Artificial Intelligence-Generated Terahertz Multi-Resonant Metasurfaces via Improved Transformer and CGAN Neural Networks
This work facilitates the design process of AI-generated metasurfaces for researchers in terahertz technology and materials science, though it appears incremental as it builds on existing neural network methods.
The authors tackled the limited generalization of traditional deep neural networks in inverse design of terahertz multi-resonant graphene metasurfaces by proposing improved Transformer and CGAN neural networks, achieving higher accuracy and generalization in spectrum-to-vector and spectrum-to-image designs.
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.