Deep neural network enabled active metasurface embedded design
View / Open Files
Authors
An, Sensong
Zheng, Bowen
Julian, Matthew
Tang, Hong
Gu, Tian
Zhang, Hualiang
Kim, Hyun Jung
Hu, Juejun
Publication Date
2022-06-10Journal Title
NANOPHOTONICS
ISSN
2192-8606
Publisher
Walter de Gruyter GmbH
Volume
0
Issue
0
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
An, S., Zheng, B., Julian, M., Williams, C., Tang, H., Gu, T., Zhang, H., et al. (2022). Deep neural network enabled active metasurface embedded design. NANOPHOTONICS, 0 (0) https://doi.org/10.1515/nanoph-2022-0152
Abstract
<jats:title>Abstract</jats:title>
<jats:p>In this paper, we propose a deep learning approach for forward modeling and inverse design of photonic devices containing embedded active metasurface structures. In particular, we demonstrate that combining neural network design of metasurfaces with scattering matrix-based optimization significantly simplifies the computational overhead while facilitating accurate objective-driven design. As an example, we apply our approach to the design of a continuously tunable bandpass filter in the mid-wave infrared, featuring narrow passband (∼10 nm), high quality factors (<jats:italic>Q</jats:italic>-factors ∼ 10<jats:sup>2</jats:sup>), and large out-of-band rejection (optical density ≥ 3). The design consists of an optical phase-change material Ge<jats:sub>2</jats:sub>Sb<jats:sub>2</jats:sub>Se<jats:sub>4</jats:sub>Te (GSST) metasurface atop a silicon heater sandwiched between two distributed Bragg reflectors (DBRs). The proposed design approach can be generalized to the modeling and inverse design of arbitrary response photonic devices incorporating active metasurfaces.</jats:p>
Identifiers
External DOI: https://doi.org/10.1515/nanoph-2022-0152
This record's URL: https://www.repository.cam.ac.uk/handle/1810/338046
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.