Abstract
We propose efficient modelling of optical fiber channel via NLSE-constrained physics-informed neural operator without reference solutions. This method can be easily scalable for distance, sequence length, launch power, and signal formats, and is implemented for ultra-fast simulations of 16-QAM signal transmission with ASE noise.
© 2022 The Author(s)
PDF ArticleMore Like This
Yuchen Song, Xiaotian Jiang, Xiao Luo, Ximeng Zhang, Min Zhang, and Danshi Wang
M2F.5 Optical Fiber Communication Conference (OFC) 2023
Xingchen He, Lianshan Yan, Lin Jiang, Anlin Yi, Zhengyu Pu, Youren Yu, Wei Pan, and Bin Luo
SM4J.6 CLEO: Science and Innovations (CLEO:S&I) 2022
Qizhi Qiu, Huazhi Lun, Xiaomin Liu, Lilin Yi, Weisheng Hu, and Qunbi Zhuge
We3B.2 European Conference and Exhibition on Optical Communication (ECOC) 2022