Learning Domain-Independent Green's Function For Elliptic Partial Differential Equations
This addresses a bottleneck in solving PDEs with variable coefficients for computational physics and engineering, offering a novel method but with incremental improvements over existing numerical approaches.
The paper tackles the challenge of finding analytical Green's functions for elliptic PDEs with variable coefficients by proposing a boundary integral network (BIN-G) that learns domain-independent Green's functions, achieving fast training and accurate evaluation as verified in numerical experiments on Poisson and Helmholtz equations.
Green's function characterizes a partial differential equation (PDE) and maps its solution in the entire domain as integrals. Finding the analytical form of Green's function is a non-trivial exercise, especially for a PDE defined on a complex domain or a PDE with variable coefficients. In this paper, we propose a novel boundary integral network to learn the domain-independent Green's function, referred to as BIN-G. We evaluate the Green's function in the BIN-G using a radial basis function (RBF) kernel-based neural network. We train the BIN-G by minimizing the residual of the PDE and the mean squared errors of the solutions to the boundary integral equations for prescribed test functions. By leveraging the symmetry of the Green's function and controlling refinements of the RBF kernel near the singularity of the Green function, we demonstrate that our numerical scheme enables fast training and accurate evaluation of the Green's function for PDEs with variable coefficients. The learned Green's function is independent of the domain geometries, forcing terms, and boundary conditions in the boundary integral formulation. Numerical experiments verify the desired properties of the method and the expected accuracy for the two-dimensional Poisson and Helmholtz equations with variable coefficients.