EUVIMEDEUVIMED entdecken
Crossref

Deep learning-assisted characterization of ultrafast optical pulses using nonlinear fiber optics

Camilo Hurtado, Julián Orozco, Raúl E. Alzate, Pedro Torres, Rodrigo Acuna Herrera

Journal of the Optical Society of America B · 01.05.2026 · 43 (5) · 863

DOI: 10.1364/josab.585160 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Optical Society of America B, online erschienen am 07.04.2026. Verfasst von Camilo Hurtado und 4 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Gefördert von: Dirección de Investigación of the Universidad Nacional de Colombia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional ultrafast pulse characterization methods face limitations in accuracy and real-time applicability. This work presents an experimental validation of a data-driven approach previously explored numerically that uses deep learning to characterize femtosecond pulses from supercontinuum (SC) spectral data. Using a fully automated system to generate a comprehensive dataset from a nonlinear photonic crystal fiber (NL-PCF), we trained and compared two distinct architectures: a deep neural network (DNN) using 1D final SC spectra and a convolutional neural network (CNN) using 2D spectral evolution maps. Both models demonstrated high predictive accuracy, achieving a coefficient of determination ( R 2 ) greater than 0.98. By successfully translating this technique from simulation to a validated experimental framework, our study establishes a powerful and practical data-driven metrology for in situ monitoring of ultrafast laser systems.

Förderung

  • Dirección de Investigación of the Universidad Nacional de Colombia

Zitieren

APA

Hurtado, C., Orozco, J., Alzate, R. E., Torres, P., & Herrera, R. A. (2026). Deep learning-assisted characterization of ultrafast optical pulses using nonlinear fiber optics. Journal of the Optical Society of America B, 43(5), 863. https://doi.org/10.1364/josab.585160

Vancouver

Hurtado C, Orozco J, Alzate RE, Torres P, Herrera RA. Deep learning-assisted characterization of ultrafast optical pulses using nonlinear fiber optics. Journal of the Optical Society of America B. 2026;43(5):863. doi:10.1364/josab.585160

BibTeX
@article{Hurtado2026,
  author = {Hurtado, Camilo and Orozco, Julián and Alzate, Raúl E. and Torres, Pedro and Herrera, Rodrigo Acuna},
  title = {Deep learning-assisted characterization of ultrafast optical pulses using nonlinear fiber optics},
  journal = {Journal of the Optical Society of America B},
  year = {2026},
  volume = {43},
  number = {5},
  pages = {863},
  doi = {10.1364/josab.585160}
}
Kostenlos starten →