Physics-Informed Machine Learning for Optical Modes in Composites

TL;DR

This paper introduces a physics-informed machine learning approach that enhances the accuracy and generalizability of modeling optical modes in composites, especially useful when exact solutions are limited or computationally expensive.

Contribution

The paper presents a novel physics-informed learning method applied to optical mode analysis in composites, improving upon traditional machine learning techniques by incorporating physical constraints.

Findings

Significantly improved accuracy in optical mode predictions.

Enhanced generalizability across different composite structures.

Applicable to other eigenvalue problem-based scenarios.

Abstract

We demonstrate that embedding physics-driven constraints into machine learning process can dramatically improve accuracy and generalizability of the resulting model. Physics-informed learning is illustrated on the example of analysis of optical modes propagating through a spatially periodic composite. The approach presented can be readily utilized in other situations mapped onto an eigenvalue problem, a known bottleneck of computational electrodynamics. Physics-informed learning can be used to improve machine-learning-driven design, optimization, and characterization, in particular in situations where exact solutions are scarce or are slow to come up with.