Hierarchical Learning to Solve Partial Differential Equations Using Physics-Informed Neural Networks

by   Jihun Han, et al.

The Neural network-based approach to solving partial differential equations has attracted considerable attention due to its simplicity and flexibility to represent the solution of the partial differential equation. In training a neural network, the network tends to learn global features corresponding to low-frequency components while high-frequency components are approximated at a much slower rate (F-principle). For a class of equations in which the solution contains a wide range of scales, the network training process can suffer from slow convergence and low accuracy due to its inability to capture the high-frequency components. In this work, we propose a hierarchical approach to improve the convergence rate and accuracy of the neural network solution to partial differential equations. The proposed method comprises multi-training levels in which a newly introduced neural network is guided to learn the residual of the previous level approximation. By the nature of neural networks' training process, the high-level correction is inclined to capture the high-frequency components. We validate the efficiency and robustness of the proposed hierarchical approach through a suite of linear and nonlinear partial differential equations.


page 11

page 15

page 19


Solving nonlinear circuits with pulsed excitation by multirate partial differential equations

In this paper the concept of Multirate Partial Differential Equations (M...

Using Hierarchical Parallelism to Accelerate the Solution of Many Small Partial Differential Equations

This paper presents efforts to improve the hierarchical parallelism of a...

SRoll3: A neural network approach to reduce large-scale systematic effects in the Planck High Frequency Instrument maps

In the present work, we propose a neural network based data inversion ap...

Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks

Physics-informed neural network (PINN) algorithms have shown promising r...

Multi-level Neural Networks for Accurate Solutions of Boundary-Value Problems

The solution to partial differential equations using deep learning appro...

An Enhanced V-cycle MgNet Model for Operator Learning in Numerical Partial Differential Equations

This study used a multigrid-based convolutional neural network architect...

VI-PINNs: Variance-involved Physics-informed Neural Networks for Fast and Accurate Prediction of Partial Differential Equations

Although physics-informed neural networks(PINNs) have progressed a lot i...

Please sign up or login with your details

Forgot password? Click here to reset