Solving parametric PDE problems with artificial neural networks
From MaRDI portal
Abstract: The curse of dimensionality is commonly encountered in numerical partial differential equations (PDE), especially when uncertainties have to be modeled into the equations as random coefficients. However, very often the variability of physical quantities derived from a PDE can be captured by a few features on the space of the coefficient fields. Based on such an observation, we propose using a neural-network (NN) based method to parameterize the physical quantity of interest as a function of input coefficients. The representability of such quantity using a neural-network can be justified by viewing the neural-network as performing time evolution to find the solutions to the PDE. We further demonstrate the simplicity and accuracy of the approach through notable examples of PDEs in engineering and physics.
Recommendations
- Numerical solution of the parametric diffusion equation by deep neural networks
- Model reduction and neural networks for parametric PDEs
- Data driven approximation of parametrized PDEs by reduced basis and neural networks
- Diffusion maps-aided neural networks for the solution of parametrized PDEs
- Proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients
Cites work
- A Data-Driven Stochastic Method for Elliptic PDEs with Random Coefficients
- Algebraic multigrid methods
- Galerkin methods for linear and nonlinear elliptic stochastic partial differential equations
- Reducing the Dimensionality of Data with Neural Networks
- Solving for high-dimensional committor functions using artificial neural networks
- Solving the quantum many-body problem with artificial neural networks
- The stochastic finite element method: past, present and future
- The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
Cited in
(only showing first 100 items - show all)- Traveling wave solutions of partial differential equations via neural networks
- Networks for nonlinear diffusion problems in imaging
- Hierarchical deep learning neural network (HiDeNN): an artificial intelligence (AI) framework for computational science and engineering
- Diffusion maps-aided neural networks for the solution of parametrized PDEs
- Numerical solution of the parametric diffusion equation by deep neural networks
- Model reduction and neural networks for parametric PDEs
- A novel sequential method to train physics informed neural networks for Allen Cahn and Cahn Hilliard equations
- Monte Carlo fPINNs: deep learning method for forward and inverse problems involving high dimensional fractional partial differential equations
- Learning phase field mean curvature flows with neural networks
- Efficient coupled deep neural networks for the time-dependent coupled Stokes-Darcy problems
- CAS4DL: Christoffel adaptive sampling for function approximation via deep learning
- Committor functions via tensor networks
- GenMod: a generative modeling approach for spectral representation of PDEs with random inputs
- Solving parametric partial differential equations with deep rectified quadratic unit neural networks
- B-DeepONet: an enhanced Bayesian deeponet for solving noisy parametric PDEs using accelerated replica exchange SGLD
- DNN expression rate analysis of high-dimensional PDEs: application to option pricing
- A theoretical analysis of deep neural networks and parametric PDEs
- Hybrid FEM-NN models: combining artificial neural networks with the finite element method
- A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
- Normalizing field flows: solving forward and inverse stochastic differential equations using physics-informed flow models
- On quadrature rules for solving partial differential equations using neural networks
- Computing the invariant distribution of randomly perturbed dynamical systems using deep learning
- Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
- Numerical approximation of partial differential equations by a variable projection method with artificial neural networks
- Learning deep implicit Fourier neural operators (IFNOs) with applications to heterogeneous material modeling
- Deep global model reduction learning in porous media flow simulation
- ConvPDE-UQ: convolutional neural networks with quantified uncertainty for heterogeneous elliptic partial differential equations on varied domains
- Solving many-electron Schrödinger equation using deep neural networks
- Simulator-free solution of high-dimensional stochastic elliptic partial differential equations using deep neural networks
- Artificial neural network approximations of Cauchy inverse problem for linear PDEs
- General solutions for nonlinear differential equations: a rule-based self-learning approach using deep reinforcement learning
- Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations
- An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications
- Solving for high-dimensional committor functions using artificial neural networks
- A multiscale neural network based on hierarchical nested bases
- Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
- An exploratory study on machine learning to couple numerical solutions of partial differential equations
- A hybrid MGA-MSGD ANN training approach for approximate solution of linear elliptic PDEs
- A finite element based deep learning solver for parametric PDEs
- DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method
- A survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problems
- Nonlocal kernel network (NKN): a stable and resolution-independent deep neural network
- ADLGM: an efficient adaptive sampling deep learning Galerkin method
- Isogeometric neural networks: a new deep learning approach for solving parameterized partial differential equations
- opPINN: physics-informed neural network with operator learning to approximate solutions to the Fokker-Planck-Landau equation
- Greedy training algorithms for neural networks and applications to PDEs
- Automated design parameter selection for neural networks solving coupled partial differential equations with discontinuities
- Efficient construction of tensor ring representations from sampling
- Connections between deep learning and partial differential equations
- Deep Adaptive Basis Galerkin Method for High-Dimensional Evolution Equations With Oscillatory Solutions
- Discretization of parameter identification in PDEs using neural networks
- A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations
- Neural parametric Fokker-Planck equation
- Deep neural network surrogates for nonsmooth quantities of interest in shape uncertainty quantification
- Physics-informed generative adversarial networks for stochastic differential equations
- A Multiscale Neural Network Based on Hierarchical Matrices
- Solving inverse problems using data-driven models
- Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data
- Stationary Density Estimation of Itô Diffusions Using Deep Learning
- A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations
- Simultaneous neural network approximation for smooth functions
- Probabilistic partition of unity networks for high‐dimensional regression problems
- Deep learning methods for partial differential equations and related parameter identification problems
- Deep capsule encoder–decoder network for surrogate modeling and uncertainty quantification
- Solving the discretised neutron diffusion equations using neural networks
- Solving nonconvex energy minimization problems in martensitic phase transitions with a mesh-free deep learning approach
- Data-driven vortex solitons and parameter discovery of 2D generalized nonlinear Schrödinger equations with a \(\mathcal{PT}\)-symmetric optical lattice
- A method for computing inverse parametric PDE problems with random-weight neural networks
- Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation
- Friedrichs Learning: Weak Solutions of Partial Differential Equations via Deep Learning
- Neural Galerkin schemes with active learning for high-dimensional evolution equations
- A mathematical perspective of machine learning
- Transferable neural networks for partial differential equations
- A conservative hybrid deep learning method for Maxwell-Ampère-Nernst-Planck equations
- Structure-preserving recurrent neural networks for a class of Birkhoffian systems
- A Review of Data‐Driven Discovery for Dynamic Systems
- Deep convolutional Ritz method: parametric PDE surrogates without labeled data
- A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology
- Bi-Orthogonal fPINN: A Physics-Informed Neural Network Method for Solving Time-Dependent Stochastic Fractional PDEs
- Connections between numerical algorithms for PDEs and neural networks
- Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
- Energy-dissipative evolutionary deep operator neural networks
- Quantification of Errors Generated by Uncertain Data in a Linear Boundary Value Problem Using Neural Networks
- Dual order-reduced Gaussian process emulators (DORGP) for quantifying high-dimensional uncertain crack growth using limited and noisy data
- A Reduced Order Schwarz Method for Nonlinear Multiscale Elliptic Equations Based on Two-Layer Neural Networks
- Is the neural tangent kernel of PINNs deep learning general partial differential equations always convergent?
- Solving inverse problems with deep learning
- On mathematical modeling in image reconstruction and beyond
- Kernel methods are competitive for operator learning
- Positional Embeddings for Solving PDEs with Evolutional Deep Neural Networks
- Approximation of smooth functionals using deep ReLU networks
- Two-stage initial-value iterative physics-informed neural networks for simulating solitary waves of nonlinear wave equations
- Data-driven modeling of partially observed biological systems
- Learning quantities of interest from parametric PDEs: an efficient neural-weighted minimal residual approach
- Multi-scale time-stepping of partial differential equations with transformers
- Gauss Newton method for solving variational problems of PDEs with neural network discretizaitons
- Meta-auto-decoder: a meta-learning-based reduced order model for solving parametric partial differential equations
- Approximation of single-barrier options partial differential equations using feed-forward neural network
- Long-time prediction of nonlinear parametrized dynamical systems by deep learning-based reduced order models
- Operator learning using random features: a tool for scientific computing
This page was built for publication: Solving parametric PDE problems with artificial neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5014839)
