Rapid phase retrieval of ultrashort pulses from dispersion scan traces using deep neural networks

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, tim...

Full description

Saved in:
Bibliographic Details
Published in:Optics letters 2019-02, Vol.44 (4), p.979-982
Main Authors: Kleinert, Sven, Tajalli, Ayhan, Nagy, Tamas, Morgner, Uwe
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Dispersion
Femtosecond pulses
Inverse problems
Knowledge management
Neural networks
Optimization
Phase retrieval
Reconstruction
Redundancy
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0146-9592
1539-4794
DOI:10.1364/ol.44.000979