Machine learning and applications in ultrafast photonics

Goëry Genty; Lauri Salmela; John M. Dudley; Daniel Brunner; Alexey Kokhanovskiy; Sergei Kobtsev; Sergei K. Turitsyn

doi:10.1038/s41566-020-00716-4

Machine learning and applications in ultrafast photonics

Goëry Genty^*, Lauri Salmela, John M. Dudley, Daniel Brunner, Alexey Kokhanovskiy, Sergei Kobtsev, Sergei K. Turitsyn

^*Corresponding author for this work

Research output: Contribution to journal › Review article › peer-review

Abstract

Recent years have seen the rapid growth and development of the field of smart photonics, where machine-learning algorithms are being matched to optical systems to add new functionalities and to enhance performance. An area where machine learning shows particular potential to accelerate technology is the field of ultrafast photonics — the generation and characterization of light pulses, the study of light–matter interactions on short timescales, and high-speed optical measurements. Our aim here is to highlight a number of specific areas where the promise of machine learning in ultrafast photonics has already been realized, including the design and operation of pulsed lasers, and the characterization and control of ultrafast propagation dynamics. We also consider challenges and future areas of research.

Original language	English
Pages (from-to)	91-101
Number of pages	11
Journal	Nature Photonics
Volume	15
Early online date	30 Nov 2020
DOIs	https://doi.org/10.1038/s41566-020-00716-4
Publication status	Published - Feb 2021

Bibliographical note

Copyright © 2020, Springer Nature Limited

Funding Information:
G.G. acknowledges the Academy of Finland (318082, 333949, Flagship PREIN 320165). L.S. acknowledges the Faculty of Engineering and Natural Sciences graduate school of Tampere University. J.M.D. and D.B. were supported by the EUR EIPHI and I-SITE BFC projects (contracts ANR-17-EURE-0002 and ANR-15-IDEX-0003). D.B. also acknowledges funding from the Volkswagen Foundation and from the French Agence Nationale de la Recherche (ANR-19-CE24-0006-02). The work of S.K.T. and A.K. was supported by the Russian Science Foundation (grant number 17-72-30006). S.K.T. acknowledges the support of the EPSRC project TRANSNET. The work of S.K. was supported by the Russian Foundation for Basic Research grant number 18-29-20025.

Access to Document

10.1038/s41566-020-00716-4

Machine Learning and Applications in Ultrafast Photonics
Copyright © 2020, Springer Nature Limited
Accepted author manuscript, 164 KB

Cite this

@article{64a48c6725a44d3a855d5f95682c5aae,

title = "Machine learning and applications in ultrafast photonics",

abstract = "Recent years have seen the rapid growth and development of the field of smart photonics, where machine-learning algorithms are being matched to optical systems to add new functionalities and to enhance performance. An area where machine learning shows particular potential to accelerate technology is the field of ultrafast photonics — the generation and characterization of light pulses, the study of light–matter interactions on short timescales, and high-speed optical measurements. Our aim here is to highlight a number of specific areas where the promise of machine learning in ultrafast photonics has already been realized, including the design and operation of pulsed lasers, and the characterization and control of ultrafast propagation dynamics. We also consider challenges and future areas of research.",

author = "Go{\"e}ry Genty and Lauri Salmela and Dudley, {John M.} and Daniel Brunner and Alexey Kokhanovskiy and Sergei Kobtsev and Turitsyn, {Sergei K.}",

note = "Copyright {\textcopyright} 2020, Springer Nature Limited Funding Information: G.G. acknowledges the Academy of Finland (318082, 333949, Flagship PREIN 320165). L.S. acknowledges the Faculty of Engineering and Natural Sciences graduate school of Tampere University. J.M.D. and D.B. were supported by the EUR EIPHI and I-SITE BFC projects (contracts ANR-17-EURE-0002 and ANR-15-IDEX-0003). D.B. also acknowledges funding from the Volkswagen Foundation and from the French Agence Nationale de la Recherche (ANR-19-CE24-0006-02). The work of S.K.T. and A.K. was supported by the Russian Science Foundation (grant number 17-72-30006). S.K.T. acknowledges the support of the EPSRC project TRANSNET. The work of S.K. was supported by the Russian Foundation for Basic Research grant number 18-29-20025.",

year = "2021",

month = feb,

doi = "10.1038/s41566-020-00716-4",

language = "English",

volume = "15",

pages = "91--101",

journal = "Nature Photonics",

issn = "1749-4885",

publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Machine learning and applications in ultrafast photonics

AU - Genty, Goëry

AU - Salmela, Lauri

AU - Dudley, John M.

AU - Brunner, Daniel

AU - Kokhanovskiy, Alexey

AU - Kobtsev, Sergei

AU - Turitsyn, Sergei K.

N1 - Copyright © 2020, Springer Nature Limited Funding Information: G.G. acknowledges the Academy of Finland (318082, 333949, Flagship PREIN 320165). L.S. acknowledges the Faculty of Engineering and Natural Sciences graduate school of Tampere University. J.M.D. and D.B. were supported by the EUR EIPHI and I-SITE BFC projects (contracts ANR-17-EURE-0002 and ANR-15-IDEX-0003). D.B. also acknowledges funding from the Volkswagen Foundation and from the French Agence Nationale de la Recherche (ANR-19-CE24-0006-02). The work of S.K.T. and A.K. was supported by the Russian Science Foundation (grant number 17-72-30006). S.K.T. acknowledges the support of the EPSRC project TRANSNET. The work of S.K. was supported by the Russian Foundation for Basic Research grant number 18-29-20025.

PY - 2021/2

Y1 - 2021/2

N2 - Recent years have seen the rapid growth and development of the field of smart photonics, where machine-learning algorithms are being matched to optical systems to add new functionalities and to enhance performance. An area where machine learning shows particular potential to accelerate technology is the field of ultrafast photonics — the generation and characterization of light pulses, the study of light–matter interactions on short timescales, and high-speed optical measurements. Our aim here is to highlight a number of specific areas where the promise of machine learning in ultrafast photonics has already been realized, including the design and operation of pulsed lasers, and the characterization and control of ultrafast propagation dynamics. We also consider challenges and future areas of research.

AB - Recent years have seen the rapid growth and development of the field of smart photonics, where machine-learning algorithms are being matched to optical systems to add new functionalities and to enhance performance. An area where machine learning shows particular potential to accelerate technology is the field of ultrafast photonics — the generation and characterization of light pulses, the study of light–matter interactions on short timescales, and high-speed optical measurements. Our aim here is to highlight a number of specific areas where the promise of machine learning in ultrafast photonics has already been realized, including the design and operation of pulsed lasers, and the characterization and control of ultrafast propagation dynamics. We also consider challenges and future areas of research.

UR - http://www.scopus.com/inward/record.url?scp=85096938518&partnerID=8YFLogxK

UR - https://www.nature.com/articles/s41566-020-00716-4

U2 - 10.1038/s41566-020-00716-4

DO - 10.1038/s41566-020-00716-4

M3 - Review article

AN - SCOPUS:85096938518

SN - 1749-4885

VL - 15

SP - 91

EP - 101

JO - Nature Photonics

JF - Nature Photonics

ER -

Machine learning and applications in ultrafast photonics

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this