A comprehensive study of boundary conditions when solving PDEs by DNNs

by   Jingrun Chen, et al.

Recent years have witnessed growing interests in solving partial differentialequationsbydeepneuralnetworks,especiallyinthehigh-dimensional case. Unlike classical numerical methods, such as finite difference method and finite element method, the enforcement of boundary conditions in deep neural networks is highly nontrivial. One general strategy is to use the penalty method. In the work, we conduct a comprehensive study of four different boundary conditions, i.e., Dirichlet, Neumann, Robin, and periodic boundary conditions, using two representative methods: deep Ritz method and deep Galerkin method. It is thought that deep Galerkin method works better for smooth solutions while deep Ritz method works better for low-regularity solutions. However, by a number of examples, we observe that deep Ritz method can outperform deep Galerkin method with a clear dependence of dimensionality even for smooth solutions and deep Galerkin method can also outperform deep Ritz method for lowregularity solutions. Besides, in some cases, when the boundary condition can be implemented in an exact manner, we find that such a strategy not only provides a better approximate solution but also facilitates the training process.


page 1

page 2

page 3

page 4


Enforcing exact boundary and initial conditions in the deep mixed residual method

In theory, boundary and initial conditions are important for the wellpos...

Finite elements for Helmholtz equations with a nonlocal boundary condition

Numerical resolution of exterior Helmholtz problems requires some approa...

BR2 discontinuous Galerkin methods for finite hyperelastic deformations

In this work we introduce a dG framework for nonlinear elasticity based ...

Learning Off-By-One Mistakes: An Empirical Study

Mistakes in binary conditions are a source of error in many software sys...

A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs

We present a unified hard-constraint framework for solving geometrically...

A hybridizable discontinuous Galerkin method for simulation of electrostatic problems with floating potential conductors

In an electrostatic simulation, an equipotential condition with an undef...

Please sign up or login with your details

Forgot password? Click here to reset