Abstract

In recent years, researchers have made great progress in solving complex electromagnetic field computing problems by using deep learning methods. However, the approaches found in literature were devoted to solving the real-number problem of electromagnetic field calculations. For the complex number problem, there was no good solution. Here, we proposed an advanced computation method for metasurfaces based on a complex residual neural network (CRNN). We predicted the scattering ${({S})_{21}}$ parameters of a cylindrical structure in the range of 1.2 to 1.7 µm wavelengths. By providing a set of cylindrical structure parameters, we could quickly predict the ${{S}_{21}}$ parameters with CRNN and design a metalens, which proved the ability of the proposed method. In addition, our method can also be extended to the calculation of electromagnetic fields where the speed of the calculation of the complex number of metasurfaces should be accelerated.

© 2023 Optica Publishing Group

Neural network enabled metasurface design for phase manipulation

Li Jiang, Xiaozhong Li, Qingxin Wu, Lianhui Wang, and Li Gao
Opt. Express 29(2) 2521-2528 (2021)

Rapid deep-learning-assisted design method for 2-bit coding metasurfaces

Jiahui Fu, Yuping Zhang, Zhongxin Dou, Zhihu Yang, Meng Liu, and Huiyun Zhang
Appl. Opt. 62(13) 3502-3511 (2023)

Inverse design of polarization conversion metasurfaces by deep neural networks

Wanglei Chen, Runkun Li, Zetian Huang, Hao Wu, Jingyang Wei, Shu Wang, Le Wang, and Yanghui Li
Appl. Opt. 62(8) 2048-2054 (2023)

Neural network-based surrogate model for inverse design of metasurfaces

Guoqing Jing, Peipei Wang, Haisheng Wu, Jianjun Ren, Zhiqiang Xie, Junmin Liu, Huapeng Ye, Ying Li, Dianyuan Fan, and Shuqing Chen
Photon. Res. 10(6) 1462-1471 (2022)

Constrained tandem neural network assisted inverse design of metasurfaces for microwave absorption

Xiangxu He, Xiaohan Cui, and C. T. Chan
Opt. Express 31(24) 40969-40979 (2023)