Graph Neural Networks for Metasurface Modeling

被引:8
|
作者
Khoram, Erfan [1 ]
Wu, Zhicheng [1 ]
Qu, Yurui [1 ]
Zhou, Ming [1 ]
Yu, Zongfu [1 ]
机构
[1] Univ Wisconsin Madison, Dept Elect & Comp Engn, Madison, WI 53706 USA
来源
ACS PHOTONICS | 2023年 / 10卷 / 04期
关键词
  graph neural network; inverse design; metasurface; hologram; INVERSE DESIGN; TOPOLOGY OPTIMIZATION; THERMAL EMISSION; METALENSES; RESOLUTION; PHASE;
D O I
10.1021/acsphotonics.2c01019
中图分类号
TB3 [工程材料学];
学科分类号
0805 ; 080502 ;
摘要
When using deep neural networks to model electromagnetic fields, one often needs to fix spatial sizes of problems to fit the input dimension of neural networks, which is determined during the training process. This limitation makes it difficult to use neural networks to model different metasurfaces with varying sizes, particularly when there is strong coupling between the scattering units in the metasurface. We propose a Graph Neural Networks (GNN) architecture which learns to model electromagnetic scattering, and it can be applied to metasurfaces of arbitrary sizes. Most importantly, it takes into account the coupling between scatterers. Using this approach, near-fields of metasurfaces with dimensions spanning hundreds of times the wavelength can be obtained in seconds. Our approach can also be used for the inverse design of large metasurfaces.
引用
收藏
页码:892 / 899
页数:8
相关论文
共 50 条
  • [1] Timing Macro Modeling with Graph Neural Networks
    Chang, Kevin Kai-Chun
    Chiang, Chun-Yao
    Lee, Pei-Yu
    Jiang, Iris Hui-Ru
    [J]. PROCEEDINGS OF THE 59TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC 2022, 2022, : 1219 - 1224
  • [2] Modeling IoT Equipment With Graph Neural Networks
    Zhang, Weishan
    Zhang, Yafei
    Xu, Liang
    Zhou, Jiehan
    Liu, Yan
    Guis, Mu
    Liu, Xin
    Yang, Su
    [J]. IEEE ACCESS, 2019, 7 : 32754 - 32764
  • [3] Modeling TCP Performance using Graph Neural Networks
    Jaeger, Benedikt
    Helm, Max
    Schwegmann, Lars
    Carle, Georg
    [J]. PROCEEDINGS OF THE 1ST INTERNATIONAL WORKSHOP ON GRAPH NEURAL NETWORKING, GNNET 2022, 2022, : 18 - 23
  • [4] xNet: Modeling Network Performance With Graph Neural Networks
    Huang, Sijiang
    Wei, Yunze
    Peng, Lingfeng
    Wang, Mowei
    Hui, Linbo
    Liu, Peng
    Du, Zongpeng
    Liu, Zhenhua
    Cui, Yong
    [J]. IEEE-ACM TRANSACTIONS ON NETWORKING, 2024, 32 (02) : 1753 - 1767
  • [5] Modeling ferroelectric phase transitions with graph convolutional neural networks
    Ouyang Xin-Jian
    Zhang Yan-Xing
    Wang Zhi-Long
    Zhang Feng
    Chen Wei-Jia
    Zhuang Yuan
    Jie Xiao
    Liu Lai-Jun
    Wang Da-Wei
    [J]. ACTA PHYSICA SINICA, 2024, 73 (08)
  • [6] RouteNet-Fermi: Network Modeling With Graph Neural Networks
    Ferriol-Galmes, Miquel
    Paillisse, Jordi
    Suarez-Varela, Jose
    Rusek, Krzysztof
    Xiao, Shihan
    Shi, Xiang
    Cheng, Xiangle
    Barlet-Ros, Pere
    Cabellos-Aparicio, Albert
    [J]. IEEE-ACM TRANSACTIONS ON NETWORKING, 2023, 31 (06) : 3080 - 3095
  • [7] HiPool: Modeling Long Documents Using Graph Neural Networks
    Li, Irene R.
    Feng, Aosong
    Radev, Dragomir
    Ying, Rex
    [J]. 61ST CONFERENCE OF THE THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, VOL 2, 2023, : 161 - 171
  • [8] Challenging the generalization capabilities of Graph Neural Networks for network modeling
    Suarez-Varela, Jose
    Carol-Bosch, Sergi
    Rusek, Krzysztof
    Almasan, Paul
    Arias, Marta
    Barlet-Ros, Pere
    Cabellos-Aparicio, Albert
    [J]. PROCEEDINGS OF THE 2019 ACM SIGCOMM CONFERENCE POSTERS AND DEMOS (SIGCOMM '19), 2019, : 114 - 115
  • [9] EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
    Dong, Yushun
    Liu, Ninghao
    Jalaian, Brian
    Li, Jundong
    [J]. PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22), 2022, : 1259 - 1269
  • [10] Exploring the Limitations of Current Graph Neural Networks for Network Modeling
    Happ, Martin
    Du, Jia Lei
    Herlich, Matthias
    Maier, Christian
    Dorfinger, Peter
    Suarez-Varela, Jose
    [J]. PROCEEDINGS OF THE IEEE/IFIP NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM 2022, 2022,