A comparative study of convolutional neural networks for the detection of strong gravitational lensing

ABSTRACT As we enter the era of large-scale imaging surveys with the upcoming telescopes such as the Large Synoptic Survey Telescope (LSST) and the Square Kilometre Array (SKA), it is envisaged that the number of known strong gravitational lensing systems will increase dramatically. However, these e...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Monthly notices of the Royal Astronomical Society 2021-08, Vol.505 (4), p.6155-6165
Hauptverfasser: Magro, Daniel, Zarb Adami, Kristian, DeMarco, Andrea, Riggi, Simone, Sciacca, Eva
Format: Artikel
Sprache:eng
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:ABSTRACT As we enter the era of large-scale imaging surveys with the upcoming telescopes such as the Large Synoptic Survey Telescope (LSST) and the Square Kilometre Array (SKA), it is envisaged that the number of known strong gravitational lensing systems will increase dramatically. However, these events are still very rare and require the efficient processing of millions of images. In order to tackle this image processing problem, we present machine learning techniques and apply them to the gravitational lens finding challenge. The convolutional neural networks (CNNs) presented here have been reimplemented within a new, modular, and extendable framework, Lens EXtrActor CaTania University of Malta (LEXACTUM). We report an area under the curve (AUC) of 0.9343 and 0.9870, and an execution time of 0.0061 and 0.0594 s per image, for the Space and Ground data sets, respectively, showing that the results obtained by CNNs are very competitive with conventional methods (such as visual inspection and arc finders) for detecting gravitational lenses.
ISSN:0035-8711
1365-2966
DOI:10.1093/mnras/stab1635