A multi-stage deep learning based algorithm for multiscale model reduction

DOI10.1016/j.cam.2021.113506OpenAlexW3134034089MaRDI QIDQ2029406

Wing Tat Leung, Eric T. Chung, Sai-Mang Pun, Zecheng Zhang

Publication date: 3 June 2021

Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2009.11341

zbMATH Keywords

deep learningmultiscale model reduction

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Finite element methods applied to problems in solid mechanics (74S05) Flows in porous media; filtration; seepage (76S05) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Finite element methods applied to problems in fluid mechanics (76M10)

Related Items (5)

Efficient hybrid explicit-implicit learning for multiscale problems ⋮ Neural Network Approximation of Coarse-Scale Surrogates in Numerical Homogenization ⋮ Hybrid explicit-implicit learning for multiscale problems with time dependent source ⋮ NH-PINN: neural homogenization-based physics-informed neural network for multiscale problems ⋮ B-DeepONet: an enhanced Bayesian deeponet for solving noisy parametric PDEs using accelerated replica exchange SGLD

Uses Software

• Tensor2Tensor
• SegNet
• CycleGAN
• pix2pix
• Inception-v4

Cites Work

• Unnamed Item
• Mixed GMsFEM for second order elliptic problem in perforated domains
• Generalized multiscale finite element methods (GMsFEM)
• Generalized multiscale finite element method. Symmetric interior penalty coupling
• Multiscale empirical interpolation for solving nonlinear PDEs
• Adaptive multiscale model reduction with generalized multiscale finite element methods
• Learning macroscopic parameters in nonlinear multiscale simulations using nonlocal multicontinua upscaling techniques
• Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori-Zwanzig formalism
• Constraint-aware neural networks for Riemann problems
• A multiscale finite element method for elliptic problems in composite materials and porous media
• Constraint energy minimizing generalized multiscale finite element method
• Machine learning of multiscale active force generation models for the efficient simulation of cardiac electromechanics
• Deep global model reduction learning in porous media flow simulation
• Reduced-order deep learning for flow dynamics. The interplay between deep learning and model reduction
• Deep multiscale model learning
• A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning
• Residual-driven online generalized multiscale finite element methods
• Randomized Oversampling for Generalized Multiscale Finite Element Methods
• Generalized multiscale finite element methods for problems in perforated heterogeneous domains
• Reduced-Contrast Approximations for High-Contrast Multiscale Flow Problems
• An Online Generalized Multiscale Discontinuous Galerkin Method (GMsDGM) for Flows in Heterogeneous Media
• Machine Learning in Adaptive Domain Decomposition Methods---Predicting the Geometric Location of Constraints
• Generalized Multiscale Finite Element Methods for Wave Propagation in Heterogeneous Media
• Generalized Multiscale Finite Element Methods. Nonlinear Elliptic Equations

This page was built for publication: A multi-stage deep learning based algorithm for multiscale model reduction