Accelerating the convergence of Newton's method for nonlinear elliptic PDEs using Fourier neural operators

Abstract

It is well known that Newton's method can have trouble converging if the initial guess is too far from the solution. Such a problem particularly occurs when this method is used to solve nonlinear elliptic partial differential equations (PDEs) discretized via finite differences. This work focuses on accelerating Newton's method convergence in this context. We seek to construct a mapping from the parameters of the nonlinear PDE to an approximation of its discrete solution, independently of the mesh resolution. This approximation is then used as an initial guess for Newton's method. To achieve these objectives, we elect to use a Fourier neural operator (FNO). The loss function is the sum of a data term (i.e., the comparison between known solutions and outputs of the FNO) and a physical term (i.e., the residual of the PDE discretization). Numerical results, in one and two dimensions, show that the proposed initial guess accelerates the convergence of Newton's method by a large margin compared to a naive initial guess, especially for highly nonlinear and anisotropic problems, with larger gains on coarse grids.

References in corpus (4)

• The JOREK non-linear extended MHD code and applications to large-scale instabilities and their control in magnetically confined fusion plasmas
• Plasma Surrogate Modelling using Fourier Neural Operators
• Geometry-Informed Neural Operator for Large-Scale 3D PDEs
• Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations

Cited by in corpus (1)

• Learning Gradient Flow: Using Equation Discovery to Accelerate Engineering Optimization