Machine Learning Analysis of Extreme Events in Optical Fibre Modulation Instability

Overview

Journal Nat Commun

Specialty Biology

Date 2018 Nov 24

PMID 30467348

Citations 10

Authors

Mikko Narhi

Lauri Salmela

Juha Toivonen

Cyril Billet

John M Dudley

Goery Genty

Affiliations

Soon will be listed here.

Abstract

A central research area in nonlinear science is the study of instabilities that drive extreme events. Unfortunately, techniques for measuring such phenomena often provide only partial characterisation. For example, real-time studies of instabilities in nonlinear optics frequently use only spectral data, limiting knowledge of associated temporal properties. Here, we show how machine learning can overcome this restriction to study time-domain properties of optical fibre modulation instability based only on spectral intensity measurements. Specifically, a supervised neural network is trained to correlate the spectral and temporal properties of modulation instability using simulations, and then applied to analyse high dynamic range experimental spectra to yield the probability distribution for the highest temporal peaks in the instability field. We also use unsupervised learning to classify noisy modulation instability spectra into subsets associated with distinct temporal dynamic structures. These results open novel perspectives in all systems exhibiting instability where direct time-domain observations are difficult.

Citing Articles

Single-Photon Level Dispersive Fourier Transform: Ultrasensitive Characterization of Noise-Driven Nonlinear Dynamics.

Sader L, Bose S, Khodadad Kashi A, Boussafa Y, Haldar R, Dauliat R ACS Photonics. 2023; 10(11):3915-3928.

PMID: 38027249 PMC: 10655252. DOI: 10.1021/acsphotonics.3c00711.

Analysis of interaction dynamics and rogue wave localization in modulation instability using data-driven dominant balance.

Ermolaev A, Mabed M, Finot C, Genty G, Dudley J Sci Rep. 2023; 13(1):10462.

PMID: 37380725 PMC: 10307870. DOI: 10.1038/s41598-023-37039-7.

A Framework for Biosensors Assisted by Multiphoton Effects and Machine Learning.

Arano-Martinez J, Martinez-Gonzalez C, Salazar M, Torres-Torres C Biosensors (Basel). 2022; 12(9).

PMID: 36140093 PMC: 9496380. DOI: 10.3390/bios12090710.

Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization.

Arguello Ron D, Freire P, Prilepsky J, Kamalian-Kopae M, Napoli A, Turitsyn S Sci Rep. 2022; 12(1):8713.

PMID: 35610254 PMC: 9130141. DOI: 10.1038/s41598-022-12563-0.

Single step phase optimisation for coherent beam combination using deep learning.

Mills B, Grant-Jacob J, Praeger M, Eason R, Nilsson J, Zervas M Sci Rep. 2022; 12(1):5188.

PMID: 35338211 PMC: 8956726. DOI: 10.1038/s41598-022-09172-2.

References

Zimmermann R, Parlitz U . Observing spatio-temporal dynamics of excitable media using reservoir computing. Chaos. 2020; 28(4):043118. DOI: 10.1063/1.5022276. View

Narhi M, Wetzel B, Billet C, Toenger S, Sylvestre T, Merolla J . Real-time measurements of spontaneous breathers and rogue wave events in optical fibre modulation instability. Nat Commun. 2016; 7:13675. PMC: 5187408. DOI: 10.1038/ncomms13675. View

Jordan M, Mitchell T . Machine learning: Trends, perspectives, and prospects. Science. 2015; 349(6245):255-60. DOI: 10.1126/science.aaa8415. View

Ziv R, Dikopoltsev A, Zahavy T, Rubinstein I, Sidorenko P, Cohen O . Deep learning reconstruction of ultrashort pulses from 2D spatial intensity patterns recorded by an all-in-line system in a single-shot. Opt Express. 2020; 28(5):7528-7538. DOI: 10.1364/OE.383217. View

Solli D, Ropers C, Koonath P, Jalali B . Optical rogue waves. Nature. 2007; 450(7172):1054-7. DOI: 10.1038/nature06402. View

Toenger S, Godin T, Billet C, Dias F, Erkintalo M, Genty G . Emergent rogue wave structures and statistics in spontaneous modulation instability. Sci Rep. 2015; 5:10380. PMC: 4438606. DOI: 10.1038/srep10380. View

Chen C, Mahjoubfar A, Tai L, Blaby I, Huang A, Niazi K . Deep Learning in Label-free Cell Classification. Sci Rep. 2016; 6:21471. PMC: 4791545. DOI: 10.1038/srep21471. View

Corwin K, Newbury N, Dudley J, Coen S, Diddams S, Weber K . Fundamental noise limitations to supercontinuum generation in microstructure fiber. Phys Rev Lett. 2003; 90(11):113904. DOI: 10.1103/PhysRevLett.90.113904. View

Lyu M, Wang W, Wang H, Wang H, Li G, Chen N . Deep-learning-based ghost imaging. Sci Rep. 2017; 7(1):17865. PMC: 5736587. DOI: 10.1038/s41598-017-18171-7. View

10.

Krupa K, Nithyanandan K, Andral U, Tchofo-Dinda P, Grelu P . Real-Time Observation of Internal Motion within Ultrafast Dissipative Optical Soliton Molecules. Phys Rev Lett. 2017; 118(24):243901. DOI: 10.1103/PhysRevLett.118.243901. View

11.

Suret P, Koussaifi R, Tikan A, Evain C, Randoux S, Szwaj C . Single-shot observation of optical rogue waves in integrable turbulence using time microscopy. Nat Commun. 2016; 7:13136. PMC: 5059780. DOI: 10.1038/ncomms13136. View

12.

Woodward R, Kelleher E . Towards 'smart lasers': self-optimisation of an ultrafast pulse source using a genetic algorithm. Sci Rep. 2016; 6:37616. PMC: 5116642. DOI: 10.1038/srep37616. View

13.

Frosz M . Validation of input-noise model for simulations of supercontinuum generation and rogue waves. Opt Express. 2010; 18(14):14778-87. DOI: 10.1364/OE.18.014778. View

14.

Rivenson Y, Zhang Y, Gunaydin H, Teng D, Ozcan A . Phase recovery and holographic image reconstruction using deep learning in neural networks. Light Sci Appl. 2019; 7:17141. PMC: 6060068. DOI: 10.1038/lsa.2017.141. View

15.

Godin T, Wetzel B, Sylvestre T, Larger L, Kudlinski A, Mussot A . Real time noise and wavelength correlations in octave-spanning supercontinuum generation. Opt Express. 2013; 21(15):18452-60. DOI: 10.1364/OE.21.018452. View

16.

Pathak J, Hunt B, Girvan M, Lu Z, Ott E . Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach. Phys Rev Lett. 2018; 120(2):024102. DOI: 10.1103/PhysRevLett.120.024102. View

17.

Higham C, Murray-Smith R, Padgett M, Edgar M . Deep learning for real-time single-pixel video. Sci Rep. 2018; 8(1):2369. PMC: 5799195. DOI: 10.1038/s41598-018-20521-y. View

18.

Wetzel B, Stefani A, Larger L, Lacourt P, Merolla J, Sylvestre T . Real-time full bandwidth measurement of spectral noise in supercontinuum generation. Sci Rep. 2012; 2:882. PMC: 3508454. DOI: 10.1038/srep00882. View