Learning Green's Functions of Linear Reaction-Diffusion Equations with Application to Fast Numerical Solver
This provides a fast numerical solver for physical modeling problems, but it is incremental as it builds on existing physics-informed deep learning approaches.
The paper tackles the problem of solving linear reaction-diffusion equations by proposing GF-Net, a neural network that learns Green's functions in an unsupervised manner, leading to an efficient solver for various domains and boundary conditions.
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.