Semi-Supervised Learning for Lensed Quasar Detection

Abstract

Lensed quasars are key to many areas of study in astronomy, offering a unique probe into the intermediate and far universe. However, finding lensed quasars has proved difficult despite significant efforts from large collaborations. These challenges have limited catalogues of confirmed lensed quasars to the hundreds, despite theoretical predictions that they should be many times more numerous. We train machine learning classifiers to discover lensed quasar candidates. By using semi-supervised learning techniques we leverage the large number of potential candidates as unlabelled training data alongside the small number of known objects, greatly improving model performance. We present our two most successful models: (1) a variational autoencoder trained on millions of quasars to reduce the dimensionality of images for input to a dense neural network classifier that can make accurate predictions and (2) a convolutional neural network trained on a mix of labelled and unlabelled data via virtual adversarial training. These models are both capable of producing high-quality candidates, as evidenced by our discovery of GRALJ140833.73+042229.98. The success of our classifier, which uses only multi-band images, is particularly exciting as it can be combined with existing classifiers, which use other data than images, to improve the classifications of both models and discover more lensed quasars.

13 pages, accepted for publication in MNRAS

References in corpus (27)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Array Programming with NumPy
• Astropy: A Community Python Package for Astronomy
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• scikit-image: Image processing in Python
• The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package
• Overview of the DESI Legacy Imaging Surveys
• astroquery: An Astronomical Web-Querying Package in Python
• Formation of Supermassive Black Holes
• The Pan-STARRS1 Database and Data Products
• Supermassive black holes and their feedback effects in the IllustrisTNG simulation
• Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• The Pan-STARRS Data Processing System
• Pan-STARRS Pixel Processing: Detrending, Warping, Stacking
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• The Million Quasars (Milliquas) Catalogue, v8
• Small Scale Structure at High Redshift: II. Physical Properties of the CIV Absorbing Clouds
• Gravitationally lensed quasars in Gaia: III. 22 new lensed quasars from Gaia Data Release 2
• Gaia Data Release 3: The extragalactic content
• Unveiling the population of dual- and lensed- AGNs at sub-arcsec separations
• Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
• Faint Resonantly Scattered Lyman Alpha Emission from the Absorption Troughs of Damped Lyman Alpha Systems at z ~ 3
• Gaia GraL: Gaia DR2 Gravitational Lens Systems. V. Doubly-imaged QSOs discovered from entropy and wavelets
• Finding quadruply imaged quasars with machine learning. I. Methods
• DELIGHT: Deep Learning Identification of Galaxy Hosts of Transients using Multi-resolution Images
• TD-CARMA: Painless, accurate, and scalable estimates of gravitational-lens time delays with flexible CARMA processes