Abstract

A machine learning framework predicting pump powers and noise figure profile for a target distributed Raman amplifier gain profile is experimentally demonstrated. We employ a single-layer neural network to learn the mapping from the gain profiles to the pump powers and noise figures. The obtained results show highly accurate gain profile designs and noise figure predictions, with a maximum error on average of $\sim 0.3 \; {\rm dB}$. This framework provides a comprehensive characterization of the Raman amplifier and thus is a valuable tool for predicting the performance of next-generation optical communication systems, expected to employ Raman amplification.

© 2021 Optical Society of America

Inverse design of a Raman amplifier in frequency and distance domains using convolutional neural networks

Mehran Soltani, Francesco Da Ros, Andrea Carena, and Darko Zibar
Opt. Lett. 46(11) 2650-2653 (2021)

Use of machine learning to efficiently predict the confinement loss in anti-resonant hollow-core fiber

Fanchao Meng, Xiaoting Zhao, Jinmin Ding, Yingli Niu, Xinghua Zhang, Mateusz Smietana, Ryszard Buczyński, Bo Lin, Guangming Tao, Lvyun Yang, Xin Wang, Shuqin Lou, Xinzhi Sheng, and Sheng Liang
Opt. Lett. 46(6) 1454-1457 (2021)

Few-mode polymer optical waveguide amplifier for mode-division multiplexed transmission

Cheng Yu, Guijun Hu, Fei Wang, Jiaying Li, Dan Zhao, and Meiling Zhang
Opt. Lett. 46(21) 5509-5512 (2021)

Extending the L-band amplification to 1623 nm using Er/Yb/P co-doped phosphosilicate fiber

Yang Chen, Yang Lou, Zhimu Gu, Qiang Qiu, Le He, Wenzhen Li, Xiaoke Yin, Xinyue Zhao, Shaokun Liu, Jinggang Peng, Haiqing Li, Yingbin Xing, Yingbo Chu, Nengli Dai, and Jinyan Li
Opt. Lett. 46(23) 5834-5837 (2021)

Experimental validation of machine-learning based spectral-spatial power evolution shaping using Raman amplifiers

Mehran Soltani, Francesco Da Ros, Andrea Carena, and Darko Zibar
Opt. Express 30(25) 45958-45969 (2022)