Deep Learning Neural Network Modeling Framework for Infrared Broadband Absorbers

doi:10.12422/j.issn.1006-396X.2023.06.006

Abstract

Abstract:

To reveal complex light?matter interactions, it is necessary to simplify the on?demand design of metamaterials for both forward and inverse applications. Deep learning, a popular data?driven approach, has recently alleviated to a large extent the time?consuming and empirical nature of widely used numerical simulations.A fully?connected deep neural network?based framework for inverse design and spectral prediction of broadband absorbers was proposed.The results demonstrate and validate the high accuracy of the proposed DNN model at 87.47%.The model not only outperform traditional numerical algorithms while ensuring accuracy, but also provides an important reference for on?demand design performance of metamaterials.

Key words: Inverse design problem, Graphene, Black phosphorus, Deep learning, Broadband absorption

摘要：

揭示复杂的光物质相互作用，必须简化超材料的正向和反向按需设计。近年来深度学习作为一种流行的数据驱动方法，在很大程度上缓解了数值模拟耗时长、重经验的特点。提出了一种基于全连接的深度神经网络框架实现宽带吸收器的逆向设计和光谱预测。结果表明，深度神经网络（DNN）模型的准确度为87.47%；与传统的数值算法相比，该模型不仅在确保精确度的同时获得更高的效率，而且可为超材料按需设计性能提供参考。

关键词: 逆设计问题, 石墨烯, 黑磷, 深度学习, 宽带吸收

CLC Number:

TP183

Xuan WANG, Naixing FENG, Yuxian ZHANG. Deep Learning Neural Network Modeling Framework for Infrared Broadband Absorbers[J]. Journal of Petrochemical Universities, 2023, 36(6): 57-63.

王璇, 冯乃星, 张玉贤. 用于红外宽带吸收器的深度学习网络模型框架[J]. 石油化工高等学校学报, 2023, 36(6): 57-63.

Figures/Tables 6

Fig.1 Broadband absorber structure main view top view of each layer

Table 1 Deep learning network inputs and outputs parameters

网络输入与输出	正向参数	逆向参数
输入	a₁、b₁、a₃、b₃、μ_c11、μ_c12、μ_c21、μ_c22、μ_c31、μ_c32	351个采样点组成的吸收光谱序列
输出	351个采样点组成的吸收光谱序列	a₁、b₁、a₃、b₃、μ_c11、μ_c12、μ_c21、μ_c22、μ_c31、μ_c32

Fig.2 Deep neural network model

Fig.3 Loss functions of forward design and reverse design

Table 2 Forward model similarity assessment

相关系数	数值/%
余弦相似度	99.075 256
皮尔逊相关系数	97.739 989
肯德尔相关系数	82.327 078

Fig.4 Comparison of absorbance and reflectance curves obtained after modeling framework for two different sets of structural body parameters

References 33

1	ASHTON M，PAUL J，SINNOTT S B，et al.Topology⁃scaling identification of layered solids and stable exfoliated 2D materials［J］.Physical Review Letters，2017，118（10）：106101.
2	LIU G P，JIN W Q，XU N P.Two⁃dimensional⁃material membranes：A new family of high⁃performance separation membranes［J］.Angewandte Chemie International Edition，2016，55（43）：13384⁃13397.
3	CAO Y，FATEMI V，FANG S A，et al.Unconventional superconductivity in magic⁃angle graphene superlattices［J］.Nature，2018，556（7699）：43⁃50.
4	ROLDÁN R，CASTELLANOS⁃GOMEZ A，CAPPELLUTI E，et al.Strain engineering in semiconducting two⁃dimensional crystals［J］.Journal of Physics：Condensed Matter，2015，27（31）：313201.
5	BURCH K S，MANDRUS D，PARK J G.Magnetism in two⁃dimensional van der Waals materials［J］.Nature，2018，563（7729）：47⁃52.
6	XIE Y N，LIU X Y，LI F J，et al.Ultra⁃wideband enhancement on mid⁃infrared fingerprint sensing for 2D materials and analytes of monolayers by a metagrating［J］.Nanophotonics，2020，9（9）：2927⁃2935.
7	SCHWIERZ F，PEZOLDT J，GRANZNER R.Two⁃dimensional materials and their prospects in transistor electronics［J］.Nanoscale，2015，7（18）：8261⁃8283.
8	NOVOSELOV K S，GEIM A K，MOROZOV S V，et al.Electric field effect in atomically thin carbon films［J］.Science，2004，306（5696）：666⁃669.
9	WANG Y，MAO J，MENG X A，et al.Catalysis with two⁃dimensional materials confining single atoms：Concept，design，and applications［J］.Chemical Reviews，2019，119（3）：1806⁃1854.
10	BONACCORSO F，SUN Z，HASAN T，et al.Graphene photonics and optoelectronics［J］.Nature Photonics，2010，4（9）：611⁃622.
11	LIU X Z，GALFSKY T，SUN Z，et al.Strong light⁃matter coupling in two⁃dimensional atomic crystals［J］.Nature Photonics，2015，9（1）：30⁃34.
12	REN T X，CHEN L.Slow light enabled high⁃modulation⁃depth graphene modulator with plasmonic metasurfaces［J］.Optics Letters，2019，44（22）：5446⁃5449.
13	ZHANG T，LIU Q，DAN Y H，et al.Machine learning and evolutionary algorithm studies of graphene metamaterials for optimized plasmon⁃induced transparency［J］.Optics Express，2020，28（13）：18899⁃18916.
14	RODRIGO D，LIMAJ O，JANNER D，et al.Mid⁃infrared plasmonic biosensing with graphene［J］.Science，2015，349（6244）：165⁃168.
15	MUELLER T，XIA F N，AVOURIS P.Graphene photodetectors for high⁃speed optical communications［J］.Nature Photonics，2010，4（5）：297⁃301.
16	HU G H，KANG J，NG L W T，et al.Functional inks and printing of two⁃dimensional materials［J］.Chemical Society Reviews，2018，47（9）：3265⁃3300.
17	XIANG D，HAN C，WU J，et al.Surface transfer doping induced effective modulation on ambipolar characteristics of few⁃layer black phosphorus［J］.Nature Communications，2015，6：6485.
18	HUANG M Q，WANG M L，CHEN C，et al.Broadband black⁃phosphorus photodetectors with high responsivity［J］.Advanced Materials，2016，28（18）：3481⁃3485.
19	ABBAS A N，LIU B L，CHEN L，et al.Black phosphorus gas sensors［J］.ACS Nano，2015，9（5）：5618⁃5624.
20	LI L K，YU Y J，YE G J，et al.Black phosphorus field⁃effect transistors［J］.Nature Nanotechnology，2014，9（5）：372⁃377.
21	DAI J，ZENG X C.Bilayer phosphorene：Effect of stacking order on bandgap and its potential applications in thin⁃film solar cells［J］.The Journal of Physical Chemistry Letters，2014，5（7）：1289⁃1293.
22	QIAO J S，KONG X H，HU Z X，et al.High⁃mobility transport anisotropy and linear dichroism in few⁃layer black phosphorus［J］.Nature Communications，2014，5（1）：4475.
23	HIGASHITARUMIZU N，UDDIN S Z，WEINBERG D，et al.Anomalous thickness dependence of photoluminescence quantum yield in black phosphorous［J］.Nature Nanotechnology，2023，18（5）：507⁃513.
24	QIU T S，SHI X，WANG J F，et al.Deep learning：A rapid and efficient route to automatic metasurface design［J］.Advanced Science，2019，6（12）：1900128.
25	PEURIFOY J，SHEN Y C，JING L，et al.Nanophotonic particle simulation and inverse design using artificial neural networks［J］.Science Advances，2018，4（6）：eaar4206.
26	KOZIEL S，ABDULLAH M.Machine⁃learning⁃powered EM⁃based framework for efficient and reliable design of low scattering metasurfaces［J］.IEEE Transactions on Microwave Theory and Techniques，2021，69（4）：2028⁃2041.
27	RODRIGUEZ J A，ABDALLA A I，WANG B，et al.Inverse design of plasma metamaterial devices for optical computing［J］.Physical Review Applied，2021，16（1）：014023.
28	HE W B，TONG M Y，XU Z J，et al.Ultrafast all⁃optical terahertz modulation based on an inverse⁃designed metasurface［J］.Photonics Research，2021，9（6）：1099.
29	YUAN L，WANG L，YANG X S，et al.An efficient artificial neural network model for inverse design of metasurfaces［J］.IEEE Antennas and Wireless Propagation Letters，2021，20（6）：1013⁃1017.
30	CEN C L，YI Z，ZHANG G F，et al.Theoretical design of a triple⁃band perfect metamaterial absorber in the THz frequency range［J］.Results in Physics，2019，14：102463.
31	CAI Y J，XU K D，FENG N X，et al.Anisotropic infrared plasmonic broadband absorber based on graphene⁃black phosphorus multilayers［J］.Optics Express，2019，27（3）：3101⁃3112.
32	SENSALE⁃RODRIGUEZ B，YAN R S，KELLY M M，et al.Broadband graphene terahertz modulators enabled by intraband transitions［J］.Nature Communications，2012，3（1）：780.
33	MUKAKA M M.Statistics corner：A guide to appropriate use of correlation coefficient in medical research［J］.Malawi Medical Journal，2012，24（3）：69⁃71.

[1]	Sai YE, Weiwei JIAN, Shuai WANG, Zaiyuan ZHANG. Kinetic Characteristics of Metal Supported Graphene Oxide on CO₂ Hydrate Formation [J]. Journal of Petrochemical Universities, 2024, 37(1): 25-33.
[2]	Honglin LI, Yuling YAN, Lihua LI. Performance Studies of Nano⁃GO⁃ZnO / CeO₂ Composite Particles in Water⁃Based Polyurethane Coatings [J]. Journal of Petrochemical Universities, 2024, 37(1): 66-73.
[3]	Jiaming SUN, Dongyang CHEN, Haonan CHEN, Zhaoru CHEN, Xiaoxu LIU. Research Progress of Graphene/Polyimide Nanocomposites [J]. Journal of Petrochemical Universities, 2023, 36(6): 1-12.
[4]	Munan TAO, Wenhui GU, Tifeng JIAO. Preparation Technology and Application Progress of Graphene Oxide Based Composite Thin Film Materials [J]. Journal of Petrochemical Universities, 2023, 36(6): 13-23.
[5]	Dawei SHENG, DIN HASEEB UD, Jiyuan ZHANG, Xiaoxu LIU. Study on Microstructure Regulation and Sodium Storage Performance of Reduced Graphene Oxide [J]. Journal of Petrochemical Universities, 2023, 36(6): 48-56.
[6]	Liuyang HE, Xiaojie LI, Chan WANG, Chunyang DUAN. Effect of Graphene Doping on Electrochemical Performance of Cathode Materials of Ternary Sodium⁃Ion Batteries [J]. Journal of Petrochemical Universities, 2023, 36(6): 64-72.
[7]	Zhiyuan YANG, Yi ZOU, Jingang WANG. One and Two⁃Photon Absorption Properties of Twist Bilayer Graphene Nanosheets [J]. Journal of Petrochemical Universities, 2023, 36(6): 73-82.
[8]	Lianjing Feng, Lijuan Wang. Applications of Sn₄P₃⁃G@C Anodes in Li⁃ion Batteries [J]. Journal of Petrochemical Universities, 2023, 36(1): 66-73.
[9]	Mengyao Tang, Tianyi Sun, Jiashu Li, Yan Ding, Jinlong Li. Molecular Simulation of Hydrogen Adsorption Performance in Graphene and Carbon Nanotubes [J]. Journal of Petrochemical Universities, 2022, 35(4): 10-17.
[10]	Jiahui Chen, Honglin Li, Zikun Yang, Hongxian Luo, Jinsheng Zhang, Lihua Li. Preparation of GO⁃Modified Cerium⁃Based Nano⁃Composite Photocatalyst and a Comparative Study on Photocatalytic Properties [J]. Journal of Petrochemical Universities, 2022, 35(1): 63-67.
[11]	Wang Yiming， Huang Wei， Cong Yufeng. A Novel GO/MoS₂ Composite Electrode： Preparation and Application in Pb(II) Adsorption [J]. Journal of Petrochemical Universities, 2021, 34(1): 28-33.
[12]	Zhu Zhou,Zhan Guohua, Zhang Bin,Zhao Jian. Effect of GO on Viscosity Behavior of HPAM [J]. Journal of Petrochemical Universities, 2015, 28(4): 31-34.