返回
Deep neural network enabled active metasurface embedded design
DOI:10.1515/nanoph-2022-0152.png)
摘要
En 中文
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 (similar to 10 nm), high quality factors (Q-factors similar to 10(2)), and large out-of-band rejection (optical density >= 3). The design consists of an optical phase-change material Ge2Sb2Se4Te (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.
Keyword:
active metasurface
deep neural network
embedded design
phase change material
tunable metasurface
期刊
IF:
6.6
论文数:
3.0K
被引数:
1.6W
机构
引用论文
A Bidirectional Deep Neural Network for Accurate Silicon Color Design用于精确硅色设计的双向深度神经网络
ADVANCED MATERIALS
IF26.8
Topological encoding method for data-driven photonics inverse design数据驱动光子学逆设计的拓扑编码方法
OPTICS EXPRESS
IF3.3
High-Efficiency All-Dielectric Metasurfaces for Ultracompact Beam Manipulation in Transmission Mode高效全介电超表面,用于传输模式下的超小光束操纵
NANO LETTERS
IF9.1
Optically reconfigurable metasurfaces and photonic devices based on phase change materials
NATURE PHOTONICS
IF32.9
The Effect of the Deposition Method on the Structural and Optical Properties of ZnS Thin Films
Coatings
IF0
Ultra-thin high-efficiency mid-infrared transmissive Huygens meta-optics超薄高效中红外透射惠更斯超光学器件
NATURE COMMUNICATIONS
IF15.7

