A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations
From MaRDI portal
Publication:5058646
DOI10.1090/MCOM/3781zbMATH Open1504.65255arXiv2103.06183OpenAlexW3135895479MaRDI QIDQ5058646FDOQ5058646
Authors: Andrea Manzoni, Paolo Zunino 
Publication date: 21 December 2022
Published in: Mathematics of Computation (Search for Journal in Brave)
Abstract: Within the framework of parameter dependent PDEs, we develop a constructive approach based on Deep Neural Networks for the efficient approximation of the parameter-to-solution map. The research is motivated by the limitations and drawbacks of state-of-the-art algorithms, such as the Reduced Basis method, when addressing problems that show a slow decay in the Kolmogorov n-width. Our work is based on the use of deep autoencoders, which we employ for encoding and decoding a high fidelity approximation of the solution manifold. To provide guidelines for the design of deep autoencoders, we consider a nonlinear version of the Kolmogorov n-width over which we base the concept of a minimal latent dimension. We show that the latter is intimately related to the topological properties of the solution manifold, and we provide theoretical results with particular emphasis on second order elliptic PDEs, characterizing the minimal dimension and the approximation errors of the proposed approach. The theory presented is further supported by numerical experiments, where we compare the proposed approach with classical POD-Galerkin reduced order models. In particular, we consider parametrized advection-diffusion PDEs, and we test the methodology in the presence of strong transport fields, singular terms and stochastic coefficients.
Full work available at URL: https://arxiv.org/abs/2103.06183
Recommendations
- A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
- Data driven approximation of parametrized PDEs by reduced basis and neural networks
- Solving parametric PDE problems with artificial neural networks
- Nonintrusive Reduced-Order Models for Parametric Partial Differential Equations via Data-Driven Operator Inference
- Model reduction and neural networks for parametric PDEs
Artificial neural networks and deep learning (68T07) Dependence of solutions to PDEs on initial and/or boundary data and/or on parameters of PDEs (35B30) PDEs with randomness, stochastic partial differential equations (35R60) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Theoretical approximation in context of PDEs (35A35)
Cites Work
- Reduced basis methods for partial differential equations. An introduction
- Reducing the Dimensionality of Data with Neural Networks
- An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- A Stochastic Collocation Method for Elliptic Partial Differential Equations with Random Input Data
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Convergence rates for greedy algorithms in reduced basis methods
- An extension of Tietze's theorem
- Title not available (Why is that?)
- Optimal nonlinear approximation
- Optimal stable nonlinear approximation
- Geometric group theory. With an appendix by Bogdan Nica
- Drei Sätze über die n-dimensionale euklidische Sphäre
- A certified reduced basis method for the Fokker-Planck equation of dilute polymeric fluids: FENE dumbbells in extensional flow
- Numerical solution of the parametric diffusion equation by deep neural networks
- Model reduction and neural networks for parametric PDEs
- \(L^ 2\) estimates for the finite element method for the Dirichlet problem with singular data
- Kolmogorov widths and low-rank approximations of parametric elliptic PDEs
- Embedding and knotting of manifolds in Euclidean spaces
- Proper orthogonal decomposition methods for partial differential equations
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Solution manifolds and submanifolds of parametrized equations and their discretization errors
- Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- Error bounds for approximations with deep ReLU networks
- Reduced order modeling for nonlinear structural analysis using Gaussian process regression
- Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
- Efficient model reduction of parametrized systems by matrix discrete empirical interpolation
- A goal-oriented reduced basis methods-accelerated generalized polynomial chaos algorithm
- Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
- Optimal approximation with sparsely connected deep neural networks
- A nonlinear manifold-based reduced order model for multiscale analysis of heterogeneous hyperelastic materials
- A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
- Reduced-order modelling of parameter-dependent, linear and nonlinear dynamic partial differential equation models
- Title not available (Why is that?)
- Approximation rates for neural networks with encodable weights in smoothness spaces
- POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
- Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs
- Decay of the Kolmogorov \(N\)-width for wave problems
- Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
- Nonlinear approximation and (deep) ReLU networks
- Error estimates for DeepONets: a deep learning framework in infinite dimensions
- A theoretical analysis of deep neural networks and parametric PDEs
- Physics-informed machine learning for reduced-order modeling of nonlinear problems
- Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences
- On the convergence of physics informed neural networks for linear second-order elliptic and parabolic type PDEs
- Estimates on the generalization error of physics-informed neural networks for approximating a class of inverse problems for PDEs
- High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
- Parameter identification for elliptic boundary value problems: an abstract framework and applications
- Generalized reduced basis methods and \(n\)-width estimates for the approximation of the solution manifold of parametric PDEs
Cited In (28)
- A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
- Deep-HyROMnet: a deep learning-based operator approximation for hyper-reduction of nonlinear parametrized PDEs
- Solving parametric partial differential equations with deep rectified quadratic unit neural networks
- The model reduction of the Vlasov–Poisson–Fokker–Planck system to the Poisson–Nernst–Planck system via the Deep Neural Network Approach
- Transformed model reduction for partial differential equations with sharp inner layers
- Meta-auto-decoder: a meta-learning-based reduced order model for solving parametric partial differential equations
- Long-time prediction of nonlinear parametrized dynamical systems by deep learning-based reduced order models
- Diffusion maps-aided neural networks for the solution of parametrized PDEs
- TGPT-PINN: nonlinear model reduction with transformed GPT-PINNs
- Mesh-informed neural networks for operator learning in finite element spaces
- Data-driven deep learning of partial differential equations in modal space
- A deep learning based reduced order modeling for stochastic underground flow problems
- A long short-term memory embedding for hybrid uplifted reduced order models
- Non-linear manifold reduced-order models with convolutional autoencoders and reduced over-collocation method
- On the latent dimension of deep autoencoders for reduced order modeling of PDEs parametrized by random fields
- Nonlinear level set learning for function approximation on sparse data with applications to parametric differential equations
- PTPI-DL-ROMs: pre-trained physics-informed deep learning-based reduced order models for nonlinear parametrized PDEs
- Parametric model reduction with convolutional neural networks
- A Local Deep Learning Method for Solving High Order Partial Differential Equations
- Learning high-dimensional parametric maps via reduced basis adaptive residual networks
- Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions
- Generalization error guaranteed auto-encoder-based nonlinear model reduction for operator learning
- Data driven approximation of parametrized PDEs by reduced basis and neural networks
- Approximation bounds for convolutional neural networks in operator learning
- Application of deep learning reduced-order modeling for single-phase flow in faulted porous media
- Uncertainty quantification for nonlinear solid mechanics using reduced order models with Gaussian process regression
- Leveraging reduced-order models for state estimation using deep learning
- A graph convolutional autoencoder approach to model order reduction for parametrized PDEs
Uses Software
This page was built for publication: A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5058646)
