Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems

Abstract

Deep learning has been shown to be an effective tool in solving partial differential equations (PDEs) through physics-informed neural networks (PINNs). PINNs embed the PDE residual into the loss function of the neural network, and have been successfully employed to solve diverse forward and inverse PDE problems. However, one disadvantage of the first generation of PINNs is that they usually have limited accuracy even with many training points. Here, we propose a new method, gradient-enhanced physics-informed neural networks (gPINNs), for improving the accuracy and training efficiency of PINNs. gPINNs leverage gradient information of the PDE residual and embed the gradient into the loss function. We tested gPINNs extensively and demonstrated the effectiveness of gPINNs in both forward and inverse PDE problems. Our numerical results show that gPINN performs better than PINN with fewer training points. Furthermore, we combined gPINN with the method of residual-based adaptive refinement (RAR), a method for improving the distribution of training points adaptively during training, to further improve the performance of gPINN, especially in PDEs with solutions that have steep gradients.

References in corpus (7)

• On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks
• Efficient training of physics-informed neural networks via importance sampling
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• When and why PINNs fail to train: A neural tangent kernel perspective
• Multi-scale Deep Neural Network (MscaleDNN) Methods for Oscillatory Stokes Flows in Complex Domains
• Physics-informed neural networks with hard constraints for inverse design
• Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks

Cited by in corpus (44)

• A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks
• 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 neural networks for solving forward and inverse problems in complex beam systems
• Physics-informed neural networks of the Saint-Venant equations for downscaling a large-scale river model
• A unified scalable framework for causal sweeping strategies for Physics-Informed Neural Networks (PINNs) and their temporal decompositions
• Discontinuity Computing using Physics-Informed Neural Network
• Physics-informed radial basis network (PIRBN): A local approximating neural network for solving nonlinear PDEs
• An overview on deep learning-based approximation methods for partial differential equations
• Physics-informed neural network methods based on Miura transformations and discovery of new localized wave solutions
• Deep energy method in topology optimization applications
• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• Adaptive Training of Grid-Dependent Physics-Informed Kolmogorov-Arnold Networks
• Hutchinson Trace Estimation for High-Dimensional and High-Order Physics-Informed Neural Networks
• Learning Specialized Activation Functions for Physics-informed Neural Networks
• Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems
• Neural Eikonal Solver: improving accuracy of physics-informed neural networks for solving eikonal equation in case of caustics
• PINN Training using Biobjective Optimization: The Trade-off between Data Loss and Residual Loss
• A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data
• Physics-informed neural networks for unsteady incompressible flows with time-dependent moving boundaries
• Asymptotic-Preserving Neural Networks for multiscale hyperbolic models of epidemic spread
• A Dimension-Augmented Physics-Informed Neural Network (DaPINN) with High Level Accuracy and Efficiency
• Data-driven modeling of Landau damping by physics-informed neural networks
• RAR-PINN algorithm for the data-driven vector-soliton solutions and parameter discovery of coupled nonlinear equations
• Invariant deep neural networks under the finite group for solving partial differential equations
• Modelling parametric uncertainty in PDEs models via Physics-Informed Neural Networks
• A mixed formulation for physics-informed neural networks as a potential solver for engineering problems in heterogeneous domains: comparison with finite element method
• Deep learning for full-field ultrasonic characterization
• Residual-Based Error Corrector Operator to Enhance Accuracy and Reliability of Neural Operator Surrogates of Nonlinear Variational Boundary-Value Problems
• Multi-soliton solutions and data-driven discovery of higher-order Burgers' hierarchy equations with physics informed neural networks
• Multi-Fidelity Machine Learning Applied to Steady Fluid Flows
• Physics-Informed Neural Networks for Nonlocal Beam Eigenvalue Problems
• Certified machine learning: Rigorous a posteriori error bounds for PDE defined PINNs
• Quantum neural compressive sensing for ghost imaging
• Sobolev neural network with residual weighting as a surrogate in linear and non-linear mechanics
• A learned conservative semi-Lagrangian finite volume scheme for transport simulations
• Asymptotic-Preserving Neural Networks for hyperbolic systems with diffusive scaling
• A Transferable Physics-Informed Framework for Battery Degradation Diagnosis, Knee-Onset Detection and Knee Prediction
• Spectral Informed Neural Network: An Efficient and Low-Memory PINN
• Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities
• Constrained or Unconstrained? Neural-Network-Based Equation Discovery from Data
• TAEN: A Model-Constrained Tikhonov Autoencoder Network for Forward and Inverse Problems
• Adjoint-based Particle Forcing Reconstruction and Uncertainty Quantification
• The Machine Learning Approach to Moment Closure Relations for Plasma: A Review