Inverse design of metasurface optical filters using deep neural network with high degrees of freedom

Xiao, Han; Fan, Ziyang; Liu, Zeyang; Li, Chao; Guo, L. Jay

doi:10.1002/inf2.12116

Cited by 48 publications

(29 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For data collection, we use the Rigorous Coupled Wave Analysis (RCWA) 54 to simulate 8411 samples. Structure parameters of are uniformly and randomly sampled in the ranges of (80, 160) nm, (30,200) nm, (160, 320) nm, and (300, 700) nm, respectively.…”

Section: Template Structures: Silicon Structure Color Inverse Designmentioning

confidence: 99%

Benchmarking deep learning-based models on nanophotonic inverse design problems

Ma¹,

Tobah²,

Wang³

et al. 2022

OES

Self Cite

View full text Add to dashboard Cite

Photonic inverse design concerns the problem of finding photonic structures with target optical properties. However, traditional methods based on optimization algorithms are time-consuming and computationally expensive. Recently, deep learning-based approaches have been developed to tackle the problem of inverse design efficiently. Although most of these neural network models have demonstrated high accuracy in different inverse design problems, no previous study has examined the potential effects under given constraints in nanomanufacturing. Additionally, the relative strength of different deep learning-based inverse design approaches has not been fully investigated. Here, we benchmark three commonly used deep learning models in inverse design: Tandem networks, Variational Auto-Encoders, and Generative Adversarial Networks. We provide detailed comparisons in terms of their accuracy, diversity, and robustness. We find that tandem networks and Variational Auto-Encoders give the best accuracy, while Generative Adversarial Networks lead to the most diverse predictions. Our findings could serve as a guideline for researchers to select the model that can best suit their design criteria and fabrication considerations. In addition, our code and data are publicly available, which could be used for future inverse design model development and benchmarking.

show abstract

Section: Template Structures: Silicon Structure Color Inverse Designmentioning

confidence: 99%

Benchmarking deep learning-based models on nanophotonic inverse design problems

Ma¹,

Tobah²,

Wang³

et al. 2022

OES

Self Cite

View full text Add to dashboard Cite

show abstract

“…Xiao Han et al demonstrates that encoded filters capable of filtering light of specific wavelength can be achieved via inverse design by varying planar geometric shape of metasurface, which is an overwhelming advantage over multilayer thin-film filters (Figure 8e) [75]. As shown in Figure 8e, the physical structures of customized metasurface spectral filtering consists 2D pattern poly-Si on Silica Substrate.…”

Section: Coded Optical Filter For Hyperspectral Imagingmentioning

confidence: 99%

Metasurface Photodetectors

Li²,

Zhou

et al. 2021

Micromachines

View full text Add to dashboard Cite

Photodetectors are the essential building blocks of a wide range of optical systems. Typical photodetectors only convert the intensity of light electrical output signals, leaving other electromagnetic parameters, such as the frequencies, phases, and polarization states unresolved. Metasurfaces are arrays of subwavelength structures that can manipulate the amplitude, phase, frequency, and polarization state of light. When combined with photodetectors, metasurfaces can enhance the light-matter interaction at the pixel level and also enable the detector pixels to resolve more electromagnetic parameters. In this paper, we review recent research efforts in merging metasurfaces with photodetectors towards improved detection performances and advanced detection schemes. The impacts of merging metasurfaces with photodetectors, on the architecture of optical systems, and potential applications are also discussed.

show abstract

“…Metamaterial, especially its two-dimensional equivalents, i.e., metasurface, has aroused widespread attention due to its splendid electromagnetic wave manipulations properties, such as beam steering [ 1 ], radiation patterns reconfiguration [ 2 ], and nearfield transformation [ 3 ]. Plasmonic metamaterials based on metal nanocavities, exhibiting notable optical properties, including extraordinary optical transmission (EOT) [ 4 ], negative refractive index [ 5 ], and enhancement of nonlinear effect [ 6 , 7 ], has been an active research field in past decades, which provide great prospects of the application in sensing [ 8 , 9 , 10 ], plasmonic color filtering [ 11 , 12 , 13 , 14 ], and subdiffractive imaging [ 15 ], etc. Metallic nanocavity concentrates optical energy to deep subwavelength regions by the excitation of surface plasmons, inducing confinement of electromagnetic fields with frequency-selective features [ 16 , 17 ].…”

Section: Introductionmentioning

confidence: 99%

A Plasmonic Infrared Multiple-Channel Filter Based on Gold Composite Nanocavities Metasurface

Zhang

Dong

et al. 2021

Nanomaterials

View full text Add to dashboard Cite

A plasmonic near-infrared multiple-channel filter is numerically and experimentally investigated based on a gold periodic composite nanocavities metasurface. By the interference among different excited plasmonic modes on the metasurface, the multipeak extraordinary optical transmission (EOT) phenomenon is induced and utilized to realize multiple-channel filtering. Investigated from the simulated transmission spectrum of the metasurface, the positions and intensity of transmission peaks are tuned by the geometrical parameters of the metasurface and environmental refractive index. The fabricated metasurface approached transmission peaks at 1128 nm, 1245 nm, and 1362 nm, functioning as a three-passbands filter. With advantages of brief single-layer fabrication and multi-frequency selectivity, the proposed plasmonic filter has potential possibilities of integration in nano-photonic switching, detecting and biological sensing systems.

show abstract

Inverse design of metasurface optical filters using deep neural network with high degrees of freedom

Cited by 48 publications

References 39 publications

Benchmarking deep learning-based models on nanophotonic inverse design problems

Benchmarking deep learning-based models on nanophotonic inverse design problems

Metasurface Photodetectors

A Plasmonic Infrared Multiple-Channel Filter Based on Gold Composite Nanocavities Metasurface

Contact Info

Product

Resources

About