Machine-learning-assisted dual harmonic generation FROG for enhanced ultrafast pulse recovery

Ultrafast pulse characterisation is crucial for studying processes that occur at femtosecond timescales and below. Because of this, various methods have been developed to recover a pulse’s electric field profile at these durations, with the frequency-resolved optical gating (FROG) technique being th...

Full description

Saved in:
Bibliographic Details
Main Authors: Wallace Jaffray, Ziheng Guo, Andrea Di Falco, Marcello Ferrera
Format: Article
Language:English
Published: IOP Publishing 2024-01-01
Series:Machine Learning: Science and Technology
Subjects:
Online Access:https://doi.org/10.1088/2632-2153/ad9f21
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850041448341176320
author Wallace Jaffray
Ziheng Guo
Andrea Di Falco
Marcello Ferrera
author_facet Wallace Jaffray
Ziheng Guo
Andrea Di Falco
Marcello Ferrera
author_sort Wallace Jaffray
collection DOAJ
description Ultrafast pulse characterisation is crucial for studying processes that occur at femtosecond timescales and below. Because of this, various methods have been developed to recover a pulse’s electric field profile at these durations, with the frequency-resolved optical gating (FROG) technique being the most common. However, this approach is computationally expensive and suffers from limitations in terms of robustness and reliability. In this regard, recent publications have demonstrated that applying machine learning towards ultrafast pulse recovery can alleviate these issues, providing more accurate retrievals. Inspired by these works, we propose an encoder–decoder scheme for a FROG system which exploits dual harmonic generation in low-index thin films. Specifically, we demonstrate enhanced reliability and accuracy of ultrafast pulse recovery when compared to machine learning approaches using second or third harmonic signals independently. As the amount of information used to train each neural network is kept constant, this study demonstrates and benchmarks the technological advantages of contextual information analysis involving multiple nonlinear processes.
format Article
id doaj-art-891a3f31851e45beb8e93021260e4e08
institution DOAJ
issn 2632-2153
language English
publishDate 2024-01-01
publisher IOP Publishing
record_format Article
series Machine Learning: Science and Technology
spelling doaj-art-891a3f31851e45beb8e93021260e4e082025-08-20T02:55:46ZengIOP PublishingMachine Learning: Science and Technology2632-21532024-01-015404507410.1088/2632-2153/ad9f21Machine-learning-assisted dual harmonic generation FROG for enhanced ultrafast pulse recoveryWallace Jaffray0https://orcid.org/0000-0001-7992-5193Ziheng Guo1https://orcid.org/0009-0002-2266-8637Andrea Di Falco2https://orcid.org/0000-0002-7338-8785Marcello Ferrera3https://orcid.org/0000-0003-4479-5127Institute of Photonics and Quantum Sciences , Heriot-Watt University, SUPA Edinburgh, Midlothian EH14 4AS, United KingdomSchool of Physics and Astronomy, University of St. Andrews , North Haugh, St Andrews, Fife KY16 9SS, United KingdomSchool of Physics and Astronomy, University of St. Andrews , North Haugh, St Andrews, Fife KY16 9SS, United KingdomInstitute of Photonics and Quantum Sciences , Heriot-Watt University, SUPA Edinburgh, Midlothian EH14 4AS, United KingdomUltrafast pulse characterisation is crucial for studying processes that occur at femtosecond timescales and below. Because of this, various methods have been developed to recover a pulse’s electric field profile at these durations, with the frequency-resolved optical gating (FROG) technique being the most common. However, this approach is computationally expensive and suffers from limitations in terms of robustness and reliability. In this regard, recent publications have demonstrated that applying machine learning towards ultrafast pulse recovery can alleviate these issues, providing more accurate retrievals. Inspired by these works, we propose an encoder–decoder scheme for a FROG system which exploits dual harmonic generation in low-index thin films. Specifically, we demonstrate enhanced reliability and accuracy of ultrafast pulse recovery when compared to machine learning approaches using second or third harmonic signals independently. As the amount of information used to train each neural network is kept constant, this study demonstrates and benchmarks the technological advantages of contextual information analysis involving multiple nonlinear processes.https://doi.org/10.1088/2632-2153/ad9f21photonicsultrafast physicsmachine learning
spellingShingle Wallace Jaffray
Ziheng Guo
Andrea Di Falco
Marcello Ferrera
Machine-learning-assisted dual harmonic generation FROG for enhanced ultrafast pulse recovery
Machine Learning: Science and Technology
photonics
ultrafast physics
machine learning
title Machine-learning-assisted dual harmonic generation FROG for enhanced ultrafast pulse recovery
title_full Machine-learning-assisted dual harmonic generation FROG for enhanced ultrafast pulse recovery
title_fullStr Machine-learning-assisted dual harmonic generation FROG for enhanced ultrafast pulse recovery
title_full_unstemmed Machine-learning-assisted dual harmonic generation FROG for enhanced ultrafast pulse recovery
title_short Machine-learning-assisted dual harmonic generation FROG for enhanced ultrafast pulse recovery
title_sort machine learning assisted dual harmonic generation frog for enhanced ultrafast pulse recovery
topic photonics
ultrafast physics
machine learning
url https://doi.org/10.1088/2632-2153/ad9f21
work_keys_str_mv AT wallacejaffray machinelearningassisteddualharmonicgenerationfrogforenhancedultrafastpulserecovery
AT zihengguo machinelearningassisteddualharmonicgenerationfrogforenhancedultrafastpulserecovery
AT andreadifalco machinelearningassisteddualharmonicgenerationfrogforenhancedultrafastpulserecovery
AT marcelloferrera machinelearningassisteddualharmonicgenerationfrogforenhancedultrafastpulserecovery