Learning local Dirichlet-to-Neumann maps of nonlinear elliptic PDEs with rough coefficients

TL;DR

This paper introduces a novel approach combining multi-scale finite element methods with machine learning to approximate local nonlinear Dirichlet-to-Neumann maps for solving complex nonlinear elliptic PDEs with rough coefficients.

Contribution

It extends MsFEM to nonlinear PDEs by learning local nonlinear DtN maps, enabling efficient multi-scale analysis beyond linear problems.

Findings

Preliminary results show successful learning of nonlinear DtN maps.

Method applied to p-Laplacian and degenerate nonlinear diffusion equations.

Potential for improved numerical approximation of complex PDEs.

Abstract

Partial differential equations (PDEs) involving high contrast and oscillating coefficients are common in scientific and industrial applications. Numerical approximation of these PDEs is a challenging task that can be addressed, for example, by multi-scale finite element analysis. For linear problems, multi-scale finite element method (MsFEM) is well established and some viable extensions to non-linear PDEs are known. However, some features of the method seem to be intrinsically based on linearity-based. In particular, traditional MsFEM rely on the reuse of computations. For example, the stiffness matrix can be calculated just once, while being used for several right-hand sides, or as part of a multi-level iterative algorithm. Roughly speaking, the offline phase of the method amounts to pre-assembling the local linear Dirichlet-to-Neumann (DtN) operators. We present some preliminary results concerning the combination of MsFEM with machine learning tools. The extension of MsFEM to nonlinear problems is achieved by means of learning local nonlinear DtN maps. The resulting learning-based multi-scale method is tested on a set of model nonlinear PDEs involving the $p-$Laplacian and degenerate nonlinear diffusion.