AMS-Net: Adaptive Multiscale Sparse Neural Network with Interpretable Basis Expansion for Multiphase Flow Problems
DOI10.1137/21M1405289zbMath1493.65234arXiv2207.11735MaRDI QIDQ5099843
Yating Wang, Wing Tat Leung, Guang Lin
Publication date: 26 August 2022
Published in: Multiscale Modeling & Simulation (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2207.11735
model reductionadaptive methodsparse learningdeep neural networkinterpretable machine learningmultiscale flow dynamics
Artificial neural networks and deep learning (68T07) 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) Mathematical modeling or simulation for problems pertaining to fluid mechanics (76-10)
Cites Work
- Generalized multiscale finite element methods (GMsFEM)
- Multiscale empirical interpolation for solving nonlinear PDEs
- Multiscale finite element methods for high-contrast problems using local spectral basis functions
- An adaptive GMsFEM for high-contrast flow problems
- Variational training of neural network approximations of solution maps for physical models
- The heterogeneous multiscale methods
- A multiscale reduced-basis method for parametrized elliptic partial differential equations with multiple scales
- The heterogeneous multiscale finite element method for elliptic homogenization problems in perforated domains
- The variational multiscale method -- a paradigm for computational mechanics
- Inferring solutions of differential equations using noisy multi-fidelity data
- Global-local nonlinear model reduction for flows in heterogeneous porous media
- Non-local multi-continua upscaling for flows in heterogeneous fractured media
- Model reduction and neural networks for parametric PDEs
- Bayesian sparse learning with preconditioned stochastic gradient MCMC and its applications
- Deep global model reduction learning in porous media flow simulation
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- Reduced-order deep learning for flow dynamics. The interplay between deep learning and model reduction
- A composite neural network that learns from multi-fidelity data: application to function approximation and inverse PDE problems
- Simulator-free solution of high-dimensional stochastic elliptic partial differential equations using deep neural networks
- Deep multiscale model learning
- Model's sparse representation based on reduced mixed GMsFE basis methods
- Multiscale finite element methods for nonlinear problems and their applications
- A prioriconvergence of the Greedy algorithm for the parametrized reduced basis method
- Mixed Multiscale Finite Element Methods Using Limited Global Information
- Certified Reduced Basis Methods for Parametrized Saddle Point Problems
- A Data-Driven Approach for Multiscale Elliptic PDEs with Random Coefficients Based on Intrinsic Dimension Reduction
- A Multiscale Neural Network Based on Hierarchical Matrices
- Mixed Generalized Multiscale Finite Element Methods and Applications
- Adaptive Mixed GMsFEM for Flows in Heterogeneous Media
- A Multiscale Mortar Mixed Finite Element Method
This page was built for publication: AMS-Net: Adaptive Multiscale Sparse Neural Network with Interpretable Basis Expansion for Multiphase Flow Problems
