Artificial neural networks for nonlinear pulse shaping in optical fibers

We use a supervised machine-learning model based on a neural network to predict the temporal and spectral intensity profiles of the pulses that form upon nonlinear propagation in optical fibers with both normal and anomalous second-order dispersion. We also show that the model is able to retrieve the parameters of the nonlinear propagation from the pulses observed at the output of the fiber. Various initial pulse shapes as well as initially chirped pulses are investigated.

[1]  C. Finot,et al.  Pulse doubling and wavelength conversion through triangular nonlinear pulse reshaping , 2011 .

[2]  Mietek Lisak,et al.  Wave breaking in nonlinear-optical fibers , 1992 .

[3]  Govind P. Agrawal,et al.  Nonlinear Fiber Optics , 1989 .

[4]  Christophe Finot,et al.  Shaping light in nonlinear optical fibers , 2017 .

[5]  Yi Lin,et al.  Harnessing machine learning for fiber-induced nonlinearity mitigation in long-haul coherent optical OFDM , 2019, Future Internet.

[6]  Sergei K Turitsyn,et al.  Performance analysis of dual-pump nonlinear amplifying loop mirror mode-locked all-fibre laser , 2019, Laser Physics Letters.

[7]  G. Millot,et al.  Optical Parabolic Pulse Generation and Applications , 2009, IEEE Journal of Quantum Electronics.

[8]  Shie Mannor,et al.  Deep Learning Reconstruction of Ultra-Short Pulses , 2018, ArXiv.

[9]  S. Boscolo,et al.  Passive Nonlinear Pulse Shaping in Normally Dispersive Fiber Systems , 2008, IEEE Journal of Quantum Electronics.

[10]  Yash Sanghvi,et al.  Embedding Deep Learning in Inverse Scattering Problems , 2020, IEEE Transactions on Computational Imaging.

[11]  R. I. Woodward,et al.  Towards ‘smart lasers’: self-optimisation of an ultrafast pulse source using a genetic algorithm , 2016, Scientific Reports.

[12]  Markus K. Oberthaler,et al.  Special narrowing of ultrashort laser pulses by self‐phase modulation in optical fibers , 1993 .

[13]  C. Finot,et al.  Simple guidelines to predict self-phase modulation patterns , 2018, Journal of the Optical Society of America B.

[14]  C. Finot,et al.  Design rules for nonlinear spectral compression in optical fibers , 2016 .

[15]  R. Stolen,et al.  Observation of pulse restoration at the soliton period in optical fibers. , 1983, Optics letters.

[16]  Sunny Chugh,et al.  Machine learning approach for computing optical properties of a photonic crystal fiber. , 2019, Optics express.

[17]  Steven L. Brunton,et al.  Deep Learning and Model Predictive Control for Self-Tuning Mode-Locked Lasers , 2017, ArXiv.

[18]  James P. Gordon,et al.  Experimental observation of picosecond pulse narrowing and solitons in optical fibers (A) , 1980 .

[19]  A. Vasylchenkova,et al.  Artificial Neural Network-Based Equaliser in the Nonlinear Fourier Domain for Fibre-Optic Communication Applications , 2019, 2019 Conference on Lasers and Electro-Optics Europe & European Quantum Electronics Conference (CLEO/Europe-EQEC).

[20]  Naftali Tishby,et al.  Machine learning and the physical sciences , 2019, Reviews of Modern Physics.

[21]  Giulia Marcucci,et al.  Machine learning inverse problem for topological photonics , 2018, Communications Physics.

[22]  Tigran Mansuryan,et al.  Dispersive regime of spectral compression , 2008 .

[23]  G. Millot,et al.  Nonlinear spectral shaping and optical rogue events in fiber-based systems , 2012 .

[24]  Lexing Ying,et al.  SwitchNet: a neural network model for forward and inverse scattering problems , 2018, SIAM J. Sci. Comput..

[25]  Cyril Billet,et al.  Machine learning analysis of extreme events in optical fibre modulation instability , 2018, Nature Communications.

[26]  Parametrically shaped femtosecond pulses in the nonlinear regime obtained by reverse propagation in an optical fiber. , 2012, Optics letters.

[27]  S. Turitsyn,et al.  Generation of triangular-shaped optical pulses in normally dispersive fibre , 2010 .

[28]  Christophe Finot,et al.  Nonlinear sculpturing of optical pulses with normally dispersive fiber-based devices , 2018, Optical Fiber Technology.