Bidirectional Adversarial Autoencoders for the design of Plasmonic Metasurfaces

TL;DR

This paper introduces a Bidirectional Adversarial Autoencoder that improves the design of nonlinear photonic metasurfaces, enabling the generation of structures with multiple spectral peaks more reliably than previous methods.

Contribution

The paper presents a novel Bidirectional Adversarial Autoencoder approach that enhances the inverse design of metasurfaces with complex spectral features, surpassing existing GAN-based methods.

Findings

Successfully generates structures with multiple spectral peaks

Outperforms traditional GAN-based design methods

Advances nonlinear metasurface design capabilities

Abstract

Deep Learning has been a critical part of designing inverse design methods that are computationally efficient and accurate. An example of this is the design of photonic metasurfaces by using their photoluminescent spectrum as the input data to predict their topology. One fundamental challenge of these systems is their ability to represent nonlinear relationships between sets of data that have different dimensionalities. Existing design methods often implement a conditional Generative Adversarial Network in order to solve this problem, but in many cases the solution is unable to generate structures that provide multiple peaks when validated. It is demonstrated that in response to the target spectrum, the Bidirectional Adversarial Autoencoder is able to generate structures that provide multiple peaks on several occasions. As a result the proposed model represents an important advance towards the generation of nonlinear photonic metasurfaces that can be used in advanced metasurface design.