Learning Green's Functions of Linear Reaction-Diffusion Equations with Application to Fast Numerical Solver

TL;DR

This paper introduces GF-Net, a neural network that learns Green's functions for linear reaction-diffusion equations, enabling fast and flexible solutions on arbitrary domains using physics-informed learning.

Contribution

The paper presents a novel unsupervised neural network approach that efficiently learns Green's functions for reaction-diffusion equations on complex domains, leveraging physics-informed principles and symmetry.

Findings

GF-Net accurately learns Green's functions on various domains.

The method enables fast solutions for different boundary conditions.

Experiments demonstrate high effectiveness on complex geometries.

Abstract

Partial differential equations are often used to model various physical phenomena, such as heat diffusion, wave propagation, fluid dynamics, elasticity, electrodynamics and image processing, and many analytic approaches or traditional numerical methods have been developed and widely used for their solutions. Inspired by rapidly growing impact of deep learning on scientific and engineering research, in this paper we propose a novel neural network, GF-Net, for learning the Green's functions of linear reaction-diffusion equations in an unsupervised fashion. The proposed method overcomes the challenges for finding the Green's functions of the equations on arbitrary domains by utilizing physics-informed approach and the symmetry of the Green's function. As a consequence, it particularly leads to an efficient way for solving the target equations under different boundary conditions and sources. We also demonstrate the effectiveness of the proposed approach by experiments in square, annular and L-shape domains.