Deep learning for isolated attosecond pulse reconstruction with the all-optical method
Journal of the Optical Society of America B · 01.10.2023 · 40 (10) · 2536
DOI: 10.1364/josab.489019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Optical Society of America B, online erschienen am 08.09.2023. Verfasst von Lihui Meng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
The characterization of attosecond pulses is crucial for attosecond metrology. In this work, we investigate the isolated attosecond pulse reconstruction with the all-optical method. The results show that this method can characterize isolated attosecond pulses with a duration shorter than 50 attoseconds. Moreover, we develop a deep learning scheme to characterize isolated attosecond pulses. Through supervised learning, the deep neural network learns the mapping from the photon spectrograms to attosecond pulses. It allows complete characterization of the amplitude and phase of isolated attosecond pulses. Compared to the conventional principal component generalized projections algorithm, the reconstruction with our neural network shows superior quality and robustness to noise. Also, the reconstruction computation time is significantly reduced to a few seconds.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Meng, L., Liang, S., He, L., Hu, J., Sun, S., Lan, P., & Lu, P. (2023). Deep learning for isolated attosecond pulse reconstruction with the all-optical method. Journal of the Optical Society of America B, 40(10), 2536. https://doi.org/10.1364/josab.489019
Vancouver
Meng L, Liang S, He L, Hu J, Sun S, Lan P, et al. Deep learning for isolated attosecond pulse reconstruction with the all-optical method. Journal of the Optical Society of America B. 2023;40(10):2536. doi:10.1364/josab.489019
BibTeX
@article{Meng2023,
author = {Meng, Lihui and Liang, Shiqi and He, Lixin and Hu, Jianchang and Sun, Siqi and Lan, Pengfei and Lu, Peixiang},
title = {Deep learning for isolated attosecond pulse reconstruction with the all-optical method},
journal = {Journal of the Optical Society of America B},
year = {2023},
volume = {40},
number = {10},
pages = {2536},
doi = {10.1364/josab.489019}
}
EUVIMED