End-to-end multichannel holographic metasurface inverse design using an enhanced bi-directional deep neural network
Optics Express · 25.08.2025 · 33 (17) · 36801
DOI: 10.1364/oe.570960 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 20.08.2025. Verfasst von Ming Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Laboratory of Basic Scientific Research for Innovation Fund, Hebei Province Science and Technology Support Program.
Abstract (Originalsprache)
We present an end-to-end inverse-design system that combines a periodicity-aware modified gradient descent (MGD) with an enhanced bidirectional neural network (EBI-DNN) to rapidly generate phase distributions and quickly get meta-atom parameters for multifunctional terahertz (THz) holographic metasurfaces. The MGD converts six grayscale letters into a smooth phase hologram, and the EBI-DNN, trained on 7.4 k samples in 40.8 s, 1.8 × faster than the conventional model, maps the phase to silicon pillar geometries parameters. This system completes designs within seconds and produces a 100 × 100 pixel, six-channel metasurface operating at 1 THz that projects the images “YT,” “CO,” and “DB” onto two focal planes with a peak signal-to-noise ratio (PSNR) of 15.7 dB, root-mean-square (RMS) error of 1.72. The system’s combined advantages of computational speed, structural accuracy, and compact form factor offer a practical pathway toward large-area, multifunctional metasurface technologies.
Förderung
- National Natural Science Foundation of China
- National Key Laboratory of Basic Scientific Research for Innovation Fund
- Hebei Province Science and Technology Support Program
- Department of Education of Hebei Province
Zitieren
APA
Zhang, M., Zhao, F., Tao, E., He, Y., Han, Q., Yang, L., & Hou, W. (2025). End-to-end multichannel holographic metasurface inverse design using an enhanced bi-directional deep neural network. Optics Express, 33(17), 36801. https://doi.org/10.1364/oe.570960
Vancouver
Zhang M, Zhao F, Tao E, He Y, Han Q, Yang L, et al. End-to-end multichannel holographic metasurface inverse design using an enhanced bi-directional deep neural network. Optics Express. 2025;33(17):36801. doi:10.1364/oe.570960
BibTeX
@article{Zhang2025,
author = {Zhang, Ming and Zhao, Fangxu and Tao, En and He, Yuhang and Han, Qi and Yang, Lin and Hou, Weimin},
title = {End-to-end multichannel holographic metasurface inverse design using an enhanced bi-directional deep neural network},
journal = {Optics Express},
year = {2025},
volume = {33},
number = {17},
pages = {36801},
doi = {10.1364/oe.570960}
}
EUVIMED