Real-time reconstruction of high energy, ultrafast laser pulses using deep learning

Matthew Stanfield; Jordan Ott; Christopher Gardner; Nicholas F. Beier; Deano M. Farinella; Christopher A. Mancuso; Pierre Baldi; Franklin Dollar

doi:10.1038/s41598-022-09041-y

Real-time reconstruction of high energy, ultrafast laser pulses using deep learning

Matthew Stanfield, Jordan Ott, Christopher Gardner, Nicholas F. Beier, Deano M. Farinella, Christopher A. Mancuso, Pierre Baldi, Franklin Dollar

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

We report a method for the phase reconstruction of an ultrashort laser pulse based on the deep learning of the nonlinear spectral changes induce by self-phase modulation. The neural networks were trained on simulated pulses with random initial phases and spectra, with pulse durations between 8.5 and 65 fs. The reconstruction is valid with moderate spectral resolution, and is robust to noise. The method was validated on experimental data produced from an ultrafast laser system, where near real-time phase reconstructions were performed. This method can be used in systems with known linear and nonlinear responses, even when the fluence is not known, making this method ideal for difficult to measure beams such as the high energy, large aperture beams produced in petawatt systems.

Original language	English (US)
Article number	5299
Journal	Scientific reports
Volume	12
Issue number	1
DOIs	https://doi.org/10.1038/s41598-022-09041-y
State	Published - Dec 2022
Externally published	Yes

Bibliographical note

Funding Information:
This work was supported by STROBE: A National Science Foundation Science & Technology Center under Grant No. DMR-1548924; This material is based upon work supported by the National Science Foundation under the CAREER program Grant No. PHY-1753165, and under grant number DGE-1633631.

Publisher Copyright:
© 2022, The Author(s).

Keywords

Deep Learning
Lasers
Light

PubMed: MeSH publication types

Journal Article
Research Support, U.S. Gov't, Non-P.H.S.

Publisher link

10.1038/s41598-022-09041-y

Find It

Find It at U of M Libraries

Cite this

@article{0ed9404a8ef24e73aa8f85cd793e3f8e,

title = "Real-time reconstruction of high energy, ultrafast laser pulses using deep learning",

abstract = "We report a method for the phase reconstruction of an ultrashort laser pulse based on the deep learning of the nonlinear spectral changes induce by self-phase modulation. The neural networks were trained on simulated pulses with random initial phases and spectra, with pulse durations between 8.5 and 65 fs. The reconstruction is valid with moderate spectral resolution, and is robust to noise. The method was validated on experimental data produced from an ultrafast laser system, where near real-time phase reconstructions were performed. This method can be used in systems with known linear and nonlinear responses, even when the fluence is not known, making this method ideal for difficult to measure beams such as the high energy, large aperture beams produced in petawatt systems.",

keywords = "Deep Learning, Lasers, Light",

author = "Matthew Stanfield and Jordan Ott and Christopher Gardner and Beier, {Nicholas F.} and Farinella, {Deano M.} and Mancuso, {Christopher A.} and Pierre Baldi and Franklin Dollar",

note = "Funding Information: This work was supported by STROBE: A National Science Foundation Science & Technology Center under Grant No. DMR-1548924; This material is based upon work supported by the National Science Foundation under the CAREER program Grant No. PHY-1753165, and under grant number DGE-1633631. Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

month = dec,

doi = "10.1038/s41598-022-09041-y",

language = "English (US)",

volume = "12",

journal = "Scientific reports",

issn = "2045-2322",

publisher = "Nature Research",

number = "1",

}

TY - JOUR

T1 - Real-time reconstruction of high energy, ultrafast laser pulses using deep learning

AU - Stanfield, Matthew

AU - Ott, Jordan

AU - Gardner, Christopher

AU - Beier, Nicholas F.

AU - Farinella, Deano M.

AU - Mancuso, Christopher A.

AU - Baldi, Pierre

AU - Dollar, Franklin

N1 - Funding Information: This work was supported by STROBE: A National Science Foundation Science & Technology Center under Grant No. DMR-1548924; This material is based upon work supported by the National Science Foundation under the CAREER program Grant No. PHY-1753165, and under grant number DGE-1633631. Publisher Copyright: © 2022, The Author(s).

PY - 2022/12

Y1 - 2022/12

N2 - We report a method for the phase reconstruction of an ultrashort laser pulse based on the deep learning of the nonlinear spectral changes induce by self-phase modulation. The neural networks were trained on simulated pulses with random initial phases and spectra, with pulse durations between 8.5 and 65 fs. The reconstruction is valid with moderate spectral resolution, and is robust to noise. The method was validated on experimental data produced from an ultrafast laser system, where near real-time phase reconstructions were performed. This method can be used in systems with known linear and nonlinear responses, even when the fluence is not known, making this method ideal for difficult to measure beams such as the high energy, large aperture beams produced in petawatt systems.

AB - We report a method for the phase reconstruction of an ultrashort laser pulse based on the deep learning of the nonlinear spectral changes induce by self-phase modulation. The neural networks were trained on simulated pulses with random initial phases and spectra, with pulse durations between 8.5 and 65 fs. The reconstruction is valid with moderate spectral resolution, and is robust to noise. The method was validated on experimental data produced from an ultrafast laser system, where near real-time phase reconstructions were performed. This method can be used in systems with known linear and nonlinear responses, even when the fluence is not known, making this method ideal for difficult to measure beams such as the high energy, large aperture beams produced in petawatt systems.

KW - Deep Learning

KW - Lasers

KW - Light

UR - http://www.scopus.com/inward/record.url?scp=85127279596&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85127279596&partnerID=8YFLogxK

U2 - 10.1038/s41598-022-09041-y

DO - 10.1038/s41598-022-09041-y

M3 - Article

C2 - 35351923

AN - SCOPUS:85127279596

SN - 2045-2322

VL - 12

JO - Scientific reports

JF - Scientific reports

IS - 1

M1 - 5299

ER -

Real-time reconstruction of high energy, ultrafast laser pulses using deep learning

Abstract

Bibliographical note

Keywords

PubMed: MeSH publication types

Publisher link

Find It

Other files and links

Fingerprint

Cite this