Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 979-982 |
| Seitenumfang | 4 |
| Fachzeitschrift | Optics Letters |
| Jahrgang | 44 |
| Ausgabenummer | 4 |
| Frühes Online-Datum | 13 Feb. 2019 |
| Publikationsstatus | Veröffentlicht - 15 Feb. 2019 |
Abstract
The knowledge of the temporal shape of femtosecond pulses is of major interest for all their applications. The reconstruction of the temporal shape of these pulses is an inverse problem for characterization techniques, which benefit from an inherent redundancy in the measurement. Conventionally, time-consuming optimization algorithms are used to solve the inverse problems. Here, we demonstrate the reconstruction of ultrashort pulses from dispersion scan traces employing a deep neural network. The network is trained with a multitude of artificial and noisy dispersion scan traces from randomly shaped pulses. The retrieval takes only 16 ms enabling video-rate reconstructions. This approach reveals a great tolerance against noisy conditions, delivering reliable retrievals from traces with signal-to-noise ratios down to 5.
ASJC Scopus Sachgebiete
- Physik und Astronomie (insg.)
- Atom- und Molekularphysik sowie Optik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Optics Letters, Jahrgang 44, Nr. 4, 15.02.2019, S. 979-982.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Rapid phase retrieval of ultrashort pulses from dispersion scan traces using deep neural networks
AU - Kleinert, Sven
AU - Tajalli, Ayhan
AU - Nagy, Tamas
AU - Morgner, Uwe
N1 - Funding information: Deutsche Forschungsgemeinschaft (DFG) under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD (Mo850/16-2; EXC 2122. ID: 390833453); Bundesministerium für Bildung und Forschung (BMBF) (13N14064); Niedersächsisches Ministerium für Wissenschaft und Kultur (MWK) (Tailored Light).
PY - 2019/2/15
Y1 - 2019/2/15
N2 - The knowledge of the temporal shape of femtosecond pulses is of major interest for all their applications. The reconstruction of the temporal shape of these pulses is an inverse problem for characterization techniques, which benefit from an inherent redundancy in the measurement. Conventionally, time-consuming optimization algorithms are used to solve the inverse problems. Here, we demonstrate the reconstruction of ultrashort pulses from dispersion scan traces employing a deep neural network. The network is trained with a multitude of artificial and noisy dispersion scan traces from randomly shaped pulses. The retrieval takes only 16 ms enabling video-rate reconstructions. This approach reveals a great tolerance against noisy conditions, delivering reliable retrievals from traces with signal-to-noise ratios down to 5.
AB - The knowledge of the temporal shape of femtosecond pulses is of major interest for all their applications. The reconstruction of the temporal shape of these pulses is an inverse problem for characterization techniques, which benefit from an inherent redundancy in the measurement. Conventionally, time-consuming optimization algorithms are used to solve the inverse problems. Here, we demonstrate the reconstruction of ultrashort pulses from dispersion scan traces employing a deep neural network. The network is trained with a multitude of artificial and noisy dispersion scan traces from randomly shaped pulses. The retrieval takes only 16 ms enabling video-rate reconstructions. This approach reveals a great tolerance against noisy conditions, delivering reliable retrievals from traces with signal-to-noise ratios down to 5.
UR - http://www.scopus.com/inward/record.url?scp=85061543774&partnerID=8YFLogxK
U2 - 10.1364/ol.44.000979
DO - 10.1364/ol.44.000979
M3 - Article
C2 - 30768040
AN - SCOPUS:85061543774
VL - 44
SP - 979
EP - 982
JO - Optics Letters
JF - Optics Letters
SN - 0146-9592
IS - 4
ER -