Inverse design of metamaterial structure based on AdaBelief residual neural network

FENG Kehao; LI Baiping; CAI Yijun; ZHOU Yuanguo

doi:10.7510/jgjs.issn.1001-3806.2022.03.003

LASER TECHNOLOGY > 2022 > 46(3): 307-311. > DOI: 10.7510/jgjs.issn.1001-3806.2022.03.003

FENG Kehao, LI Baiping, CAI Yijun, ZHOU Yuanguo. Inverse design of metamaterial structure based on AdaBelief residual neural network[J]. LASER TECHNOLOGY, 2022, 46(3): 307-311. DOI: 10.7510/jgjs.issn.1001-3806.2022.03.003

Citation:

PDF (3946 KB)

Inverse design of metamaterial structure based on AdaBelief residual neural network

1.
Department of Communication and Information Engineering, Xi'an University of Science and Technology, Xi'an 710000, China
2.
Departement of Optoelectronics and Communication Engineering, Xiamen University of Technology, Xiamen 361000, China

More Information

Received Date: April 05, 2021
Revised Date: July 01, 2021
Published Date: May 24, 2022

Graphical Abstract

Abstract

Abstract

In recent years, the design of metamaterial devices based on deep learning has made unprecedented development. However, for the reverse design of two-dimensional materials, it is difficult to solve the problems of falling into the local optimal value in a small sample space by using the traditional artificial neural network. Meanwhile, a lot of computational cost will be needed with the increase of the complexity of the structure. To solve these defects, a residual neural network based on AdaBelief optimization algorithm was proposed. The validity of the network was verified by choosing the design of multilayer alternating thin film structure based on graphene. The structure parameters of the multi-resonant perfect absorption spectra of samples were constructed by using the characteristic matrix method. The results show that the network model reaches 97% of prediction accuracy within a shorter training time. Compared with the prediction results of other neural networks, this network shows the advantages of high prediction accuracy and fast convergence rate, and achieves the design goal of perfect absorption metamaterial structure based on graphene.
- optical design,
- metamaterials,
- AdaBelief optimization algorithm,
- graphene

FullText(HTML)

References (20)

References

[1]	TAN T, JIANG X, WANG C, et al. 2D material optoelectronics for information functional device applications: Status and challenges[J]. Advanced Science, 2020, 7(11): 2000058. DOI: 10.1002/advs.202000058
[2]	RESERBAT-PLANTEY A, EPSTEIN I, TORRE I, et al. Quantum nano-photonics in two-dimensional materials[J]. ACS Photonics, 2021, 8(1): 85-101. DOI: 10.1021/acsphotonics.0c01224
[3]	LI X, SUN T, ZHOU K, et al. Broadband InSb/Si hetero junction photodetector with graphene transparent electrode[J]. Nanotechnology, 2020, 31(31): 315204. DOI: 10.1088/1361-6528/ab884c
[4]	STANFORD M G, ZHANG C, FOWLKES J D, et al. High-resolution laser-induced graphene. Flexible electronics beyond the visible limit[J]. ACS Applied Materials & Interfaces, 2020, 12(9): 10902-10907.
[5]	TAN T, YUAN Zh Y, CHEN Y F. Graphene-based fiber functional sensors and laser devices[J]. Laser & Optoelectronics Progress, 2019, 56(17): 170613(in Chinese).
[6]	NIU H S, ZHU L Q, LIU K M. Design method of bernal-stacked bilayer graphene 1.06μm resonance-enhanced photodetector[J]. Journal of Infrared and Millimeter Waves, 2019, 38(1): 93-98(in Chinese).
[7]	POLYCARPOU A C. Introduction to the finite element method in electromagnetics[J]. Synthesis Lectures on Computational Electromagnetics, 2005, 1(1): 1-126.
[8]	GEDNEY S D. Introduction to the finite-difference time-domain (FDTD) method for electromagnetics[J]. Synthesis Lectures on Computational Electromagnetics, 2011, 6(1): 1-250. DOI: 10.2200/S00316ED1V01Y201012CEM027
[9]	ZHAN T, SHI X, DAI Y, et al. Transfer matrix method for optics in graphene layers[J]. Journal of Physics, 2013, 25(21): 215301.
[10]	KAYA M, HAJIMIRZA S. Nonparametric design of nanoparticles with maximum scattering using evolutionary topology optimization[J]. International Journal of Heat and Mass Transfer, 2021, 166: 120738. DOI: 10.1016/j.ijheatmasstransfer.2020.120738
[11]	SONG Y, WANG F, CHEN X. An improved genetic algorithm for numerical function optimization[J]. Applied Intelligence, 2019, 49(5): 1880-1902. DOI: 10.1007/s10489-018-1370-4
[12]	KAO C Y, OSHER S, YABLONOVITCH E. Maximizing band gaps in two-dimensional photonic crystals by using level set methods[J]. Applied Physics, 2005, B81(2): 235-244.
[13]	GUAN Sh H, YANG G, LI H, et al. Hyperspectral image classification based on 3-D convolutional recurrent neural network[J]. Laser Technology, 2020, 44(4): 91-97(in Chinese).
[14]	ZHANG C P, MA Y, MAO T, et al. Leukocyte recognition oriented to computer micro-vision system[J]. Laser Technology, 2020, 44(1): 125-129(in Chinese).
[15]	MORABITO A F, IERACITANO C, MORABITO F C. A machine-learning and compressive-sensing inspired approach to the optimal array pattern synthesis[C]//2019 PhotonIcs & Electromagnetics Research Symposium-Spring (PIERS-Spring). New York, USA: IEEE, 2019: 2891-2898.
[16]	LIU D, TAN Y, KHORAM E, et al. Training deep neural networks for the inverse design of nanophotonic structures[J]. ACS Photonics, 2018, 5(4): 1365-1369. DOI: 10.1021/acsphotonics.7b01377
[17]	SEIF-DARGAHI H. Ultra-fast all-optical encoder using photonic crystal-based ring resonators[J]. Photonic Network Communications, 2018, 36(2): 272-277. DOI: 10.1007/s11107-018-0779-3
[18]	MA W, CHENG F, LIU Y. Deep-learning-enabled on-demand design of chiral metamaterials[J]. ACS Nano, 2018, 12(6): 6326-6334. DOI: 10.1021/acsnano.8b03569
[19]	BOR E, ALPARSLAN O, TURDUEV M, et al. Integrated silicon photonic device design by attractor selection mechanism based on artificial neural networks: Optical coupler and asymmetric light transmitter[J]. Optics Express, 2018, 26(22): 29032-29044. DOI: 10.1364/OE.26.029032
[20]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2016: 770-778.

[1]	CHEN Yuwei, BIAN Li'an, LIU Peiguo, WANG Jian, FAN Chongyi. Design of graphene absorber based on multilayer F-P resonator[J]. LASER TECHNOLOGY, 2023, 47(3): 317-321. DOI: 10.7510/jgjs.issn.1001-3806.2023.03.005
[2]	HU Li, XI Feng. Plasmonic Fano resonance based on the graphene nanosheet array[J]. LASER TECHNOLOGY, 2023, 47(1): 19-24. DOI: 10.7510/jgjs.issn.1001-3806.2023.01.003
[3]	LIAO Qiuyu, ZHANG Yurong, WU Zhihang, YE Ting, ZHANG Kefei. Research on topological boundary transmission state on the surface of periodic graphene disk[J]. LASER TECHNOLOGY, 2021, 45(5): 642-646. DOI: 10.7510/jgjs.issn.1001-3806.2021.05.018
[4]	JIANG Dafei, JIANG Xiaowei, FANG Xiaomin. Improve the extraction efficiency of graphene[J]. LASER TECHNOLOGY, 2021, 45(2): 186-190. DOI: 10.7510/jgjs.issn.1001-3806.2021.02.010
[5]	HE Yifan, LIU Chenchen, JIANG Qingyun, YIN Chengping. Goos-Hänchen shift in graphene-hexagonal boron nitride structure[J]. LASER TECHNOLOGY, 2020, 44(4): 424-428. DOI: 10.7510/jgjs.issn.1001-3806.2020.04.005
[6]	LIU Chundong, LÜ Ke, YANG Cheng. Method for improving stability of Raman substrates based on graphene[J]. LASER TECHNOLOGY, 2019, 43(5): 708-712. DOI: 10.7510/jgjs.issn.1001-3806.2019.05.023
[7]	WU Jijiang, GAO Jinxia. Absorption characteristics of metal-graphene photonic crystal-metal structures[J]. LASER TECHNOLOGY, 2019, 43(5): 614-618. DOI: 10.7510/jgjs.issn.1001-3806.2019.05.005
[8]	MA Rongkun, ZHANG Yichi, FANG Yuntuan. Broadband THz absorbers based on graphene and 1-D photonic crystal[J]. LASER TECHNOLOGY, 2017, 41(5): 723-727. DOI: 10.7510/jgjs.issn.1001-3806.2017.05.021
[9]	LIN Hongyi, HUANG Xiaohua, XU Yingchao, MENG Xianguo, CHENG Zaijun, SUN Dong. Research progress of graphene passively Q-switched Nd3+-doped lasers[J]. LASER TECHNOLOGY, 2016, 40(2): 259-263. DOI: 10.7510/jgjs.issn.1001-3806.2016.02.023
[10]	CHEN Yongqing, ZHANG Chentao, ZHANG Jianhuan. Simulation of temperature field of graphene substrate fabricated by laser chemical vapor deposition[J]. LASER TECHNOLOGY, 2015, 39(5): 648-653. DOI: 10.7510/jgjs.issn.1001-3806.2015.05.013

Cited By

Get Citation

PDF

XML

Article views (13) PDF downloads (12)

Turn off MathJax

Article Contents

Abstract

References

Inverse design of metamaterial structure based on AdaBelief residual neural network

Abstract

References

Related Articles

Catalog

Links：

Inverse design of metamaterial structure based on AdaBelief residual neural network

Abstract

References

Related Articles

Catalog

Links：

Export File

Citation

Format

Content