Machine-learning-powered efficient design of photonic crystal cavities

Li Liu; Yangcan Long

doi:10.1186/s43074-025-00201-7

Article Contents

Article Navigation > PhotoniX > > Accepted Manuscript

Li Liu, Yangcan Long. Machine-learning-powered efficient design of photonic crystal cavities[J]. PhotoniX. doi: 10.1186/s43074-025-00201-7

Citation:

Li Liu, Yangcan Long. Machine-learning-powered efficient design of photonic crystal cavities[J]. PhotoniX. doi: 10.1186/s43074-025-00201-7

Li Liu, Yangcan Long. Machine-learning-powered efficient design of photonic crystal cavities[J]. PhotoniX. doi: 10.1186/s43074-025-00201-7

Citation:

Li Liu, Yangcan Long. Machine-learning-powered efficient design of photonic crystal cavities[J]. PhotoniX. doi: 10.1186/s43074-025-00201-7

PDF( 3038 KB)

Machine-learning-powered efficient design of photonic crystal cavities

doi: 10.1186/s43074-025-00201-7

Li Liu^{1, 2, 3},
Yangcan Long^{1, 4, 5}

1.
School of Automation, China University of Geosciences, Wuhan, 430074, China
2.
State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, 710071, China
3.
State Key Laboratory of Materials for Integrated Circuits, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, 865 Changning Road, Shanghai, 200050, China
4.
Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems, Wuhan, 430074, China
5.
Engineering Research Center of Intelligent Technology for Geo-Exploration, Ministry of Education, Wuhan, 430074, China

Funds: This work is supported by the National Natural Science Foundation of China (Grant No. 62175220), Open Research Fund of State Key Laboratory of Materials for Integrated Circuits (Grant No. SKLJC-K2025-07), and the Fundamental Research Funds for the Central Universities (Grant No. G1323525012).

Received Date: 2025-01-21
Accepted Date: 2025-09-20
Rev Recd Date: 2025-08-18

Available Online: 2025-10-07

Abstract

Abstract

While machine learning holds remarkable potential for designing high-quality (Q) photonic crystal (PC) cavities, its effectiveness heavily relies on the availability of thousands of data samples. This requirement necessitates substantial simulation resources and considerable time. To tackle the challenge of data scarcity in high-Q microcavity designs, we propose an innovative intelligent model for efficient data augmentation that entails merely a few hundred original samples. Notably, our novel structural reshaping strategy, involving the groundbreaking Euler-bend air-hole structure, significantly enhances the fabrication robustness, addressing the consistency difficulty associated with large-scale manufacturing of high-Q PC microcavity arrays. Silicon PC nanobeam cavities are experimentally demonstrated, featuring record-breaking loaded Q factors, large tolerance for the Euler-bend holes and extremely compact sizes of 6 μm². Importantly, to emphasize the on-chip high-resolution signal processing, the cavity-based microwave photonic filters (MPFs) offer unprecedented capabilities, including ultra-narrow bandwidths, an unlimited frequency tuning range and ultra-high rejection ratios using a micrometer-scale cavity. This breakthrough truly transcends the traditional limitations between the filter size, frequency resolution and tuning range. These exceptional characteristics position our MPFs with a cavity-based record-breaking Q_MPF/S ratio (S: device size).
- Engineering",
- High-Q photonic crystal nanobeam cavity')">" data-track="click" data-track-action="view keyword" data-track-label="link">High-Q photonic crystal nanobeam cavity,
- Engineering",
- Data augmentation model')">" data-track="click" data-track-action="view keyword" data-track-label="link">Data augmentation model,
- Engineering",
- Euler-bend air hole')">" data-track="click" data-track-action="view keyword" data-track-label="link">Euler-bend air hole,
- Engineering",
- High design efficiency')">" data-track="click" data-track-action="view keyword" data-track-label="link">High design efficiency,
- Engineering",
- Exceptional tolerance')">" data-track="click" data-track-action="view keyword" data-track-label="link">Exceptional tolerance

FullText(HTML)

References(77)

References

[1]	Tang R, Sun C, Bao K, Chen Z, Ju Z, et al. High-resolution 2D quasi-distributed optical sensing with on-chip multiplexed FSR-free nanobeam cavity array. Laser Photon Rev. 2024;18:2300828.
[2]	Dong P, Zhang L, Dai D, Shi Y. All-optical switching of silicon nanobeam cavities with an ultra-compact heater utilizing the photothermal effect. ACS Photonics. 2021;9:197–202.
[3]	Liang H, Luo R, He Y, Jiang H, Lin Q. High-quality lithium niobate photonic crystal nanocavities. Optica. 2017;4:1251–8.
[4]	Ding SW, Haas M, Guo X, Kuruma K, Jin C, et al. High-Q cavity interface for color centers in thin film diamond. Nat Commun. 2024;15:6358.
[5]	Asano T, Ochi Y, Takahashi Y, Kishimoto K, Noda S. Photonic crystal nanocavity with a Q factor exceeding eleven million. Opt Express. 2017;25:1769–77.
[6]	Maeno K, Takahashi Y, Nakamura T, Asano T, Noda S. Analysis of high-Q photonic crystal L3 nanocavities designed by visualization of the leaky components. Opt Express. 2017;25:367–76.
[7]	Yamamoto T, Pashkin YA, Astafiev O, Nakamura Y, Tsai JS. Demonstration of conditional gate operation using superconducting charge qubits. Nature. 2003;425:941–4.
[8]	Yang DQ, Kita S, Liang F, Wang C, Tian HP, et al. High sensitivity and high Q-factor nanoslotted parallel quadrabeam photonic crystal cavity for real-time and label-free sensing. Appl Phys Lett. 2014;105:063118.
[9]	Huang L, Zhou J, Sun F, Fu Z, Tian H. Optimization of one dimensional photonic crystal elliptical-hole low-index mode nanobeam cavities for on-chip sensing. J Lightwave Technol. 2016;34:3496–502.
[10]	Zhang J, Cheng Z, Dong J, Zhang X. Cascaded nanobeam spectrometer with high resolution and scalability. Optica. 2022;9:517–21.
[11]	Cheng Z, Zhao Y, Zhang J, Zhou H, Gao D, et al. Generalized modular spectrometers combining a compact nanobeam microcavity and computational reconstruction. ACS Photonics. 2021;9:74–81.
[12]	Lee P-T, Lu T-W, Chiu L-H. Dielectric-band photonic crystal nanobeam lasers. J Lightwave Technol. 2013;31:36–42.
[13]	Deotare PB, Mahony TS, Bulovic V. Ultracompact low-threshold organic laser. ACS Nano. 2014;8:11080–5.
[14]	Li M, Ling J, He Y, Javid UA, Xue S, et al. Lithium niobate photonic-crystal electro-optic modulator. Nat Commun. 2020;11:4123.
[15]	Zhang J, Leroux X, Durán-Valdeiglesias E, Alonso-Ramos C, Marris-Morini D, et al. Generating fano resonances in a single-waveguide silicon nanobeam cavity for efficient electro-optical modulation. ACS Photonics. 2018;5:4229–37.
[16]	Liu L, Ye M, Yu Z, Xue W. Notch microwave photonic filter with narrow bandwidth and ultra-high all-optical tuning efficiency based on a silicon nanobeam cavity. J Lightwave Technol. 2023;41:5051–8.
[17]	Zhao Y, Chen LH, Wang XH. Tuning the coupling between quantum dot and microdisk with photonic crystal nanobeam cavity. Opt Express. 2019;27:20211–20.
[18]	Fink JM, Kalaee M, Norte R, Pitanti A, Painter O. Efficient microwave frequency conversion mediated by a photonics compatible silicon nitride nanobeam oscillator. Quantum Sci Technol. 2020;5:034011.
[19]	Fegadolli WS, Oliveira JE, Almeida VR, Scherer A. Compact and low power consumption tunable photonic crystal nanobeam cavity. Opt Express. 2013;21:3861–71.
[20]	Zhong T, Rochman J, Kindem JM, Miyazono E, Faraon A. High quality factor nanophotonic resonators in bulk rare-earth doped crystals. Opt Express. 2016;24:536–44.
[21]	Yang D, Wang B, Chen X, Wang C, Ji Y. Ultracompact on-chip multiplexed sensor array based on dense integration of flexible 1-D photonic crystal nanobeam cavity with large free spectral range and high Q-factor. IEEE Photonics J. 2017;9:1–12.
[22]	Sun F, Li Z, Tang B, Li B, Zhang P, et al. Scalable high Q-factor fano resonance from air-mode photonic crystal nanobeam cavity. Nanophotonics. 2023;12:3135–48.
[23]	Md Zain AR, Johnson NP, Sorel M, De La Rue RM. Ultra high quality factor one dimensional photonic crystal/photonic wire micro-cavities in silicon-on-insulator (SOI). Opt Express. 2008;16:12084–9.
[24]	Liang F, Quan Q. Detecting single gold nanoparticles (1.8 nm) with ultrahigh-Q air-mode photonic crystal nanobeam cavities. ACS Photon. 2015;2:1692–7.
[25]	Deotare PB, McCutcheon MW, Frank IW, Khan M, Lončar M. High quality factor photonic crystal nanobeam cavities. Appl Phys Lett. 2009;94:121106.
[26]	Shibata T, Asano T, Noda S. Fabrication and characterization of an L3 nanocavity designed by an iterative machine-learning method. APL Photon. 2021;6:036113.
[27]	Asano T, Noda S. Iterative optimization of photonic crystal nanocavity designs by using deep neural networks. Nanophotonics. 2019;8:2243–56.
[28]	Li R, Gu X, Li K, Huang Y, Li Z, et al. Deep learning-based modeling of photonic crystal nanocavities. Opt Mater Express. 2021;11:2122–33.
[29]	Singh R, Agarwal A, W Anthony B. Mapping the design space of photonic topological states via deep learning. Opt Express. 2020;28:27893–902.
[30]	Zhang W, Wu B, Gu W, Cheng J, Zhou H, et al. Large-scale optical programmable logic array for two-dimensional cellular automaton. Adv Photon. 2024;6:056007.
[31]	Cheng J, Huang C, Zhang J, Wu B, Zhang W, et al. Multimodal deep learning using on-chip diffractive optics with in situ training capability. Nat Commun. 2024;15:6189.
[32]	Huang L, Jin R, Zhou C, Li G, Xu L, et al. Ultrahigh-Q guided mode resonances in an all-dielectric metasurface. Nat Commun. 2023;14:3433.
[33]	Akahane Y, Asano T, Song BS, Noda S. Fine-tuned high-Q photonic-crystal nanocavity. Opt Express. 2005;13:1202–14.
[34]	Lalanne P, Hugonin JP. Bloch-wave engineering for high-Q, small-V microcavities. IEEE J Quantum Electron. 2003;39:1430–8.
[35]	Palamaru M, Lalanne P. Photonic crystal waveguides: out-of-plane losses and adiabatic modal conversion. Appl Phys Lett. 2001;78:1466–8.
[36]	Hryciw AC, Barclay PE. Optical design of split-beam photonic crystal nanocavities. Opt Lett. 2013;38:1612–4.
[37]	Zhao S, Yue X, Zhang S, Li B, Zhao H, et al. A review of single-source deep unsupervised visual domain adaptation. IEEE Trans Neural Netw Learn Syst. 2022;33:473–93.
[38]	Ma T, Tobah M, Wang H, Guo LJ. Benchmarking deep learning-based models on nanophotonic inverse design problems. Opto-Electron Sci. 2022;1:210012.
[39]	Liu L, Ma CG, Ye MY, Yu ZH, Xue W, et al. Photonic crystal nanobeam cavity with a high experimental Q factor exceeding two million based on machine learning. J Lightwave Technol. 2022;40:7150–8.
[40]	Kar AK. Bio inspired computing – a review of algorithms and scope of applications. Expert Syst Appl. 2016;59:20–32.
[41]	Quan Q, Deotare PB, Loncar M. Photonic crystal nanobeam cavity strongly coupled to the feeding waveguide. Appl Phys Lett. 2010;96:203102.
[42]	Nijem J, Naiman A, Zektzer R, Frydendahl C, Mazurski N, et al. High-Q and high finesse silicon microring resonator. Opt Express. 2024;32:7896–906.
[43]	Wang Y, Zhang N, Jiang Z, Wang L, Xiao Y, et al. Chip-scale mass manufacturable high-Q silicon microdisks. Adv Mater Technol. 2017;2:1600299.
[44]	Zhang N, Wang Y, Sun W, Liu S, Huang C, et al. High-Q and highly reproducible microdisks and microlasers. Nanoscale. 2018;10:2045–51.
[45]	Shi W, Yun H, Zhang W, Lin C, Chang TK, et al. Ultra-compact, high-Q silicon microdisk reflectors. Opt Express. 2012;20:21840–6.
[46]	Zhang W, Yao J. Silicon-based single-mode on-chip ultracompact microdisk resonators with standard silicon photonics foundry process. J Lightwave Technol. 2017;35:4418–24.
[47]	Manipatruni S, Preston K, Chen L, Lipson M. Ultra-low voltage, ultra-small mode volume silicon microring modulator. Opt Express. 2010;18:18235–42.
[48]	Yu P, Qiu H, Yu H, Wu F, Wang Z, et al. High-Q and high-order side-coupled air-mode nanobeam photonic crystal cavities in silicon. IEEE Photon Technol Lett. 2016;28:2121–4.
[49]	Yao K, Shi Y. High-Q width modulated photonic crystal stack mode-gap cavity and its application to refractive index sensing. Opt Express. 2012;20:27039–44.
[50]	Deotare PB, McCutcheon MW, Frank IW, Khan M, Lončar M. Coupled photonic crystal nanobeam cavities. Appl Phys Lett. 2009;95:031102.
[51]	Li X, Wang J, Yu F, Chen J, Chen X, et al. Nonlinear memristive computational spectrometer. Light Sci Appl. 2025;14:47.
[52]	Zhou C, Zhou M, Fu Z, He H, Deng ZL, et al. Ultrahigh-Q quasi-BICs via precision-controlled asymmetry in dielectric metasurfaces. Nano Lett. 2025;25:5916–24.
[53]	Jin R, Huang L, Zhou C, Guo J, Fu Z, et al. Toroidal dipole BIC-driven highly robust perfect absorption with a graphene-loaded metasurface. Nano Lett. 2023;23:9105–13.
[54]	Sekoguchi H, Takahashi Y, Asano T, Noda S. Photonic crystal nanocavity with a Q-factor of ~9 million. Opt Express. 2014;22:916–24.
[55]	Rasras MS, Kun-Yii T, Gill DM, Young-Kai C, White AE, et al. Demonstration of a tunable microwave-photonic notch filter using low-loss silicon ring resonators. J Lightwave Technol. 2009;27:2105–10.
[56]	Liu L, Yang T, Dong J-J. Microwave photonic filter with a continuously tunable central frequency using an SOI high-Q microdisk resonator. Chin Phys B. 2014;23:093201.
[57]	Zhang L, Hong S, Wang Y, Yan H, Xie Y, et al. Ultralow-loss silicon photonics beyond the singlemode regime. Laser Photon Rev. 2022;16:2100292.
[58]	Liu L, Liao S. Ultra-high peak rejection, sub-gigahertz narrowband and bandwidth tunable microwave photonic filter based on silicon racetrack resonators. J Lightwave Technol. 2023;41:5820–6.
[59]	Liu L, Yu Z. Low error and broadband microwave frequency measurement using a silicon Mach-Zehnder interferometer coupled ring array. J Lightwave Technol. 2023;41:6126–33.
[60]	Liu L, Ye M, Xue W. Silicon-on-insulator-based narrowband microwave photonic filter with widely tunable bandwidth. J Lightwave Technol. 2023;41:6341–7.
[61]	Tao Y, Shu H, Wang X, Jin M, Tao Z, et al. Hybrid-integrated high-performance microwave photonic filter with switchable response. Photon Res. 2021;9:1569–80.
[62]	Liu L, Chen C, Hu C, Zhao P. Narrow passband tunable optical filter based on silicon high-Q rings assisted MZI structure. J Lightwave Technol. 2024;42:2049–56.
[63]	Liu L, Liao S. Si₃n₄-based narrowband and high peak rejection microwave photonic filter with adjustable bandwidth. J Lightwave Technol. 2024;42:1580–5.
[64]	Liu L, Liao S. Low-power active tunable microwave photonic filter using photonic crystal nanocavities. IEEE Photon Technol Lett. 2020;32:999–1002.
[65]	Liu X, Yu Y, Tang H, Xu L, Dong J, et al. Silicon-on-insulator-based microwave photonic filter with narrowband and ultrahigh peak rejection. Opt Lett. 2018;43:1359–62.
[66]	Sancho J, Bourderionnet J, Lloret J, Combrie S, Gasulla I, et al. Integrable microwave filter based on a photonic crystal delay line. Nat Commun. 2012;3:1075.
[67]	Marpaung D, Morrison B, Pant R, Roeloffzen C, Leinse A, et al. Si₃N₄ ring resonator-based microwave photonic notch filter with an ultrahigh peak rejection. Opt Express. 2013;21:23286–94.
[68]	Liu Y, Choudhary A, Ren G, Vu K, Morrison B, et al. Integration of Brillouin and passive circuits for enhanced radio-frequency photonic filtering. APL Photon. 2019;4:106103.
[69]	Daulay O, Liu G, Ye K, Botter R, Klaver Y, et al. Ultrahigh dynamic range and low noise figure programmable integrated microwave photonic filter. Nat Commun. 2022;13:7798.
[70]	Liu Y, Hotten J, Choudhary A, Eggleton BJ, Marpaung D. All-optimized integrated RF photonic notch filter. Opt Lett. 2017;42:4631–4.
[71]	Liu L, Long Y, Fu K, Zhao P, Hu C. High-Q silicon photonic crystal ring resonator based on machine learning. J Lightwave Technol. 2025;43:674–83.
[72]	Liu D, Tan Y, Khoram E, Yu Z. Training deep neural networks for the inverse design of nanophotonic structures. ACS Photonics. 2018;5:1365–9.
[73]	Asano T, Noda S. Optimization of photonic crystal nanocavities based on deep learning. Opt Express. 2018;26:32704–16.
[74]	Unni R, Yao K, Zheng Y. Deep convolutional mixture density network for inverse design of layered photonic structures. ACS Photonics. 2020;7:2703–12.
[75]	Sajedian I, Kim J, Rho J. Finding the optical properties of plasmonic structures by image processing using a combination of convolutional neural networks and recurrent neural networks. Microsyst Nanoeng. 2019;5:27.
[76]	Gao W, Lu L, Zhou L, Chen J. Automatic calibration of silicon ring-based optical switch powered by machine learning. Opt Express. 2020;28:10438–55.
[77]	Wang J, Chen J, Yu F, Chen R, Wang J, et al. Unlocking ultra-high holographic information capacity through nonorthogonal polarization multiplexing. Nat Commun. 2024;15:6284.