Abstract

To reduce the atmospheric turbulence-induced power loss, an AlexNet-based convolutional neural network (CNN) for wavefront aberration compensation is experimentally investigated for free-space optical (FSO) communication systems with standard single mode fiber-pigtailed photodiodes. The wavefront aberration is statistically constructed to mimic the received light beams with the Zernike mode-based theory for the Kolmogorov turbulence. By analyzing impacts of CNN structures, quantization resolution/noise, and mode count on the power penalty, the AlexNet-based CNN with 8 bit resolution is identified for experimental study. Experimental results indicate that the average power penalty decreases to 1.8 dB from 12.4 dB in the strong turbulence.

© 2021 Chinese Laser Press

Jointly recognizing OAM mode and compensating wavefront distortion using one convolutional neural network

Chenda Lu, Qinghua Tian, Xiangjun Xin, Bo Liu, Qi Zhang, Yongjun Wang, Feng Tian, Leijing Yang, and Ran Gao
Opt. Express 28(25) 37936-37945 (2020)

Nonlinear wavefront reconstruction with convolutional neural networks for Fourier-based wavefront sensors

R. Landman and S. Y. Haffert
Opt. Express 28(11) 16644-16657 (2020)

Predicting the orbital angular momentum of atmospheric turbulence for OAM-based free-space optical communication

Wuli Hu, Jiaxiong Yang, Long Zhu, and Andong Wang
Opt. Express 31(25) 41060-41071 (2023)

Turbulence aberration correction for vector vortex beams using deep neural networks on experimental data

Yanwang Zhai, Shiyao Fu, Jianqiang Zhang, Xueting Liu, Heng Zhou, and Chunqing Gao
Opt. Express 28(5) 7515-7527 (2020)

Prediction of wavefront distortion for wavefront sensorless adaptive optics based on deep learning

Yushuang Li, Dan Yue, and Yihao He
Appl. Opt. 61(14) 4168-4176 (2022)