A Discontinuity Capturing Shallow Neural Network for Elliptic Interface Problems

Abstract

In this paper, a new Discontinuity Capturing Shallow Neural Network (DCSNN) for approximating $d$-dimensional piecewise continuous functions and for solving elliptic interface problems is developed. There are three novel features in the present network; namely, (i) jump discontinuities are accurately captured, (ii) it is completely shallow, comprising only one hidden layer, (iii) it is completely mesh-free for solving partial differential equations. The crucial idea here is that a $d$-dimensional piecewise continuous function can be extended to a continuous function defined in $(d+1)$-dimensional space, where the augmented coordinate variable labels the pieces of each sub-domain. We then construct a shallow neural network to express this new function. Since only one hidden layer is employed, the number of training parameters (weights and biases) scales linearly with the dimension and the neurons used in the hidden layer. For solving elliptic interface problems, the network is trained by minimizing the mean square error loss that consists of the residual of the governing equation, boundary condition, and the interface jump conditions. We perform a series of numerical tests to demonstrate the accuracy of the present network. Our DCSNN model is efficient due to only a moderate number of parameters needed to be trained (a few hundred parameters used throughout all numerical examples), and the results indicate good accuracy. Compared with the results obtained by the traditional grid-based immersed interface method (IIM), which is designed particularly for elliptic interface problems, our network model shows a better accuracy than IIM. We conclude by solving a six-dimensional problem to demonstrate the capability of the present network for high-dimensional applications.

References in corpus (8)

• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• A Machine Learning Framework for Solving High-Dimensional Mean Field Game and Mean Field Control Problems
• PFNN: A Penalty-Free Neural Network Method for Solving a Class of Second-Order Boundary-Value Problems on Complex Geometries
• Deep least-squares methods: an unsupervised learning-based numerical method for solving elliptic PDEs
• A mesh-free method for interface problems using the deep learning approach
• A Shallow Ritz Method for Elliptic Problems with Singular Sources

Cited by in corpus (6)

• A cusp-capturing PINN for elliptic interface problems
• A shallow physics-informed neural network for solving partial differential equations on surfaces
• A Shallow Ritz Method for Elliptic Problems with Singular Sources
• The Hard-Constraint PINNs for Interface Optimal Control Problems
• An efficient neural-network and finite-difference hybrid method for elliptic interface problems with applications
• A hybrid neural-network and MAC scheme for Stokes interface problems