Quasi-optimal \textit{hp}-finite element refinements towards singularities via deep neural network prediction

DOI10.1016/j.camwa.2023.04.023arXiv2209.05844OpenAlexW4367309267MaRDI QIDQ6103655

Sergio Rojas, Witold Dzwinel, Rafał Grzeszczuk, Maciej Paszynski, Tomasz Służalec

Publication date: 5 June 2023

Published in: Computers \& Mathematics with Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2209.05844

zbMATH Keywords

direct solversdeep neural networks\textit{hp}-adaptive finite element

Mathematics Subject Classification ID

Computational methods for sparse matrices (65F50) Finite element methods applied to problems in solid mechanics (74S05) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Mesh generation, refinement, and adaptive methods for boundary value problems involving PDEs (65N50) Direct numerical methods for linear systems and matrix inversion (65F05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Fully Asynchronous Multifrontal Solver Using Distributed Dynamic Scheduling
• Adaptive remeshing and \(h-p\) domain decomposition
• Toward a universal h-p adaptive finite element strategy. III: Design of h-p meshes
• A collection of 2D elliptic problems for testing adaptive grid refinement algorithms
• The h-p version of the finite element method. I. The basic approximation results
• The h-p version of the finite element method. II. General results and applications
• Multifrontal parallel distributed symmetric and unsymmetric solvers
• \(H^1\), \(H\)(curl) and \(H\)(div)-conforming projection-based interpolation in three dimensions: Quasi-optimal \(p\)-interpolation estimates
• Direct solvers performance on \(h\)-adapted grids
• Impact of element-level static condensation on iterative solver performance
• Recurrent neural networks as optimal mesh refinement strategies
• Refinement of polygonal grids using convolutional neural networks with applications to polygonal discontinuous Galerkin and virtual element methods
• Output-based adaptive aerodynamic simulations using convolutional neural networks
• The multi-level \(hp\)-method for three-dimensional problems: dynamically changing high-order mesh refinement with arbitrary hanging nodes
• Fully automatic \(hp\)-adaptivity in three dimensions
• Integration of \(hp\)-adaptivity and a two-grid solver for elliptic problems
• Machine learning based refinement strategies for polyhedral grids with applications to virtual element and polyhedral discontinuous Galerkin methods
• The Multifrontal Solution of Unsymmetric Sets of Linear Equations
• The Multifrontal Solution of Indefinite Sparse Symmetric Linear
• Mesh Refinement Processes Based on the Generalized Bisection of Simplices
• A multiscale finite-element method
• Graph Clustering and Minimum Cut Trees
• An Approximate Minimum Degree Ordering Algorithm
• A Comparison of hp -Adaptive Strategies for Elliptic Partial Differential Equations
• Computing with hp-ADAPTIVE FINITE ELEMENTS
• Towards a tighter coupling of bottom-up and top-down sparse matrix ordering methods

This page was built for publication: Quasi-optimal \textit{hp}-finite element refinements towards singularities via deep neural network prediction