DeepGreen: Deep Learning of Green's Functions for Nonlinear Boundary Value Problems

TL;DR

DeepGreen introduces a deep learning framework that learns Green's functions for nonlinear boundary value problems by discovering invertible transforms, enabling efficient solutions across diverse nonlinear systems.

Contribution

It proposes a dual-autoencoder deep learning architecture to linearize nonlinear BVPs and identify Green's functions, a novel approach for solving nonlinear boundary value problems.

Findings

Successfully applied to nonlinear Helmholtz and Sturm–Liouville problems

Effectively solves nonlinear elasticity and 2D nonlinear Poisson equations

Combines deep learning with physics-based Green's functions for flexible solutions

Abstract

Boundary value problems (BVPs) play a central role in the mathematical analysis of constrained physical systems subjected to external forces. Consequently, BVPs frequently emerge in nearly every engineering discipline and span problem domains including fluid mechanics, electromagnetics, quantum mechanics, and elasticity. The fundamental solution, or Green's function, is a leading method for solving linear BVPs that enables facile computation of new solutions to systems under any external forcing. However, fundamental Green's function solutions for nonlinear BVPs are not feasible since linear superposition no longer holds. In this work, we propose a flexible deep learning approach to solve nonlinear BVPs using a dual-autoencoder architecture. The autoencoders discover an invertible coordinate transform that linearizes the nonlinear BVP and identifies both a linear operator $L$ and Green's function $G$ which can be used to solve new nonlinear BVPs. We find that the method succeeds on a variety of nonlinear systems including nonlinear Helmholtz and Sturm--Liouville problems, nonlinear elasticity, and a 2D nonlinear Poisson equation. The method merges the strengths of the universal approximation capabilities of deep learning with the physics knowledge of Green's functions to yield a flexible tool for identifying fundamental solutions to a variety of nonlinear systems.