized Residual-Based Error Estimators for Parametrized Equations
• Efficient State/Parameter Estimation in Nonlinear Unsteady PDEs by a Reduced Basis Ensemble Kalman Filter
• Space--Time Least-Squares Petrov--Galerkin Projection for Nonlinear Model Reduction
• Combining Field Data and Computer Simulations for Calibration and Prediction
• Gappy data and reconstruction procedures for flow past a cylinder
• Missing Point Estimation in Models Described by Proper Orthogonal Decomposition
• Data-Driven Time Parallelism via Forecasting
• A posteriorierror bounds for reduced-basis approximations of parametrized parabolic partial differential equations
• Accurate Solution of Bayesian Inverse Uncertainty Quantification Problems Combining Reduced Basis Methods and Reduction Error Models
• Random forests

This page was built for publication: Machine-learning error models for approximate solutions to parameterized systems of nonlinear equations