Variational Physics-Informed Neural Networks For Solving Partial Differential Equations

Abstract

Physics-informed neural networks (PINNs) [31] use automatic differentiation to solve partial differential equations (PDEs) by penalizing the PDE in the loss function at a random set of points in the domain of interest. Here, we develop a Petrov-Galerkin version of PINNs based on the nonlinear approximation of deep neural networks (DNNs) by selecting the {\em trial space} to be the space of neural networks and the {\em test space} to be the space of Legendre polynomials. We formulate the \textit{variational residual} of the PDE using the DNN approximation by incorporating the variational form of the problem into the loss function of the network and construct a \textit{variational physics-informed neural network} (VPINN). By integrating by parts the integrand in the variational form, we lower the order of the differential operators represented by the neural networks, hence effectively reducing the training cost in VPINNs while increasing their accuracy compared to PINNs that essentially employ delta test functions. For shallow networks with one hidden layer, we analytically obtain explicit forms of the \textit{variational residual}. We demonstrate the performance of the new formulation for several examples that show clear advantages of VPINNs over PINNs in terms of both accuracy and speed.

24 pages, 12 figures

References in corpus (8)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• Machine Learning of Linear Differential Equations using Gaussian Processes
• Nonlinear Approximation and (Deep) ReLU Networks
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• Nonlinear Approximation via Compositions
• Nonlinear Approximation Using Gaussian Kernels
• Greedy Deep Dictionary Learning

Cited by in corpus (48)

• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• SciANN: A Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
• Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations
• Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
• Non-invasive Inference of Thrombus Material Properties with Physics-informed Neural Networks
• A two-stage physics-informed neural network method based on conserved quantities and applications in localized wave solutions
• A nonlocal physics-informed deep learning framework using the peridynamic differential operator
• Hybrid FEM-NN models: Combining artificial neural networks with the finite element method
• An overview on deep learning-based approximation methods for partial differential equations
• Variational Physics Informed Neural Networks: the role of quadratures and test functions
• Magnetostatics and micromagnetics with physics informed neural networks
• Physics-informed neural network methods based on Miura transformations and discovery of new localized wave solutions
• Weak Form Theory-guided Neural Network (TgNN-wf) for Deep Learning of Subsurface Single and Two-phase Flow
• BINN: A deep learning approach for computational mechanics problems based on boundary integral equations
• Conditional physics informed neural networks
• Mosaic Flows: A Transferable Deep Learning Framework for Solving PDEs on Unseen Domains
• Recipes for when Physics Fails: Recovering Robust Learning of Physics Informed Neural Networks
• Error estimates of residual minimization using neural networks for linear PDEs
• Energy-based error bound of physics-informed neural network solutions in elasticity
• Error convergence and engineering-guided hyperparameter search of PINNs: towards optimized I-FENN performance
• Physics-Informed Deep Learning of Rate-and-State Fault Friction
• A priori and a posteriori error estimates for the Deep Ritz method applied to the Laplace and Stokes problem
• A Deep Double Ritz Method (D${}^2$RM) for solving Partial Differential Equations using Neural Networks
• Deep learning for solution and inversion of structural mechanics and vibrations
• Spectrally Adapted Physics-Informed Neural Networks for Solving Unbounded Domain Problems
• Modelling parametric uncertainty in PDEs models via Physics-Informed Neural Networks
• Explicit physics-informed neural networks for non-linear upscaling closure: the case of transport in tissues
• Variational PINNs with tree-based integration and boundary element data in the modeling of multi-phase architected materials
• Analytical derivatives of Neural Networks
• Preconditioned FEM-based Neural Networks for Solving Incompressible Fluid Flows and Related Inverse Problems
• An operator preconditioning perspective on training in physics-informed machine learning
• Numerical simulation of transient heat conduction with moving heat source using Physics Informed Neural Networks
• Data-Centric Engineering: integrating simulation, machine learning and statistics. Challenges and Opportunities
• Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation
• Galerkin Neural Networks: A Framework for Approximating Variational Equations with Error Control
• Gradient Flow Based Phase-Field Modeling Using Separable Neural Networks
• Deep Ritz-Finite Element methods: Neural Network Methods trained with Finite Elements
• A Physics-Informed Neural Network Framework For Partial Differential Equations on 3D Surfaces: Time-Dependent Problems
• Error bounds for PDE-regularized learning
• A Convolutional Neural Network-based Approach to Field Reconstruction
• Theory-training deep neural networks for an alloy solidification benchmark problem
• Learning To Estimate Regions Of Attraction Of Autonomous Dynamical Systems Using Physics-Informed Neural Networks
• Machine-learning custom-made basis functions for partial differential equations