Abstract

A novel method based on deep learning technique for the modal decomposition of the optical fields emerging from the few-mode fiber is demonstrated in this paper. By combining the advantages of principal component analysis (PCA) and Back-Propagation (BP) neural network, this scheme can reveal the exact superposition of eigenmodes. Firstly, PCA algorithm is applied to preprocess the target samples to reduce the computational complexity and extract the characteristics of the samples. Then, the mapping between the mode coefficients and the preprocessed near-field beam patterns is learned by using the BP neural network. The superiority of the proposed scheme is evaluated through simulation and experiment. The results show that the scheme can perform a complete modal decomposition within a few milliseconds, and it can still work well when the SNR level is as low as 20 dB. It is also worth noting that the method described in this work also has the advantages of short network training time, non-iterative, and low experimental equipment requirements.

Learning to decompose the modes in few-mode fibers with deep convolutional neural network

Yi An, Liangjin Huang, Jun Li, Jinyong Leng, Lijia Yang, and Pu Zhou
Opt. Express 27(7) 10127-10137 (2019)

M² factor estimation in few-mode fibers based on a shallow neural network

Min Jiang, Yi An, Liangjin Huang, Jun Li, Jinyong Leng, Rongtao Su, and Pu Zhou
Opt. Express 30(15) 27304-27313 (2022)

Sub-sampled modal decomposition in few-mode fibers

Kyuhong Choi and Changsu Jun
Opt. Express 29(20) 32670-32681 (2021)

Complete modal decomposition of a few-mode fiber based on ptychography technology

Yuanyuan Liu, Qingwen Liu, Junjie Xiong, Shuangxiang Zhao, Meng Lyu, Xingchen Pan, Junyong Zhang, and Zuyuan He
Opt. Lett. 47(22) 5813-5816 (2022)

Transfer learning assisted convolutional neural networks for modulation format recognition in few-mode fibers

Xiaorong Zhu, Bo Liu, Xu Zhu, Jianxin Ren, Rahat Ullah, Yaya Mao, Xiangyu Wu, Mingye Li, Shuaidong Chen, and Yu Bai
Opt. Express 29(22) 36953-36963 (2021)