A deep learning approach to resonant light transmission through single subwavelength apertures

TL;DR

This paper presents a deep learning framework that accurately models and designs resonant light transmission through subwavelength apertures in metallic screens, significantly advancing computational efficiency and inverse design capabilities.

Contribution

It introduces a neural network-based approach combined with a semi-analytical dataset generation method for efficient modeling and inverse design of nanostructured metallic apertures.

Findings

Neural networks accurately predict transmission spectra from geometrical parameters.

A tandem deep learning architecture enables inverse design of nanostructures.

The approach reduces computational cost compared to traditional simulation methods.

Abstract

Resonant transmission of light is a surface-wave assisted phenomenon that enables funneling light through subwavelength apertures milled in otherwise opaque metallic screens. In this work, we introduce a deep learning approach to efficiently compute and design the optical response of a single subwavelength slit perforated in a metallic screen and surrounded by periodic arrangements of indentations. First, we show that a semi-analytical framework based on a coupled-mode theory formalism is a robust and efficient method to generate the large training datasets required in the proposed approach. Second, we discuss how simple, densely connected artificial neural networks can accurately learn the mapping from the geometrical parameters defining the topology of the system to its corresponding transmission spectrum. Finally, we report on a deep learning tandem architecture able to perform inverse design tasks for the considered class of systems. We expect this work to stimulate further work on the application of deep learning to the analysis of light-matter interaction in nanostructured metallic films.