Abstract

The nonlinear propagation of ultrashort pulses in optical fibers depends sensitively on the input pulse and fiber parameters. As a result, the optimization of propagation for specific applications generally requires time-consuming simulations based on the sequential integration of the generalized nonlinear Schrödinger equation (GNLSE). Here, we train a feed-forward neural network to learn the differential propagation dynamics of the GNLSE, allowing emulation of direct numerical integration of fiber propagation, and particularly the highly complex case of supercontinuum generation. Comparison with a recurrent neural network shows that the feed-forward approach yields faster training and computation, and reduced memory requirements. The approach is generic and can be extended to other physical systems.

© 2022 Optica Publishing Group

Feed-forward neural network as nonlinear dynamics integrator for supercontinuum generation: erratum

Lauri Salmela, Mathilde Hary, Mehdi Mabed, Alessandro Foi, John M. Dudley, and Goëry Genty
Opt. Lett. 47(7) 1741-1741 (2022)

Design and analysis of recurrent neural networks for ultrafast optical pulse nonlinear propagation

Gustavo R. Martins, Luís C. B. Silva, Marcelo E. V. Segatto, Helder R. O. Rocha, and Carlos E. S. Castellani
Opt. Lett. 47(21) 5489-5492 (2022)

Taming femtosecond laser filamentation and supercontinuum generation in liquids using neural networks

Panagiotis Konstantakis, Paul E. Dufour, Maria Manousidaki, Anastasios D. Koulouklidis, and Stelios Tzortzakis
Opt. Lett. 47(21) 5445-5448 (2022)

Nonlinear autoregressive with external input neural network for predicting the nonlinear dynamics of supercontinuum generation in optical fibers

Luís C. B. Silva and Marcelo E. V. Segatto
J. Opt. Soc. Am. B 40(5) 1292-1298 (2023)

Deep neural network for modeling soliton dynamics in the mode-locked laser

Yin Fang, Hao-Bin Han, Wen-Bo Bo, Wei Liu, Ben-Hai Wang, Yue-Yue Wang, and Chao-Qing Dai
Opt. Lett. 48(3) 779-782 (2023)