A knowledge-inherited learning for intelligent metasurface design and assembly

Yuetian Jia; Qian Qian; Zhixiang Fan; Tong Cai; Er-Ping Li; Hongsheng Chen

doi:10.1038/s41377-023-01131-19

Go to Nature Website

Your Location：

Home >

Browse articles >

A knowledge-inherited learning for intelligent metasurface design and assembly

Original Articles

- A knowledge-inherited learning for intelligent metasurface design and assembly
- Light: Science & Applications Vol. 12, Issue 4, Pages: 680-690(2023)
- Affiliations：
  
  1.ZJU-UIUC Institute, Interdisciplinary Center for Quantum Information, State Key Laboratory of Extreme Photonics and Instrumentation, Zhejiang University, Hangzhou 310027, China
  2.ZJU-Hangzhou Global Science and Technology Innovation Center, Key Lab. of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang, Zhejiang University, Hangzhou 310027, China
  3.Jinhua Institute of Zhejiang University, Zhejiang University, Jinhua 321099, China
  4.Air and Missile Defense College, Air Force Engineering University, Xi' an 710051, China
  5.Shaoxing Institute of Zhejiang University, zhejiang University, Shaoxing, 321000, China
- Author bio：
  
  Chao Qian (qianchaozju@zju.edu.cn)
  Hongsheng Chen (hansomchen@zju.edu.cn)
- Funds：
- DOI：10.1038/s41377-023-01131-19
  CLC：
- Published：30 April 2023，
  
  Published Online：30 March 2023，
  
  Received：11 November 2022，
  
  Revised：5 March 2023，
  
  Accepted：11 March 2023
Scan for full text
Jia, Y.T.et al. A knowledge-inherited learning for intelligent metasurface design and assembly.Light: Science & Applications,12, 680-690 (2023).
DOI：

Jia, Y.T.et al. A knowledge-inherited learning for intelligent metasurface design and assembly.Light: Science & Applications,12, 680-690 (2023). DOI： 10.1038/s41377-023-01131-19.

摘要

Abstract

Recent breakthroughs in deep learning have ushered in an essential tool for optics and photonics

recurring in various applications of material design

system optimization

and automation control. Deep learning-enabled on-demand metasurface design has been the subject of extensive expansion

as it can alleviate the time-consuming

low-efficiency

and experience-orientated shortcomings in conventional numerical simulations and physics-based methods. However

collecting samples and training neural networks are fundamentally confined to predefined individual metamaterials and tend to fail for large problem sizes. Inspired by object-oriented C++ programming

we propose a knowledge-inherited paradigm for multi-object and shape-unbound metasurface inverse design. Each inherited neural network carries knowledge from the "parent" metasurface and then is freely assembled to construct the "offspring" metasurface; such a process is as simple as building a container-type house. We benchmark the paradigm by the free design of aperiodic and periodic metasurfaces

with accuracies that reach 86.7%. Furthermore

we present an intelligent origami metasurface to facilitate compatible and lightweight satellite communication facilities. Our work opens up a new avenue for automatic metasurface design and leverages the assemblability to broaden the adaptability of intelligent metadevices.

关键词

Keywords

references

Jordan, M. I. & Mitchell, T. M. Machine learning: trends, perspectives, and prospects.Science349, 255–260 (2015).

Qian, C. & Chen, H. S. A perspective on the next generation of invisibility cloaks—intelligent cloaks.Appl. Phys. Lett.118, 180501 (2021).

Ma, W. et al. Deep learning for the design of photonic structures.Nat. Photonics15, 77–90 (2021).

Li, L. L. et al. Machine-learning reprogrammable metasurface imager.Nat. Commun.10, 1082 (2019).

Fan, Z. X. et al. Homeostatic neuro-metasurfaces for dynamic wireless channel management.Sci. Adv.8, eabn7905 (2022).

Yu, N. F. & Capasso, F. Flat optics with designer metasurfaces.Nat. Mater.13, 139–150 (2014).

Qian, C. et al. Experimental observation of superscattering.Phys. Rev. Lett.122, 063901 (2019).

Jia, M. et al. Efficient manipulations of circularly polarized terahertz waves with transmissive metasurfaces.Light Sci. Appl.8, 16 (2019).

Cai, T. et al. Ultrawideband chromatic aberration-free meta-mirrors.Adv. Photonics3, 016001 (2021).

Qian, C. et al. Performing optical logic operations by a diffractive neural network.Light Sci. Appl.9, 59 (2020).

Liao, K. et al. All-optical computing based on convolutional neural networks.Opto-Electron. Adv.4, 200060 (2021).

Gao, L. et al. A bidirectional deep neural network for accurate silicon color design.Adv. Mater.31, 1905467 (2019).

Mohammadi Estakhri, N., Edwards, B. & Engheta, N. Inverse-designed metastructures that solve equations.Science363, 1333–1338 (2019).

Wang, Z. D. et al. Demonstration of spider-eyes-like intelligent antennas for dynamically perceiving incoming waves.Adv. Intell. Syst.3, 2100066 (2021).

Chen, H. Y., Chan, C. T. & Sheng, P. Transformation optics and metamaterials.Nat. Mater.9, 387–396 (2010).

Cai, T. et al. High-performance bifunctional metasurfaces in transmission and reflection geometries.Adv. Opt. Mater.5, 1600506 (2017).

Jiang, J. Q. & Fan, J. A. Global optimization of dielectric metasurfaces using a physics-driven neural network.Nano Lett.19, 5366–5372 (2019).

Ren, H. R. et al. Complex-amplitude metasurface-based orbital angular momentum holography in momentum space.Nat. Nanotechnol.15, 948–955 (2020).

Wiecha, P. R. & Muskens, O. L. Deep learning meets nanophotonics: a generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures.Nano Lett.20, 329–338 (2019).

Peurifoy, J. et al. Nanophotonic particle simulation and inverse design using artificial neural networks.Sci. Adv.4, eaar4206 (2018).

Jiang, J. Q., Chen, M. K. & Fan, J. A. Deep neural networks for the evaluation and design of photonic devices.Nat. Rev. Mater.6, 679–700 (2021).

Krasikov, S. et al. Intelligent metaphotonics empowered by machine learning.Opto-Electron. Adv.5, 210147 (2022).

Qian, C. et al. Deep-learning-enabled self-adaptive microwave cloak without human intervention.Nat. Photonics14, 383–390 (2020).

Jia, Y. T. et al. In situ customized illusion enabled by global metasurface reconstruction.Adv. Funct. Mater.32, 2109331 (2022).

Fan, Z. X. et al. Transfer-learning-assisted inverse metasurface design for 30% data saving.Phys. Rev. Appl.18, 024022 (2022).

Zhu, R. C. et al. Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning.Nat. Commun.12, 2974 (2021).

Liu, Z. C. et al. Generative model for the inverse design of metasurfaces.Nano Lett.18, 6570–6576 (2018).

Zhang, J. et al. Heterogeneous transfer-learning-enabled diverse metasurface design.Adv. Opt. Mater.10, 2200748 (2022).

Chen, X. D. et al. A review of deep learning approaches for inverse scattering problems.Prog. Electromagnet. Res.167, 67–81 (2020).

Zhen, Z. et al. Realizing transmitted metasurface cloak by a tandem neural network.Photonics Res.9, B229–B235 (2021).

Cohen, J.Statistical Power Analysis for the Behavioral Sciences2nd edn. (Lawrence Erlbaum Associates, 1988).

Krieger, G., Gebert, N. & Moreira, A. Multidimensional waveform encoding: a new digital beamforming technique for synthetic aperture radar remote sensing.IEEE Trans. Geosci. Remote Sens.46, 31–46 (2008).

Qian, C. et al. Dynamic recognition and mirage using neuro-metamaterials.Nat. Commun.13, 2694 (2022).

Wainberg, M. et al. Deep learning in biomedicine.Nat. Biotechnol.36, 829–838 (2018).

Tan, Q. Z. et al. Solving multivariable equations with tandem metamaterial kernels.Prog. Electromagnet. Res.175, 139–147 (2022).

Schütt, K. T. et al. Quantum-chemical insights from deep tensor neural networks.Nat. Commun.8, 13890 (2017).

Wu, N. X. et al. Pushing the limits of metasurface cloak using global inverse design.Adv. Opt. Mater.https://doi.org/10.1002/adom.202202130https://doi.org/10.1002/adom.202202130(2023).

Tan, Q. Z., Qian, C. & Chen, H. S. Inverse-designed metamaterials for on-chip combinational optical logic circuit.Prog. Electromagnet. Res.176, 55–56 (2023).

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰