Artificial intelligence with metasurfaces: from intelligent design to intelligent computing

Qian Ma; Zi Rui Feng; Junming Hou; Che Liu; Yu Ming Ning; Rui Si Li; Qian Wen Wu; Yi Su Huang; Ze Gu; Jian Wei You; Tie Jun Cui

doi:10.1186/s43074-026-00239-1

journal article Open Access Apr 03, 2026

Artificial intelligence with metasurfaces: from intelligent design to intelligent computing

Qian Ma

Zi Rui Feng Junming Hou Che Liu

Yu Ming Ning Rui Si Li Qian Wen Wu Yi Su Huang Ze Gu

Jian Wei You

Tie Jun Cui

PhotoniX Vol. 7 No. 1 · Springer Science and Business Media LLC

View at Publisher Save 10.1186/s43074-026-00239-1

Abstract

Abstract
The rapid development of artificial intelligence (AI) has revolutionized traditional design and optimization approaches for metamaterials. By leveraging AI techniques, the time required for the metamaterial design process is significantly reduced, thus improving the overall efficiency. On the other hand, the advancement of AI has placed extremely high demands on computational power. In exploring high-speed and energy- efficient next-generation computing hardware, metasurface-based intelligent computing technologies such as diffractive neural networks have attracted widespread attention. In this work, we focus on two main aspects: intelligent design of metasurfaces and intelligent computing based on metasurfaces. In the field of intelligent design, we analyze how deep learning-based inverse design methods overcome the efficiency bottleneck of traditional electromagnetic simulations and enable high-precision and automated generation of subwavelength structures. In intelligent computing, we comprehensively explore the implementation mechanisms of optical diffractive neural networks and microwave programmable neural networks based on metamaterials. By comparing the application performance of physical neural networks with different architectures in scenarios such as image recognition and wireless communication, we reveal the crucial role of deep integration of the metasurfaces and AI in driving new computing paradigms, providing a theoretical framework and technological roadmap for next-generation intelligent electromagnetic systems.

Topics

No keywords indexed for this article. Browse by subject →

References

114

[1]

Grimberg R. Electromagnetic metamaterials. Mater Sci Eng B Solid-State Mater. 2013;178:1285–95. https://doi.org/10.1016/j.mseb.2013.03.022. 10.1016/j.mseb.2013.03.022

[2]

Valentine J, et al. Three-dimensional optical metamaterial with a negative refractive index. Nature. 2008;455:376–9. https://doi.org/10.1038/nature07247. 10.1038/nature07247

[3]

Ziolkowski RW. Propagation in and scattering from a matched metamaterial having a zero index of refraction. Phys Rev E. 2004;70:046608. https://doi.org/10.1103/PhysRevE.70.046608. 10.1103/physreve.70.046608

[4]

Pimenov A, Loidl A. Experimental demonstration of artificial dielectrics with a high index of refraction. Phys Rev B. 2006;74:193102. https://doi.org/10.1103/PhysRevB.74.193102. 10.1103/physrevb.74.193102

[5]

Chen BH, et al. GaN metalens for pixel-level full-color routing at visible light. Nano Lett. 2017;17:6345–52. https://doi.org/10.1021/acs.nanolett.7b03135. 10.1021/acs.nanolett.7b03135

[6]

Hsu L, Ndao A, Kanté B. Broadband and linear polarization metasurface carpet cloak in the visible. Opt Lett. 2019;44:2978–81. https://doi.org/10.1364/OL.44.002978. 10.1364/ol.44.002978

[7]

Hu J, Lang T, Shen C, Shao L. Combined Mie Resonance Metasurface for Wideband Terahertz Absorber. Appl Sci. 2018;8:1679. 10.3390/app8091679

[8]

Light Propagation with Phase Discontinuities: Generalized Laws of Reflection and Refraction

Nanfang Yu, Patrice Genevet, Mikhail A. Kats et al.

Science 2011 10.1126/science.1210713

[9]

Guo X, et al. Flexible and tunable dielectric color meta-hologram. Plasmonics. 2020;15:217–23. https://doi.org/10.1007/s11468-019-01025-5. 10.1007/s11468-019-01025-5

[10]

Coding metamaterials, digital metamaterials and programmable metamaterials

Tie Jun Cui, Mei Qing Qi, Xiang Wan et al.

Light: Science & Applications 2014 10.1038/lsa.2014.99

[11]

Cui TJ, Liu S, Bai GD, Ma Q. Direct transmission of digital message via programmable coding metasurface. Research. 2019. https://doi.org/10.34133/2019/2584509. 10.34133/2019/2584509

[12]

Dai JY, et al. Wireless Communication Based on Information Metasurfaces. IEEE Trans Microw Theory Tech. 2021;69:1493–510. https://doi.org/10.1109/TMTT.2021.3054662. 10.1109/tmtt.2021.3054662

[13]

Zhang L, et al. A wireless communication scheme based on space- and frequency-division multiplexing using digital metasurfaces. Nat Electron. 2021;4:218–27. https://doi.org/10.1038/s41928-021-00554-4. 10.1038/s41928-021-00554-4

[14]

Chen L, et al. Touch-programmable metasurface for various electromagnetic manipulations and encryptions. Small. 2022;18:2203871. https://doi.org/10.1002/smll.202203871. 10.1002/smll.202203871

[15]

Li L, et al. Intelligent metasurface imager and recognizer. Light Sci Appl. 2019;97:97. https://doi.org/10.1038/s41377-019-0209-z. 10.1038/s41377-019-0209-z

[16]

Ma Q. et al. Smart metasurface with self-adaptively reprogrammable functions. Light Sci Appl. 2019;8:98. https://doi.org/10.1038/s41377-019-0205-3. 10.1038/s41377-019-0205-3

[17]

Ma Q, et al. Directly wireless communication of human minds via non-invasive brain-computer-metasurface platform. eLight. 2022;2:11. https://doi.org/10.1186/s43593-022-00019-x. 10.1186/s43593-022-00019-x

[18]

Gao X, et al. Programmable surface plasmonic neural networks for microwave detection and processing. Nat Electron. 2023;6:319–28. https://doi.org/10.1038/s41928-023-00951-x. 10.1038/s41928-023-00951-x

[19]

Liu C, et al. A programmable diffractive deep neural network based on a digital-coding metasurface array. Nat Electron. 2022;5:113–22. https://doi.org/10.1038/s41928-022-00719-9. 10.1038/s41928-022-00719-9

[20]

Zhang Q, et al. Shaping electromagnetic waves using software-automatically-designed metasurfaces. Sci Rep. 2017;7:3588. https://doi.org/10.1038/s41598-017-03764-z. 10.1038/s41598-017-03764-z

[21]

Zhang Q, et al. Machine-learning designs of anisotropic digital coding metasurfaces. Adv Theory Simul. 2019;2:1800132. https://doi.org/10.1002/adts.201800132. 10.1002/adts.201800132

[22]

A Deep Learning Approach for Objective-Driven All-Dielectric Metasurface Design

Sensong An, Clayton Fowler, Bowen Zheng et al.

ACS Photonics 2019 10.1021/acsphotonics.9b00966

[23]

Zhu R, et al. Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning. Nat Commun. 2021;12:2974. https://doi.org/10.1038/s41467-021-23087-y. 10.1038/s41467-021-23087-y

[24]

Liu Z, Zhu D, Rodrigues SP, Lee K-T, Cai W. Generative model for the inverse design of metasurfaces. Nano Lett. 2018;18:6570–6. https://doi.org/10.1021/acs.nanolett.8b03171. 10.1021/acs.nanolett.8b03171

[25]

Malkiel I, et al. Plasmonic nanostructure design and characterization via deep learning. Light Sci Appl. 2018;7:60. https://doi.org/10.1038/s41377-018-0060-7. 10.1038/s41377-018-0060-7

[26]

Jia Y, Fan Z, Qian C, del Hougne P, Chen H. Dynamic inverse design of broadband metasurfaces with synthetical neural networks. Laser Photon Rev. 2024;18:2400063. https://doi.org/10.1002/lpor.202400063. 10.1002/lpor.202400063

[27]

Spectral transfer-learning-based metasurface design assisted by complex-valued deep neural network

Yi Xu, Fu Li, Jianqiang Gu et al.

Advanced Photonics Nexus 2024 10.1117/1.apn.3.2.026002

[28]

Wu H, Dai Q. Artificial intelligence accelerated by light. Nature. 2021;589:25–6. 10.1038/d41586-020-03572-y

[29]

All-analog photoelectronic chip for high-speed vision tasks

Yitong Chen, Maimaiti Nazhamaiti, Han Xu et al.

Nature 2023 10.1038/s41586-023-06558-8

[30]

Xu Z, et al. Large-scale photonic chiplet Taichi empowers 160-TOPS/W artificial general intelligence. Science. 2024;384:202–9. https://doi.org/10.1126/science.adl1203. 10.1126/science.adl1203

[31]

Hughes TW, W. IAD, Minkov M, Fan S. Wave physics as an analog recurrent neural network. Sci Adv. 2019;5:eaay6946. 10.1126/sciadv.aay6946

[32]

Wetzstein G, et al. Inference in artificial intelligence with deep optics and photonics. Nature. 2020;588:39–47. https://doi.org/10.1038/s41586-020-2973-6. 10.1038/s41586-020-2973-6

[33]

Feldmann J, Youngblood N, Wright CD, Bhaskaran H, Pernice WHP. All-optical spiking neurosynaptic networks with self-learning capabilities. Nature. 2019;569:208–14. https://doi.org/10.1038/s41586-019-1157-8. 10.1038/s41586-019-1157-8

[34]

Deep physical neural networks trained with backpropagation

Logan G. Wright, Tatsuhiro Onodera, Martin M. Stein et al.

Nature 2022 10.1038/s41586-021-04223-6

[35]

Wang T, et al. Image sensing with multilayer nonlinear optical neural networks. Nat Photon. 2023;17:408–15. https://doi.org/10.1038/s41566-023-01170-8. 10.1038/s41566-023-01170-8

[36]

A silicon photonic–electronic neural network for fibre nonlinearity compensation

Chaoran Huang, Shinsuke Fujisawa, Thomas Ferreira de Lima et al.

Nature Electronics 2021 10.1038/s41928-021-00661-2

[37]

Ashtiani F, Geers AJ, Aflatouni F. An on-chip photonic deep neural network for image classification. Nature. 2022;606:501–6. https://doi.org/10.1038/s41586-022-04714-0. 10.1038/s41586-022-04714-0

[38]

Shastri BJ, et al. Photonics for artificial intelligence and neuromorphic computing. Nat Photonics. 2021;15:102–14. https://doi.org/10.1038/s41566-020-00754-y. 10.1038/s41566-020-00754-y

[39]

Tiankuang Zhou, W. W., Jinzhi Zhang, Shaoliang Yu, Lu Fang. Ultrafast dynamic machine vision with spatiotemporal photonic computing. Sci Adv (2023).

[40]

Xing Lin, Y. R., Nezih T. Yardimci, Muhammed Veli, Yi Luo, Mona Jarrahi, Aydogan Ozcan. All-optical machine learning using diffractive deep neural networks. Science (2018). 10.1364/cleo_si.2019.sf1n.2

[41]

Deep learning in holography and coherent imaging

Yair Rivenson, Yichen Wu, Aydogan Ozcan

Light: Science & Applications 2019 10.1038/s41377-019-0196-0

[42]

Mengu D, Tabassum A, Jarrahi M, Ozcan A. Snapshot multispectral imaging using a diffractive optical network. Light Sci Appl. 2023;12:86. https://doi.org/10.1038/s41377-023-01135-0. 10.1038/s41377-023-01135-0

[43]

Li J, Mengu D, Yardimci NT, Luo Y, Li X, Veli M, et al. Spectrally encoded single-pixel machine vision using diffractive networks. Sci Adv. 2021;7(13):7690. 10.1126/sciadv.abd7690

[44]

Rapid sensing of hidden objects and defects using a single-pixel diffractive terahertz sensor

Jingxi Li, Xurong Li, Nezih T. Yardimci et al.

Nature Communications 2023 10.1038/s41467-023-42554-2

[45]

Li J, Gan T, Zhao Y, Bai B, Shen CY, Sun S, et al. Unidirectional imaging using deep learning–designed materials. Sci Adv. 2023;9(17):eadg1505. 10.1126/sciadv.adg1505

[46]

Design of task-specific optical systems using broadband diffractive neural networks

Yi Luo, Deniz Mengu, Nezih T. Yardimci et al.

Light: Science & Applications 2019 10.1038/s41377-019-0223-1

[47]

Duan Z, Chen H, Lin X. Optical multi-task learning using multi-wavelength diffractive deep neural networks. Nanophotonics. 2023;12:893–903. https://doi.org/10.1515/nanoph-2022-0615. 10.1515/nanoph-2022-0615

[48]

In situ optical backpropagation training of diffractive optical neural networks

Tiankuang Zhou, Lu Fang, Tao Yan et al.

Photonics Research 2020 10.1364/prj.389553

[49]

Yan T, et al. Fourier-space diffractive deep neural network. Phys Rev Lett. 2019;123:023901. https://doi.org/10.1103/PhysRevLett.123.023901. 10.1103/physrevlett.123.023901

[50]

Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit

Tiankuang Zhou, Xing Lin, Jiamin Wu et al.

Nature Photonics 2021 10.1038/s41566-021-00796-w

Showing 50 of 114 references

Metrics

0

Citations

114

References

Details

Published: Apr 03, 2026
Vol/Issue: 7(1)
License: View

Authors

Q

Qian Ma

School of Automation, Nanjing University of Science and Technology, Nanjing, China

Institute for Molecular Virology and McArdle Laboratory for Cancer Research, University of Wisconsin—Madison, Madison, Wisconsin, USA

Y

Yu Ming Ning

Institute of Electromagnetic Space Southeast University Nanjing 210096 China; State Key Laboratory of Millimeter Wave Southeast University Nanjing 210096 China

Southeast University Nanjing China

T

Tie Jun Cui

Cite This Article

Qian Ma, Zi Rui Feng, Junming Hou, et al. (2026). Artificial intelligence with metasurfaces: from intelligent design to intelligent computing. PhotoniX, 7(1). https://doi.org/10.1186/s43074-026-00239-1

Artificial intelligence with metasurfaces: from intelligent design to intelligent computing

You May Also Like