Finding high-redshift strong lenses in DES using convolutional neural networks

Abstract

We search Dark Energy Survey (DES) Year 3 imaging data for galaxy-galaxy strong gravitational lenses using convolutional neural networks. We generate 250,000 simulated lenses at redshifts > 0.8 from which we create a data set for training the neural networks with realistic seeing, sky and shot noise. Using the simulations as a guide, we build a catalogue of 1.1 million DES sources with 1.8 < g − i < 5, 0.6 < g − r < 3, r_mag > 19, g_mag > 20 and i_mag > 18.2. We train two ensembles of neural networks on training sets consisting of simulated lenses, simulated non-lenses, and real sources. We use the neural networks to score images of each of the sources in our catalogue with a value from 0 to 1, and select those with scores greater than a chosen threshold for visual inspection, resulting in a candidate set of 7,301 galaxies. During visual inspection we rate 84 as "probably" or "definitely" lenses. Four of these are previously known lenses or lens candidates. We inspect a further 9,428 candidates with a different score threshold, and identify four new candidates. We present 84 new strong lens candidates, selected after a few hours of visual inspection by astronomers. This catalogue contains a comparable number of high-redshift lenses to that predicted by simulations. Based on simulations we estimate our sample to contain most discoverable lenses in this imaging and at this redshift range.

Strong gravitational lensing of explosive transients

“…A large number of gravitationally lensed distant galaxies have also been discovered by deep imaging of central regions of massive clusters of galaxies [30][31][32]. Recently, more strong lens systems are being found in various surveys such as Gaia [33][34][35], Dark Energy Survey [36][37][38][39], Kilo-Degree Survey [40], Pan-STARRS1 [41], and Subaru Hyper Suprime-Cam survey [42,43].…”

Image Simulations for Strong and Weak Gravitational Lensing

“…Jacobs et al (2019aJacobs et al ( ,b, 2017 have used convolutional neural networks (CNNs, (LeCun et al 1989)) to produce a catalog of galaxy-galaxy strong lenses (including high-redshift systems) using data from the Dark Energy Survey, and Petrillo et al (2017Petrillo et al ( , 2019 have correspondingly found hundreds of candidates in KiDS data. Jacobs et al (2019b) use the LENSPOP (Collett 2015) code to generate a training set that consists of hundreds of thousands of labeled simulated examples to train a CNN that classifies lenses and non-lenses. Metcalf et al (2019) use N-body (Millenium) and ray-tracing (GLAMER, ; ) simulations to analyze a variety of methods including CNN's, visual inspection, and arc finders to assess their efficiency and completeness, and identify biases in the face of large future datasets.…”

Surveying the reach and maturity of machine learning and artificial intelligence in astronomy

“…A major challenge for deep learning methods in lens finding is paucity of training data; this has been solved using simulated lenses at galaxy scale. Deep neural nets trained on simulations have resulted in lens discoveries in survey data including the KiDS (de Jong et al, ) by Petrillo et al (, ); and the Dark Energy Survey (Dark Energy Survey Collaboration et al, ) by Jacobs, Collett, Glazebrook, Buckley‐Geer, et al () and Jacobs, Collett, Glazebrook, McCarthy, et al (). A strong lens finding challenge was recently conducted using simulated data (Metcalf et al, ), and deep learning‐based methods outperformed all other methodologies including examination by human experts. Gravitational wave astronomy The recent detection of gravitational wave signals from coalescing black hole binaries (Abbott et al, ), and other related compact systems, has relied on real‐time computation and analysis of streams of data from the Advanced Laser Interferometer Gravitational‐Wave Observatory (LIGO) detectors (Harry and LIGO Scientific Collaboration, ).…”

“…A major challenge for deep learning methods in lens finding is paucity of training data; this has been solved using simulated lenses at galaxy scale. Deep neural nets trained on simulations have resulted in lens discoveries in survey data including the KiDS (de Jong et al, 2015) by Petrillo et al (2017Petrillo et al ( , 2019; and the Dark Energy Survey (Dark Energy Survey Collaboration et al, 2016) by Jacobs, Collett, Glazebrook, Buckley-Geer, et al (2019) and Jacobs, Collett, Glazebrook, McCarthy, et al (2019). A strong lens finding challenge was recently conducted using simulated data (Metcalf et al, 2019), and deep learning-based methods outperformed all other methodologies including examination by human experts.…”