Fast dispersion-scan retrieval: neural networks vs iterative algorithm
Open Access
- 10 July 2026
- journal article
- Published by Optica Publishing Group in Optics Express
- Vol. 34 (14) , 26640
Abstract
The dispersion-scan (d-scan) is a simple, inline pulse characterization with single-shot trace acquisition implementations. Together with fast d-scan retrieval algorithms it enables a pathway for (near) single-shot and real-time pulse retrieval. In this work, we extend current neural networks (NNs) to simultaneously retrieve the spectrum and spectral phase of a pulse from dispersion scan traces and compare their speed and retrieval quality with a highly optimized iterative algorithm.Keywords
Funding Information
- HORIZON EUROPE European Innovation Council (101058075-SISHOT)
- Vetenskapsrådet (2021-04691)
- Vetenskapsrådet (2022-03519)
This publication has 24 references indexed in Scilit:
- Roadmap on basic research needs for laser technologyJournal of Optics, 2024
- Complex-Valued Neural Networks: A Comprehensive SurveyIEEE/CAA Journal of Automatica Sinica, 2022
- High power, high repetition rate laser-based sources for attosecond scienceJournal of Physics: Photonics, 2022
- Ultrafast laser manufacturing: from physics to industrial applicationsCIRP Annals, 2021
- Machine learning and applications in ultrafast photonicsNature Photonics, 2020
- Compact 200 kHz HHG source driven by a few-cycle OPCPAJournal of Optics, 2017
- Compact single-shot d-scan setup for the characterization of few-cycle laser pulsesApplied Optics, 2017
- Single-pass high harmonic generation at high repetition rate and photon fluxJournal of Physics B: Atomic, Molecular and Optical Physics, 2016
- High-order harmonic generation using a high-repetition-rate turnkey laserReview of Scientific Instruments, 2014
- Parallel Computing Experiences with CUDAIEEE Micro, 2008