Predicting Kerr Soliton Combs in Microresonators via Deep Neural Networks

被引:12
作者
Tan, Teng [1 ,2 ]
Peng, Cheng [1 ,3 ,4 ]
Yuan, Zhongye [1 ]
Xie, Xu [10 ]
Liu, Hao [5 ]
Xie, Zhenda [6 ,7 ,8 ]
Huang, Shu-Wei [9 ]
Rao, Yunjiang [1 ,2 ]
Yao, Baicheng [1 ]
机构
[1] Univ Elect Sci & Technol China, Key Lab Opt Fiber Sensing & Commun, Educ Minist China, Chengdu 611731, Peoples R China
[2] Zhejiang Lab, Res Ctr Opt Fiber Sensing, Hangzhou 310000, Peoples R China
[3] Univ Elect Sci & Technol China, Glasgow Colleague, Chengdu 611731, Peoples R China
[4] Univ Glasgow, Sch Engn, Glasgow G12 8QQ, Lanark, Scotland
[5] Univ Calif Los Angeles, Fang Lu Mesoscop Opt & Quantum Elect Lab, Los Angeles, CA 90095 USA
[6] Nanjing Univ, Natl Lab Solid State Microstruct, Nanjing 210023, Peoples R China
[7] Nanjing Univ, Sch Phys, Sch Elect Sci & Engn, Nanjing 210023, Peoples R China
[8] Nanjing Univ, Coll Engn & Appl Sci, Nanjing 210023, Peoples R China
[9] Univ Colorado, Dept Elect Comp & Energy Engn, Boulder, CO 80309 USA
[10] Univ Calif Los Angeles, Stat Dept, UCLA Ctr Vis Cogn Learning & Anat, Los Angeles, CA USA
基金
中国国家自然科学基金;
关键词
Deep neural networks; Kerr solitons; microresonators; FREQUENCY COMBS; GENERATION;
D O I
10.1109/JLT.2020.3015586
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Formation of the Kerr soliton combs is a widely recognized important but complex issue, which relates to cross-influences among intra-cavity nonlinearities, chromatic dispersions, mode interactions, and pumping effects. Here, we propose and demonstrate a deep neural network model to predict Kerr comb spectra in silica microspheres statistically, via training their transmission spectra. Such a scheme enables soliton comb identification under a particular pump scanning, with error <8%, verified by experimental measurements. This study bridging the deep learning and the microcomb photonics, may provide a powerful and convenient tool for photonic device test and investigation.
引用
收藏
页码:6591 / 6599
页数:9
相关论文
共 48 条
[1]  
Agarap A. F., 2018, DEEP LEARNING USING, V2, P8375
[2]   Fiber laser mode locked through an evolutionary algorithm [J].
Andral, U. ;
Fodil, R. Si ;
Amrani, F. ;
Billard, F. ;
Hertz, E. ;
Grelu, P. .
OPTICA, 2015, 2 (04) :275-278
[3]   Optimization of photonic crystal nanocavities based on deep learning [J].
Asano, Takashi ;
Noda, Susumu .
OPTICS EXPRESS, 2018, 26 (25) :32704-32716
[4]   Spatial mode-interaction induced single soliton generation in microresonators [J].
Bao, Chengying ;
Xuan, Yi ;
Leaird, Daniel E. ;
Wabnitz, Stefan ;
Qi, Minghao ;
Weiner, Andrew M. .
OPTICA, 2017, 4 (09) :1011-1015
[5]   Learning to see through multimode fibers [J].
Borhani, Navid ;
Kakkava, Eirini ;
Moser, Christophe ;
Psaltis, Demetri .
OPTICA, 2018, 5 (08) :960-966
[6]   Photonic chip-based optical frequency comb using soliton Cherenkov radiation [J].
Brasch, V. ;
Geiselmann, M. ;
Herr, T. ;
Lihachev, G. ;
Pfeiffer, M. H. P. ;
Gorodetsky, M. L. ;
Kippenberg, T. J. .
SCIENCE, 2016, 351 (6271) :357-360
[7]   Reinforcement learning in a large-scale photonic recurrent neural network [J].
Bueno, J. ;
Maktoobi, S. ;
Froehly, L. ;
Fischer, I. ;
Jacquot, M. ;
Larger, L. ;
Brunner, D. .
OPTICA, 2018, 5 (06) :756-760
[8]   Biochemical sensing in graphene-enhanced microfiber resonators with individual molecule sensitivity and selectivity [J].
Cao, Zhongxu ;
Yao, Baicheng ;
Qin, Chenye ;
Yang, Run ;
Guo, Yanhong ;
Zhang, Yufeng ;
Wu, Yu ;
Bi, Lei ;
Chen, Yuanfu ;
Xie, Zhenda ;
Peng, Gangding ;
Huang, Shu-Wei ;
Wong, Chee Wei ;
Rao, Yunjiang .
LIGHT-SCIENCE & APPLICATIONS, 2019, 8 (1)
[9]   Solving the quantum many-body problem with artificial neural networks [J].
Carleo, Giuseppe ;
Troyer, Matthias .
SCIENCE, 2017, 355 (6325) :602-605
[10]   Machine Learning Phases of Strongly Correlated Fermions [J].
Ch'ng, Kelvin ;
Carrasquilla, Juan ;
Melko, Roger G. ;
Khatami, Ehsan .
PHYSICAL REVIEW X, 2017, 7 (03)