Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems

Abstract

Despite the great promise of the physics-informed neural networks (PINNs) in solving forward and inverse problems, several technical challenges are present as roadblocks for more complex and realistic applications. First, most existing PINNs are based on point-wise formulation with fully-connected networks to learn continuous functions, which suffer from poor scalability and hard boundary enforcement. Second, the infinite search space over-complicates the non-convex optimization for network training. Third, although the convolutional neural network (CNN)-based discrete learning can significantly improve training efficiency, CNNs struggle to handle irregular geometries with unstructured meshes. To properly address these challenges, we present a novel discrete PINN framework based on graph convolutional network (GCN) and variational structure of PDE to solve forward and inverse partial differential equations (PDEs) in a unified manner. The use of a piecewise polynomial basis can reduce the dimension of search space and facilitate training and convergence. Without the need of tuning penalty parameters in classic PINNs, the proposed method can strictly impose boundary conditions and assimilate sparse data in both forward and inverse settings. The flexibility of GCNs is leveraged for irregular geometries with unstructured meshes. The effectiveness and merit of the proposed method are demonstrated over a variety of forward and inverse computational mechanics problems governed by both linear and nonlinear PDEs.

27 pages, 10 figures

References in corpus (7)

• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• Uncovering near-wall blood flow from sparse data with physics-informed neural networks
• Variational Physics-Informed Neural Networks For Solving Partial Differential Equations
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework
• Site-specific graph neural network for predicting protonation energy of oxygenate molecules

Cited by in corpus (30)

• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• Deep Learning in Deterministic Computational Mechanics
• Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries
• Novel DeepONet architecture to predict stresses in elastoplastic structures with variable complex geometries and loads
• Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
• $\Delta$-PINNs: physics-informed neural networks on complex geometries
• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• On the use of graph neural networks and shape-function-based gradient computation in the deep energy method
• Finite Volume Graph Network(FVGN): Predicting unsteady incompressible fluid dynamics with finite volume informed neural network
• A Framework Based on Symbolic Regression Coupled with eXtended Physics-Informed Neural Networks for Gray-Box Learning of Equations of Motion from Data
• RBF-MGN:Solving spatiotemporal PDEs with Physics-informed Graph Neural Network
• Mesh Neural Networks for SE(3)-Equivariant Hemodynamics Estimation on the Artery Wall
• A Finite Element-Inspired Hypergraph Neural Network: Application to Fluid Dynamics Simulations
• Fully probabilistic deep models for forward and inverse problems in parametric PDEs
• Predicting fluid-structure interaction with graph neural networks
• Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes
• The Principle of Minimum Pressure Gradient: An Alternative Basis for Physics-Informed Learning of Incompressible Fluid Mechanics
• Modelling parametric uncertainty in PDEs models via Physics-Informed Neural Networks
• On the data-driven description of lattice materials mechanics
• Modeling Global Surface Dust Deposition Using Physics-Informed Neural Networks
• Physics-informed graph neural networks for flow field estimation in carotid arteries
• Physics-Informed Graph-Mesh Networks for PDEs: A hybrid approach for complex problems
• Preconditioned FEM-based Neural Networks for Solving Incompressible Fluid Flows and Related Inverse Problems
• Frame invariance and scalability of neural operators for partial differential equations
• Physics-Guided Discovery of Highly Nonlinear Parametric Partial Differential Equations
• Physics-Informed Graph Convolutional Networks: Towards a generalized framework for complex geometries
• Neural network-based Godunov corrections for approximate Riemann solvers using bi-fidelity learning
• Latent Dynamics Graph Convolutional Networks for model order reduction of parameterized time-dependent PDEs
• Solver-in-the-Loop joint operator learning: fractional Laplace-Beltrami features for interface reconstruction