Abstract

Neural networks (NNs), random forests (RF), and extreme gradient boosting (XGBoost) are applied separately to inversely design the ring-core few-mode fiber (FMF) with a desired weakly coupled performance. We demonstrate the procedure of inverse designing of FMF via machine learning (ML) algorithms and evaluate the prediction accuracy of the above ML algorithms. Compared with RF and XGBoost, the NN performs the highest prediction accuracy. For the NN, RF, and XGBoost, the correlation coefficients of the mode effective index difference are 0.99993, 0.99857, and 0.99937, respectively. Subsequently, by utilizing the method of permuting feature importance ranking, we obtain the high-correlation fiber structural features with the mode effective index difference. Moreover, we analyze the effect of the minimum index difference between two adjacent modes $(\Delta {n_{\rm eff,min}})$ on the structural parameters and get consistent feature attribution via permuting feature importance ranking above. Finally, we design a weakly coupled ring-core fiber that supports four modes (${{\rm HE}_{11}}$, ${{\rm TE}_{01}}$, ${{\rm HE}_{21}}$, ${{\rm TM}_{01}}$) based on the NN algorithm, which could be successfully applied in vector mode division multiplexing.

© 2022 Optica Publishing Group

Machine learning aided inverse design for few-mode fiber weak-coupling optimization

Zhiqin He, Jiangbing Du, Xinyi Chen, Weihong Shen, Yuting Huang, Chang Wang, Ke Xu, and Zuyuan He
Opt. Express 28(15) 21668-21681 (2020)

Eight-mode ring-core few-mode fiber using cross-arranged different-material-filling side holes

Shuo Chen, Yue Tong, and Huiping Tian
Appl. Opt. 59(15) 4634-4641 (2020)

Active learning aided four-mode fiber design with equalized zero dispersion for short-reach MDM optical communications

Xinyi Chen, Jiangbing Du, Baining Ye, Ke Xu, and Zuyuan He
J. Opt. Soc. Am. B 39(7) 1958-1963 (2022)

Optimizing graded-index few-mode fiber for space division multiplexing

Komal Ojha, Darpan Mishra, Kumar Appaiah, and Deepak Jain
Opt. Express 31(13) 21784-21795 (2023)

Low cross talk homogeneous few-mode multi-core fiber with a suspended air-trench and V-type index core

ZengHui Li, ShuGuang Li, Ying Guo, XiaoJian Meng, Yan Wang, LuYao Wang, MengQiang Li, LiLing Ma, Peng Shuai Shao, and Chun Wang
J. Opt. Soc. Am. B 39(10) 2840-2848 (2022)