The neural network shifted-proper orthogonal decomposition: a machine learning approach for non-linear reduction of hyperbolic equations

DOI10.1016/j.cma.2022.114687OpenAlexW3194202055WikidataQ114952522 ScholiaQ114952522MaRDI QIDQ2138717

Gianluigi Rozza, Michele Girfoglio, Nicola Demo, Davide Papapicco, Giovanni Stabile

Publication date: 12 May 2022

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

Full work available at URL: https://arxiv.org/abs/2108.06558

zbMATH Keywords

nonlinear hyperbolic equationsmultiphase simulationdeep neural networks (DNNs)reduced order modelling (ROM)shifted-POD (sPOD)

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65M99) Finite volume methods for initial value and initial-boundary value problems involving PDEs (65M08)

Related Items

Embedded domain reduced basis models for the shallow water hyperbolic equations with the shifted boundary method ⋮ Neural-network-augmented projection-based model order reduction for mitigating the Kolmogorov barrier to reducibility ⋮ Physics-data combined machine learning for parametric reduced-order modelling of nonlinear dynamical systems in small-data regimes ⋮ SVD perspectives for augmenting DeepONet flexibility and interpretability ⋮ POD-based reduced order methods for optimal control problems governed by parametric partial differential equation with varying boundary control ⋮ Data-driven reduced order modelling for patient-specific hemodynamics of coronary artery bypass grafts with physical and geometrical parameters ⋮ A continuous convolutional trainable filter for modelling unstructured data ⋮ Front transport reduction for complex moving fronts ⋮ Forward sensitivity analysis and mode dependent control for closure modeling of Galerkin systems ⋮ Non-linear manifold reduced-order models with convolutional autoencoders and reduced over-collocation method ⋮ Towards a machine learning pipeline in reduced order modelling for inverse problems: neural networks for boundary parametrization, dimensionality reduction and solution manifold approximation ⋮ Symplectic model reduction of Hamiltonian systems using data-driven quadratic manifolds ⋮ Predicting solar wind streams from the inner-heliosphere to Earth via shifted operator inference

Uses Software

• redbKIT

Cites Work

• Reduced order methods for modeling and computational reduction
• Data-driven POD-Galerkin reduced order model for turbulent flows
• Numerical models for differential problems. Translated by Silvia Quarteroni.
• A stable and accurate convective modelling procedure based on quadratic upstream interpolation
• POD-Galerkin reduced order methods for CFD using finite volume discretisation: vortex shedding around a circular cylinder
• Model order reduction for parametrized nonlinear hyperbolic problems as an application to uncertainty quantification
• Neural networks based subgrid scale modeling in large eddy simulations
• A POD-Galerkin reduced order model for a LES filtering approach
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• The finite volume method in computational fluid dynamics. An advanced introduction with OpenFOAM and Matlab
• Kolmogorov widths under holomorphic mappings
• Certified Reduced Basis Methods for Parametrized Partial Differential Equations
• Supremizer stabilization of POD-Galerkin approximation of parametrized steady incompressible Navier-Stokes equations
• Theoretical Numerical Analysis
• On the Early History of the Singular Value Decomposition
• Stabilized Weighted Reduced Basis Methods for Parametrized Advection Dominated Problems with Random Inputs
• Transport Reversal for Model Reduction of Hyperbolic Partial Differential Equations
• The Shifted Proper Orthogonal Decomposition: A Mode Decomposition for Multiple Transport Phenomena
• A Registration Method for Model Order Reduction: Data Compression and Geometry Reduction
• Model Reduction for Transport-Dominated Problems via Online Adaptive Bases and Adaptive Sampling
• Model Order Reduction for Problems with Large Convection Effects
• Reduced Basis Approximation of Parametrized Advection-Diffusion PDEs with High Péclet Number
• Deep learning in fluid dynamics
• Reduced Basis Methods for Partial Differential Equations
• Numerical simulation of moving contact line problems using a volume-of-fluid method

This page was built for publication: The neural network shifted-proper orthogonal decomposition: a machine learning approach for non-linear reduction of hyperbolic equations