Artificial Intelligence-Generated Terahertz Multi-Resonant Metasurfaces via Improved Transformer and CGAN Neural Networks

TL;DR

This paper introduces advanced neural network models, including an improved Transformer and CGAN, to enhance the inverse design process of terahertz graphene metasurfaces, enabling more accurate and comprehensive design capabilities.

Contribution

It presents novel neural network architectures that improve the accuracy and generalization in the inverse design of THz metasurfaces, surpassing traditional methods.

Findings

Improved Transformer outperforms MLP in Spectrum to Vector design.

CGAN provides more detailed and accurate Spectrum to Image design.

The models enable direct inverse design from absorption spectra to metasurface images.

Abstract

It is well known that the inverse design of terahertz (THz) multi-resonant graphene metasurfaces by using traditional deep neural networks (DNNs) has limited generalization ability. In this paper, we propose improved Transformer and conditional generative adversarial neural networks (CGAN) for the inverse design of graphene metasurfaces based upon THz multi-resonant absorption spectra. The improved Transformer can obtain higher accuracy and generalization performance in the StoV (Spectrum to Vector) design compared to traditional multilayer perceptron (MLP) neural networks, while the StoI (Spectrum to Image) design achieved through CGAN can provide more comprehensive information and higher accuracy than the StoV design obtained by MLP. Moreover, the improved CGAN can achieve the inverse design of graphene metasurface images directly from the desired multi-resonant absorption spectra. It is turned out that this work can finish facilitating the design process of artificial intelligence-generated metasurfaces (AIGM), and even provide a useful guide for developing complex THz metasurfaces based on 2D materials using generative neural networks.