A comparison of neural network architectures for data-driven reduced-order modeling
From MaRDI portal
Publication:2138791
DOI10.1016/j.cma.2022.114764OpenAlexW3204011834MaRDI QIDQ2138791
Lili Ju, Max D. Gunzburger, Zhu Wang, Anthony Gruber
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/2110.03442
parametric PDEsreduced-order modelingnonlinear dimensionality reductiongraph convolutionconvolutional autoencoder
Finite element, Rayleigh-Ritz and Galerkin methods for initial value and initial-boundary value problems involving PDEs (65M60) Numerical solution of discretized equations for initial value and initial-boundary value problems involving PDEs (65M22)
Related Items
Neural-network-augmented projection-based model order reduction for mitigating the Kolmogorov barrier to reducibility, Mesh-informed neural networks for operator learning in finite element spaces, Multiscale graph neural network autoencoders for interpretable scientific machine learning, A multifidelity Monte Carlo method for realistic computational budgets, A graph convolutional autoencoder approach to model order reduction for parametrized PDEs, Structure-preserving recurrent neural networks for a class of Birkhoffian systems, AI‐enhanced iterative solvers for accelerating the solution of large‐scale parametrized systems, Emulation of cardiac mechanics using graph neural networks
Uses Software
Cites Work
- Unnamed Item
- Wavelets on graphs via spectral graph theory
- A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
- POD/DEIM reduced-order modeling of time-fractional partial differential equations with applications in parameter identification
- Neural network modeling for near wall turbulent flow.
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Algorithm 866
