Non-linear manifold reduced-order models with convolutional autoencoders and reduced over-collocation method

DOI10.1007/s10915-023-02128-2arXiv2203.00360OpenAlexW4320728490MaRDI QIDQ6158995

Unnamed Author, Gianluigi Rozza, Giovanni Stabile

Publication date: 20 June 2023

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.00360

zbMATH Keywords

computational fluid dynamicsmanifold learningdata-driven methodsnon-linear model order reduction

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Algorithms for approximation of functions (65D15) Numerical solution of discretized equations for initial value and initial-boundary value problems involving PDEs (65M22)

Related Items

Canonical and noncanonical Hamiltonian operator inference, A new method to interpolate POD reduced bases–Application to the parametric model order reduction of a gas bearings supported rotor, A continuous convolutional trainable filter for modelling unstructured data, Branched latent neural maps, A graph convolutional autoencoder approach to model order reduction for parametrized PDEs, Model order reduction for parameterized electromagnetic problems using matrix decomposition and deep neural networks

Cites Work

• Unnamed Item
• Unnamed Item
• The GNAT method for nonlinear model reduction: effective implementation and application to computational fluid dynamics and turbulent flows
• Iterative methods for model reduction by domain decomposition
• Nonlinear Kolmogorov widths
• Reduced-order modeling of a two-dimensional flow with moving shocks.
• An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
• Optimal nonlinear approximation
• Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics
• POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
• An EIM-degradation free reduced basis method via over collocation and residual hyper reduction-based error estimation
• A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
• The neural network shifted-proper orthogonal decomposition: a machine learning approach for non-linear reduction of hyperbolic equations
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Decay of the Kolmogorov \(N\)-width for wave problems
• Reduced-order model for the BGK equation based on POD and optimal transport
• A nonlinear manifold-based reduced order model for multiscale analysis of heterogeneous hyperelastic materials
• Kolmogorov widths under holomorphic mappings
• Generalized Reduced Basis Methods and n-Width Estimates for the Approximation of the Solution Manifold of Parametric PDEs
• Efficient non-linear model reduction via a least-squares Petrov-Galerkin projection and compressive tensor approximations
• Kolmogorov and Linear Widths of Balls in Sobolev Spaces on Compact Manifolds
• Certified Reduced Basis Methods for Parametrized Partial Differential Equations
• Nonlinear Model Reduction via Discrete Empirical Interpolation
• Model Reduction and Approximation
• Space--Time Least-Squares Petrov--Galerkin Projection for Nonlinear Model Reduction
• A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations
• Interpolation-based reduced-order modelling for steady transonic flows via manifold learning
• SNS: A Solution-Based Nonlinear Subspace Method for Time-Dependent Model Order Reduction
• A Stochastic Collocation Method for Elliptic Partial Differential Equations with Random Input Data
• Solution of the implicitly discretised reacting flow equations by operator-splitting