Euclid Preparation XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong lensing events

Abstract

Forthcoming imaging surveys will potentially increase the number of known galaxy-scale strong lenses by several orders of magnitude. For this to happen, images of tens of millions of galaxies will have to be inspected to identify potential candidates. In this context, deep learning techniques are particularly suitable for the finding patterns in large data sets, and convolutional neural networks (CNNs) in particular can efficiently process large volumes of images. We assess and compare the performance of three network architectures in the classification of strong lensing systems on the basis of their morphological characteristics. We train and test our models on different subsamples of a data set of forty thousand mock images, having characteristics similar to those expected in the wide survey planned with the ESA mission \Euclid, gradually including larger fractions of faint lenses. We also evaluate the importance of adding information about the colour difference between the lens and source galaxies by repeating the same training on single-band and multi-band images. Our models find samples of clear lenses with $\gtrsim 90\%$ precision and completeness, without significant differences in the performance of the three architectures. Nevertheless, when including lenses with fainter arcs in the training set, the three models' performance deteriorates with accuracy values of $\sim 0.87$ to $\sim 0.75$ depending on the model. Our analysis confirms the potential of the application of CNNs to the identification of galaxy-scale strong lenses. We suggest that specific training with separate classes of lenses might be needed for detecting the faint lenses since the addition of the colour information does not yield a significant improvement in the current analysis, with the accuracy ranging from $\sim 0.89$ to $\sim 0.78$ for the different models.

23 pages,12 figures

References in corpus (33)

• Galaxies in the Hubble Ultra Deep Field: I. Detection, Multiband Photometry, Photometric Redshifts, and Morphology
• The Detection of a Population of Submillimeter-Bright, Strongly-Lensed Galaxies
• The CFHTLS Strong Lensing Legacy Survey: I. Survey overview and T0002 release sample
• An excess of small-scale gravitational lenses observed in galaxy clusters
• The Herschel-ATLAS: a sample of 500μm-selected lensed galaxies over 600 square degrees
• RingFinder: automated detection of galaxy-scale gravitational lenses in ground-based multi-filter imaging data
• LinKS: Discovering galaxy-scale strong lenses in the Kilo-Degree Survey using Convolutional Neural Networks
• Euclid preparation. XVIII. The NISP photometric system
• Arcfinder: An algorithm for the automatic detection of gravitational arcs
• Realistic simulations of gravitational lensing by galaxy clusters: extracting arc parameters from mock DUNE images
• A gravitationally lensed water maser in the early Universe
• Strong lens systems search in the Dark Energy Survey using Convolutional Neural Networks
• High-quality strong lens candidates in the final Kilo Degree survey footprint
• A new high-precision strong lensing model of the galaxy cluster MACS J0416.1-2403
• HOLISMOKES. VI. New galaxy-scale strong lens candidates from the HSC-SSP imaging survey
• Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in $\sim 100,000$ SDSS and $\sim 20,000$ CANDELS Galaxies
• HOLISMOKES. VIII. High-redshift, strong-lens search in the Hyper Suprime-Cam Subaru Strategic Program
• On the average density profile of dark-matter halos in the inner regions of massive early-type galaxies
• Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3
• Illuminating the past 8 billion years of cold gas towards two gravitationally lensed quasars
• The probability of galaxy-galaxy strong lensing events in hydrodynamical simulations of galaxy clusters
• Strong lensing in UNIONS: Toward a pipeline from discovery to modeling
• Sensitivity of strong lensing observations to dark matter substructure: a case study with Euclid
• Survey of Gravitationally-lensed Objects in HSC Imaging (SuGOHI). VIII. New galaxy-scale lenses from the HSC SSP
• Reliable Shapelet Image Analysis
• Strong lensing selection effects
• CLASH: Extending galaxy strong lensing to small physical scales with distant sources highly-magnified by galaxy cluster members
• Statistical strong lensing. III. Inferences with complete samples of lenses
• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• Streamlined Lensed Quasar Identification in Multiband Images via Ensemble Networks
• Probing the Slope of Cluster Mass Profile with Gravitational Einstein Rings: Application to Abell 1689
• Discovery of two Einstein crosses from massive post--blue nugget galaxies at z>1 in KiDS
• Searching for galaxy-scale strong-lenses in galaxy clusters with deep networks -- I: methodology and network performance

Cited by in corpus (8)

• Euclid. I. Overview of the Euclid mission
• A model for galaxy-galaxy strong lensing statistics in surveys
• Euclid preparation. LI. Forecasting the recovery of galaxy physical properties and their relations with template-fitting and machine-learning methods
• Euclid preparation. LXVIII. Extracting physical parameters from galaxies with machine learning
• Enhancing Cosmological Model Selection with Interpretable Machine Learning
• Galaxy-scale lens search in the PEARLS NEP TDF and CEERS JWST fields
• Gaia GraL: Gaia gravitational lens systems IX. Using XGBoost to explore the Gaia Focused Product Release GravLens catalogue
• Gravitational Lensing of Gravitational Waves from Astrophysical Sources: Theory, Detection, and Applications