Abstract

We apply an artificial neural network (ANN) of 20 hidden layers and backpropagation regression to the forecast of experimental time series from a Kerr lens mode locking (KLM) Ti:sapphire laser and a Nd:vanadate with modulation losses. In both cases the neural network is able to predict up to 10 steps ahead. In the Ti:sapphire laser the prediction in pulse amplitude is accurate even when the pulse is an extreme event. In the Nd:vanadate laser we forecast both pulse amplitude and pulse-to-pulse time separation. In both cases the prediction goes beyond the Lyapunov prediction horizon.

© 2023 Optica Publishing Group

Forecasting the chaotic dynamics of external cavity semiconductor lasers

Chao Kai, Pu Li, Yi Yang, Bingjie Wang, K. Alan Shore, and Yuncai Wang
Opt. Lett. 48(5) 1236-1239 (2023)

Machine learning-based pulse characterization in figure-eight mode-locked lasers

Alexey Kokhanovskiy, Anastasia Bednyakova, Evgeny Kuprikov, Aleksey Ivanenko, Mikhail Dyatlov, Daniil Lotkov, Sergey Kobtsev, and Sergey Turitsyn
Opt. Lett. 44(13) 3410-3413 (2019)

Predicting the dynamical behaviors for chaotic semiconductor lasers by reservoir computing

Xiao-Zhou Li, Bin Sheng, and Man Zhang
Opt. Lett. 47(11) 2822-2825 (2022)

On prediction of chaotic dynamics in semiconductor lasers by reservoir computing

Xiao-Zhou Li, Bo Yang, Shiyuan Zhao, Yiying Gu, and Mingshan Zhao
Opt. Express 31(24) 40592-40603 (2023)

32 Gb/s chaotic optical communications by deep-learning-based chaos synchronization

Junxiang Ke, Lilin Yi, Zhao Yang, Yunpeng Yang, Qunbi Zhuge, Yaping Chen, and Weisheng Hu
Opt. Lett. 44(23) 5776-5779 (2019)