Streamlined Lensed Quasar Identification in Multiband Images via Ensemble Networks

Abstract

Quasars experiencing strong lensing offer unique viewpoints on subjects related to the cosmic expansion rate, the dark matter profile within the foreground deflectors, and the quasar host galaxies. Unfortunately, identifying them in astronomical images is challenging since they are overwhelmed by the abundance of non-lenses. To address this, we have developed a novel approach by ensembling cutting-edge convolutional networks (CNNs) -- for instance, ResNet, Inception, NASNet, MobileNet, EfficientNet, and RegNet -- along with vision transformers (ViTs) trained on realistic galaxy-quasar lens simulations based on the Hyper Suprime-Cam (HSC) multiband images. While the individual model exhibits remarkable performance when evaluated against the test dataset, achieving an area under the receiver operating characteristic curve of $>$97.3% and a median false positive rate of 3.6%, it struggles to generalize in real data, indicated by numerous spurious sources picked by each classifier. A significant improvement is achieved by averaging these CNNs and ViTs, resulting in the impurities being downsized by factors up to 50. Subsequently, combining the HSC images with the UKIRT, VISTA, and unWISE data, we retrieve approximately 60 million sources as parent samples and reduce this to 892,609 after employing a photometry preselection to discover $z>1.5$ lensed quasars with Einstein radii of ${\theta }_{\mathrm{E}}<5$ arcsec. Afterward, the ensemble classifier indicates 3080 sources with a high probability of being lenses, for which we visually inspect, yielding 210 prevailing candidates awaiting spectroscopic confirmation. These outcomes suggest that automated deep learning pipelines hold great potential in effectively detecting strong lenses in vast datasets with minimal manual visual inspection involved.

arXiv commentAccepted for publication in the Astronomy & Astrophysics journal. 28 pages, 11 figures, and 3 tables. We welcome comments from the reader

References in corpus (110)

• Array Programming with NumPy
• Maps of Dust IR Emission for Use in Estimation of Reddening and CMBR Foregrounds
• Astropy: A Community Python Package for Astronomy
• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• Measuring Reddening with SDSS Stellar Spectra and Recalibrating SFD
• The Gaia mission
• The Dust Content and Opacity of Actively Star-Forming Galaxies
• Gaia Data Release 3: Summary of the content and survey properties
• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Correcting for the Effects of Interstellar Extinction
• The UKIRT Infrared Deep Sky Survey (UKIDSS)
• Ensemble deep learning: A review
• The Baryon Oscillation Spectroscopic Survey of SDSS-III
• The propagation of uncertainties in stellar population synthesis modeling I: The relevance of uncertain aspects of stellar evolution and the IMF to the derived physical properties of galaxies
• EAZY: A Fast, Public Photometric Redshift Code
• Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
• H0LiCOW XIII. A 2.4% measurement of $H_0$ from lensed quasars: $5.3\sigma$ tension between early and late-Universe probes
• The propagation of uncertainties in stellar population synthesis modeling III: model calibration, comparison, and evaluation
• Spectral Energy Distributions of Hard X-ray selected AGNs in the XMDS Survey
• The SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Overview and Early Data
• The Assembly of the First Massive Black Holes
• First Data Release of the Hyper Suprime-Cam Subaru Strategic Program
• An Empirical Ultraviolet Template for Iron Emission in Quasars as Derived from I Zw 1
• Second Data Release of the Hyper Suprime-Cam Subaru Strategic Program
• An updated analytic model for the attenuation by the intergalactic medium
• The Cosmic Lens All-Sky Survey: I. Source selection and observations
• The unWISE Catalog: Two Billion Infrared Sources from Five Years of WISE Imaging
• Reionization of the Intergalactic Medium and the Damping Wing of the Gunn-Peterson Trough
• Photometric redshift and classification for the XMM-COSMOS sources
• Third Data Release of the Hyper Suprime-Cam Subaru Strategic Program
• The population of galaxy-galaxy strong lenses in forthcoming optical imaging surveys
• The Cosmic Lens All-Sky Survey:II. Gravitational lens candidate selection and follow-up
• The Eighteenth Data Release of the Sloan Digital Sky Surveys: Targeting and First Spectra from SDSS-V
• Dissecting Photometric redshift for Active Galactic Nuclei using XMM- and Chandra-COSMOS samples
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Internal and Collective Properties of Galaxies in the Sloan Digital Sky Survey
• The propagation of uncertainties in stellar population synthesis modeling II: The challenge of comparing galaxy evolution models to observations
• The z=5 Quasar Luminosity Function from SDSS Stripe 82
• The Evolution of Lyman Limit Absorption Systems to Redshift Six
• The Sloan Digital Sky Survey Quasar Lens Search. I. Candidate Selection Algorithm
• The UKIRT Hemisphere Survey: Definition and J-band Data Release
• The Sloan Digital Sky Survey Quasar Lens Search. V. Final Catalog from the Seventh Data Release
• The Strong Gravitational Lens Finding Challenge
• Fast calculation of a family of elliptical mass gravitational lens models
• Photometry and Proper Motions of M, L, and T Dwarfs from the Pan-STARRS1 3$\pi$ Survey
• AutoLens: Automated Modeling of a Strong Lens's Light, Mass and Source
• CosmoDC2: A Synthetic Sky Catalog for Dark Energy Science with LSST
• Gravitationally Lensed Quasars in Gaia: II. Discovery of 24 Lensed Quasars
• The SDSS-IV extended Baryonic Oscillation Spectroscopic Survey: Luminous Red Galaxy Target Selection
• LinKS: Discovering galaxy-scale strong lenses in the Kilo-Degree Survey using Convolutional Neural Networks
• The Cosmic Horseshoe: Discovery of an Einstein Ring around a Giant Luminous Red Galaxy
• SDSS J092455.87+021924.9: an Interesting Gravitationally Lensed Quasar from the Sloan Digital Sky Survey
• Survey of Gravitationally-lensed Objects in HSC Imaging (SuGOHI). I. Automatic search for galaxy-scale strong lenses
• Finding Strong Gravitational Lenses in the DESI DECam Legacy Survey
• The Faint End of the z=5 Quasar Luminosity Function from the CFHTLS
• Gravitationally lensed quasars in Gaia: III. 22 new lensed quasars from Gaia Data Release 2
• The Discovery of a Gravitationally Lensed Quasar at z = 6.51
• The Sloan Digital Sky Survey Quasar Lens Search. II. Statistical Lens Sample from the Third Data Release
• Correcting the z~8 Galaxy Luminosity Function for Gravitational Lensing Magnification Bias
• Strong lensing time-delay cosmography in the 2020s
• PyAutoLens: Open-Source Strong Gravitational Lensing
• Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
• Euclid preparation: V. Predicted yield of redshift 7<z<9 quasars from the wide survey
• A survey of luminous high-redshift quasars with SDSS and WISE II. the bright end of the quasar luminosity function at z ~ 5
• New high-quality strong lens candidates with deep learning in the Kilo Degree Survey
• GALEX far-UV color selection of UV-bright high-redshift quasars
• Gravitationally lensed quasars in Gaia -- IV. 150 new lenses, quasar pairs, and projected quasars
• AGN Populations in Large Volume X-ray Surveys: Photometric Redshifts and Population Types found in the Stripe 82X Survey
• Catalogues of Active Galactic Nuclei From Gaia and unWISE Data
• Survey of Gravitationally-lensed Objects in HSC Imaging (SuGOHI). VI. Crowdsourced lens finding with Space Warps
• Data Mining for Gravitationally Lensed Quasars
• Strong lens systems search in the Dark Energy Survey using Convolutional Neural Networks
• The STRong lensing Insights into the Dark Energy Survey (STRIDES) 2017/2018 follow-up campaign: Discovery of 10 lensed quasars and 10 quasar pairs
• HOLISMOKES. VI. New galaxy-scale strong lens candidates from the HSC-SSP imaging survey
• Mining for Strong Gravitational Lenses with Self-supervised Learning
• Survey of Gravitationally-lensed Objects in HSC Imaging (SuGOHI). V. Group-to-cluster scale lens search from the HSC-SSP Survey
• HOLISMOKES. VIII. High-redshift, strong-lens search in the Hyper Suprime-Cam Subaru Strategic Program
• The Sloan Digital Sky Survey Quasar Lens Search. IV. Statistical Lens Sample from the Fifth Data Release
• KiDS-SQuaD II: Machine learning selection of bright extragalactic objects to search for new gravitationally lensed quasars
• KiDS-SQuaD: The KiDS Strongly lensed Quasar Detection project
• Survey of Gravitationally-lensed Objects in HSC Imaging (SuGOHI). IV. Lensed quasar search in the HSC survey
• SDSS J1335+0118: A New Two-Image Gravitational Lens
• Probing the Nature of High Redshift Weak Emission Line Quasars: A Young Quasar with a Starburst Host Galaxy
• Brown dwarf census with the Dark Energy Survey year 3 data and the thin disk scale height of early L types
• Quasar lenses and pairs in the VST-ATLAS and Gaia
• HOLISMOKES -- IV. Efficient mass modeling of strong lenses through deep learning
• Discovery of Four Gravitationally Lensed Quasars from the Sloan Digital Sky Survey
• Discovery of a Gravitationally Lensed Quasar from the Sloan Digital Sky Survey: SDSS J133222.62+034739.9
• SDSS J0909$+$4449: A Large-separation Strongly Lensed Quasar at $z\sim 2.8$ with Three Images
• Survey of Gravitationally lensed Objects in HSC Imaging (SuGOHI) -- VII. Discovery and Confirmation of Three Strongly Lensed Quasars
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Most Lensed Quasars at $z>6$ are Missed by Current Surveys
• Survey of Gravitationally-lensed Objects in HSC Imaging (SuGOHI). VIII. New galaxy-scale lenses from the HSC SSP
• Red quasars blow out molecular gas from galaxies during the peak of cosmic star formation
• Quasar Lenses in the South: searches over the DES public footprint
• Revisiting the Lensed Fraction of High-Redshift Quasars
• A Survey for High-redshift Gravitationally Lensed Quasars and Close Quasars Pairs. I. the Discoveries of an Intermediately-lensed Quasar and a Kpc-scale Quasar Pair at $z\sim 5$
• A machine learning based approach to gravitational lens identification with the International LOFAR Telescope
• Discovery of three strongly lensed quasars in the Sloan Digital Sky Survey
• A Mock Catalog of Gravitationally Lensed Quasars for the LSST Survey
• A Highly Magnified Gravitationally Lensed Red QSO at z = 2.5 with a Significant Flux Ratio Anomaly
• HOLISMOKES -- IX. Neural network inference of strong-lens parameters and uncertainties from ground-based images
• ULAS J234311.93-005034.0: A gravitational lens system selected from UKIDSS and SDSS
• Discovering strongly lensed quasar candidates with catalogue-based methods from DESI Legacy Surveys
• Discovery of Strongly Lensed Quasars in the Ultraviolet Near Infrared Optical Northern Survey (UNIONS)
• Finding quadruply imaged quasars with machine learning. I. Methods
• Developing a Victorious Strategy to the Second Strong Gravitational Lensing Data Challenge
• When Spectral Modeling Meets Convolutional Networks: A Method for Discovering Reionization-era Lensed Quasars in Multi-band Imaging Data
• Strong Lensed QSOs with Variability Detectable by LSST: How many are there?

Cited by in corpus (8)

• Euclid Preparation XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong lensing events
• A Bayesian Approach to Strong Lens Finding in the Era of Wide-area Surveys
• HOLISMOKES XIII: Strong-lens candidates at all mass scales and their environments from the Hyper-Suprime Cam and deep learning
• Accelerating lensed quasar discovery and modeling with physics-informed variational autoencoders
• HOLISMOKES XVI: Lens search in HSC-PDR3 with a neural network committee and post-processing for false-positive removal
• Reducing false positives in strong lens detection through effective augmentation and ensemble learning
• Confirming HSC strong lens candidates with DESI Spectroscopy. I. Project overview and first results
• A Value-added Physical Properties Catalog for Low-redshift Galaxies from DESI Legacy Imaging Surveys DR10