LinKS: discovering galaxy-scale strong lenses in the Kilo-Degree Survey using convolutional neural networks. Issue 3 (17th January 2019)

• Record Type: Journal Article
• Authors: Petrillo, C E; Tortora, C; Vernardos, G; Koopmans, L V E; Verdoes Kleijn, G; Bilicki, M; Napolitano, N R; Chatterjee, S; Covone, G; Dvornik, A; Erben, T; Getman, F; Giblin, B; Heymans, C; de Jong, J T A; Kuijken, K; Schneider, P; Shan, H; Spiniello, C; Wright, A H
• Is Part Of: Monthly notices of the Royal Astronomical Society. Volume 484:Issue 3(2019)
• Page Start: 3879
• Page End: 3896
• Publication Date: 2019-01-17
• Subjects: gravitational lensing: strong -- galaxies: elliptical and lenticular, cD; Astronomy -- Periodicals; Periodicals; 520.5
• DOI: 10.1093/mnras/stz189
• Languages: English
• ISSNs: 0035-8711

Abstract

ABSTRACT: We present a new sample of galaxy-scale strong gravitational lens candidates, selected from 904 deg 2 of Data Release 4 of the Kilo-Degree Survey, i.e. the 'Lenses in the Kilo-Degree Survey' (LinKS) sample. We apply two convolutional neural networks (ConvNets) to ${\sim }88\, 000$ colour–magnitude-selected luminous red galaxies yielding a list of 3500 strong lens candidates. This list is further downselected via human inspection. The resulting LinKS sample is composed of 1983 rank-ordered targets classified as 'potential lens candidates' by at least one inspector. Of these, a high-grade subsample of 89 targets is identified with potential strong lenses by all inspectors. Additionally, we present a collection of another 200 strong lens candidates discovered serendipitously from various previous ConvNet runs. A straightforward application of our procedure to future Euclid or Large Synoptic Survey Telescope data can select a sample of ∼3000 lens candidates with less than 10 per cent expected false positives and requiring minimal human intervention.