Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations

Abstract

Forthcoming large imaging surveys such as Euclid and the Vera Rubin Observatory Legacy Survey of Space and Time are expected to find more than $10^5$ strong gravitational lens systems, including many rare and exotic populations such as compound lenses, but these $10^5$ systems will be interspersed among much larger catalogues of $\sim 10^9$ galaxies. This volume of data is too much for visual inspection by volunteers alone to be feasible and gravitational lenses will only appear in a small fraction of these data which could cause a large amount of false positives. Machine learning is the obvious alternative but the algorithms' internal workings are not obviously interpretable, so their selection functions are opaque and it is not clear whether they would select against important rare populations. We design, build, and train several Convolutional Neural Networks (CNNs) to identify strong gravitational lenses using VIS, Y, J, and H bands of simulated data, with F1 scores between 0.83 and 0.91 on 100,000 test set images. We demonstrate for the first time that such CNNs do not select against compound lenses, obtaining recall scores as high as 76\% for compound arcs and 52\% for double rings. We verify this performance using Hubble Space Telescope (HST) and Hyper Suprime-Cam (HSC) data of all known compound lens systems. Finally, we explore for the first time the interpretability of these CNNs using Deep Dream, Guided Grad-CAM, and by exploring the kernels of the convolutional layers, to illuminate why CNNs succeed in compound lens selection.

MNRAS accepted. 16 pages, 17 figures, The code used in this paper is publicly available at github.com/JoshWilde/LensFindery-McLensFinderFace

References in corpus (18)

• scikit-image: Image processing in Python
• Understanding Neural Networks Through Deep Visualization
• The Sloan Lens ACS Survey. V. The Full ACS Strong-Lens Sample
• The Detection of a Population of Submillimeter-Bright, Strongly-Lensed Galaxies
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• The Sloan Lens ACS Survey. VI: Discovery and analysis of a double Einstein ring
• First catalog of strong lens candidates in the COSMOS field
• The Herschel-ATLAS: a sample of 500μm-selected lensed galaxies over 600 square degrees
• The Sloan Lens ACS Survey. XIII. Discovery of 40 New Galaxy-Scale Strong Lenses
• Over-constrained Gravitational Lens Models and the Hubble Constant
• Gravitational lenses and lens candidates identified from the COSMOS field
• Using Convolutional Neural Networks to identify Gravitational Lenses in Astronomical images
• NOEMA redshift measurements of bright Herschel galaxies
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3
• A Spectroscopically Confirmed Double Source Plane Lens System in the Hyper Suprime-Cam Subaru Strategic Program
• Finding bright $z\ge 6.6$ Lyman-$\alpha$ emitters with lensing: prospects for Euclid
• Strong Lensing considerations for the LSST observing strategy