Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder

Abstract

In this paper we develop a new unsupervised machine learning technique comprised of a feature extractor, a convolutional autoencoder (CAE), and a clustering algorithm consisting of a Bayesian Gaussian mixture model (BGM). We apply this technique to visual band space-based simulated imaging data from the Euclid Space Telescope using data from the Strong Gravitational Lenses Finding Challenge. Our technique promisingly captures a variety of lensing features such as Einstein rings with different radii, distorted arc structures, etc, without using predefined labels. After the clustering process, we obtain several classification clusters separated by different visual features which are seen in the images. Our method successfully picks up $\sim$63\ percent of lensing images from all lenses in the training set. With the assumed probability proposed in this study, this technique reaches an accuracy of $77.25\pm 0.48$\% in binary classification using the training set. Additionally, our unsupervised clustering process can be used as the preliminary classification for future surveys of lenses to efficiently select targets and to speed up the labelling process. As the starting point of the astronomical application using this technique, we not only explore the application to gravitationally lensed systems, but also discuss the limitations and potential future uses of this technique.

arXiv comment18 pages, 18 figures. Accepted to MNRAS

References in corpus (86)

• Scikit-learn: Machine Learning in Python
• Auto-Encoding Variational Bayes
• Euclid Definition Study Report
• Resolving Cosmic Structure Formation with the Millennium-II Simulation
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Dark Energy Survey Year 1 Results: Cosmological Constraints from Cosmic Shear
• Detection of Weak Gravitational Lensing by Large-scale Structure
• Weak lensing for precision cosmology
• Improving galaxy morphologies for SDSS with Deep Learning
• CLASH: Three Strongly Lensed Images of a Candidate z ~ 11 Galaxy
• Two accurate time-delay distances from strong lensing: Implications for cosmology
• H0LiCOW I. $H_0$ Lenses in COSMOGRAIL's Wellspring: Program Overview
• The population of galaxy-galaxy strong lenses in forthcoming optical imaging surveys
• Detection of lensing substructure using ALMA observations of the dusty galaxy SDP.81
• The Density Profiles of Massive, Relaxed Galaxy Clusters. II. Separating Luminous and Dark Matter in Cluster Cores
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Cosmology from gravitational lens time delays and Planck data
• Inference of the Cold Dark Matter substructure mass function at z=0.2 using strong gravitational lenses
• ANNz2 - photometric redshift and probability distribution function estimation using machine learning
• Spectroscopic detections of CIII]1909 at z~6-7: A new probe of early star forming galaxies and cosmic reionisation
• Photometric Supernova Classification With Machine Learning
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• Weak Lensing Probes of Modified Gravity
• Galaxy-Galaxy Lensing in the Hubble Deep Field: The Halo Tully-Fisher Relation at Intermediate Redshift
• The SL2S Galaxy-scale Lens Sample. V. Dark Matter Halos and Stellar IMF of Massive Early-type Galaxies out to Redshift 0.8
• The Strong Gravitational Lens Finding Challenge
• Weak lensing analysis in three dimensions
• Strong Lens Time Delay Challenge: II. Results of TDC1
• Precision calculations of the cosmic shear power spectrum projection
• Cosmological Constraints from the double source plane lens SDSSJ0946+1006
• Finding strong lenses in CFHTLS using convolutional neural networks
• Keck Spectroscopy of Gravitationally Lensed z=4 Galaxies: Improved Constraints on the Escape Fraction of Ionizing Photons
• RingFinder: automated detection of galaxy-scale gravitational lenses in ground-based multi-filter imaging data
• Cosmic shear statistics in the Suprime-Cam 2.1 sq deg field: Constraints on Omega_m and sigma_8
• SOMz: photometric redshift PDFs with self organizing maps and random atlas
• Optimising Automatic Morphological Classification of Galaxies with Machine Learning and Deep Learning using Dark Energy Survey Imaging
• Astrophysical Applications of Gravitational Microlensing
• Survey of Gravitationally-lensed Objects in HSC Imaging (SuGOHI). I. Automatic search for galaxy-scale strong lenses
• Revealing the complex nature of the strong gravitationally lensed system H-ATLAS J090311.6+003906 using ALMA
• The BOSS Emission-Line Lens Survey. IV. : Smooth Lens Models for the BELLS GALLERY Sample
• An Earth-mass Planet in a 1-AU Orbit around an Ultracool Dwarf
• Cosmic Shear Results from the Deep Lens Survey - II: Full Cosmological Parameter Constraints from Tomography
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Galaxy and Mass Assembly (GAMA): The halo mass of galaxy groups from maximum-likelihood weak lensing
• Automated detection of galaxy-scale gravitational lenses in high resolution imaging data
• Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
• Unsupervised self-organised mapping: a versatile empirical tool for object selection, classification and redshift estimation in large surveys
• VDES J2325-5229 a z=2.7 gravitationally lensed quasar discovered using morphology independent supervised machine learning
• METAPHOR: A machine learning based method for the probability density estimation of photometric redshifts
• Realistic simulations of gravitational lensing by galaxy clusters: extracting arc parameters from mock DUNE images
• Convolutional Clustering for Unsupervised Learning
• A Submillimeter Survey of Gravitationally Lensed Quasars
• Arc Statistics
• Probing the nature of dark matter by forward modeling flux ratios in strong gravitational lenses
• Neural network-based clustering using pairwise constraints
• Gravitational lensing reveals extreme dust-obscured star formation in quasar host galaxies
• Testing Star Formation Laws in a Starburst Galaxy At Redshift 3 Resolved with ALMA
• Modelling high resolution ALMA observations of strongly lensed highly star forming galaxies detected by Herschel
• A PCA-based automated finder for galaxy-scale strong lenses
• The use of convolutional neural networks for modelling large optically-selected strong galaxy-lens samples
• A free-form lensing model of A370 revealing stellar mass dominated BCGs, in Hubble Frontier Fields images
• Red nuggets grow inside-out: evidence from gravitational lensing
• Probing the cosmic distance duality relation using time delay lenses
• Cosmic shear bispectrum from second-order perturbations in General Relativity
• Effective description of dark matter self-interactions in small dark matter haloes
• Can Self-Organizing Maps accurately predict photometric redshifts?
• Support Vector Machine classification of strong gravitational lenses
• A Neural Network Gravitational Arc Finder based on the Mediatrix filamentation Method
• Gravitational Microlensing I: A Unique Astrophysical Tool
• The PCA Lens-Finder: application to CFHTLS
• SDSS-IV MaNGA: The Spectroscopic Discovery of Strongly Lensed Galaxies
• Kiloparsec Mass/Light Offsets in the Galaxy Pair-Ly$\alpha$ Emitter Lens System SDSS\,J1011$+$0143
• The shape of galaxy dark matter halos in massive galaxy clusters: Insights from strong gravitational lensing
• A magnified glance into the dark sector: probing cosmological models with strong lensing in A1689
• Automated Lensing Learner: Automated Strong Lensing Identification with a Computer Vision Technique
• Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders
• Spectral analysis of four 'hypervariable' AGN: a microneedle in the haystack?
• Models of gravitational lens candidates from Space Warps CFHTLS
• Spatially Resolved Patchy Lyman-$\alpha$ Emission Within the Central Kiloparsec of a Strongly Lensed Quasar Host Galaxy at z = 2.8
• CLaSPS: a new methodology for Knowledge extraction from complex astronomical dataset
• The VIMOS Public Extragalactic Redshift Survey (VIPERS). Unsupervised classification with photometric redshifts: a method to accurately classify large galaxy samples without spectroscopic information
• Photo-$z$ with CuBAN$z$: An improved photometric redshift estimator using Clustering aided Back Propagation Neural network
• OGLE-2017-BLG-0482Lb: A Microlensing Super-Earth Orbiting a Low-mass Host Star
• Human-like Clustering with Deep Convolutional Neural Networks

Cited by in corpus (50)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Self-Supervised Representation Learning for Astronomical Images
• HOLISMOKES -- II. Identifying galaxy-scale strong gravitational lenses in Pan-STARRS using convolutional neural networks
• Beyond the Hubble Sequence -- Exploring Galaxy Morphology with Unsupervised Machine Learning
• AstroCLIP: A Cross-Modal Foundation Model for Galaxies
• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• HOLISMOKES. VI. New galaxy-scale strong lens candidates from the HSC-SSP imaging survey
• Mining for Strong Gravitational Lenses with Self-supervised Learning
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• A review of unsupervised learning in astronomy
• A variational encoder-decoder approach to precise spectroscopic age estimation for large Galactic surveys
• Automatic Classification of Galaxy Morphology: a rotationally invariant supervised machine learning method based on the UML-dataset
• Strong lens modelling: comparing and combining Bayesian neural networks and parametric profile fitting
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Applications of Machine Learning to Predicting Core-collapse Supernova Explosion Outcomes
• A machine learning based approach to gravitational lens identification with the International LOFAR Telescope
• Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning
• A Robust Study of High-Redshift Galaxies: Unsupervised Machine Learning for Characterising morphology with JWST up to z ~ 8
• Augmenting machine learning photometric redshifts with Gaussian mixture models
• Streamlined Lensed Quasar Identification in Multiband Images via Ensemble Networks
• Photometric identification of compact galaxies, stars and quasars using multiple neural networks
• Auto-identification of unphysical source reconstructions in strong gravitational lens modelling
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• Identifying outliers in astronomical images with unsupervised machine learning
• Gaia GraL: Gaia DR2 Gravitational Lens Systems. V. Doubly-imaged QSOs discovered from entropy and wavelets
• HOLISMOKES -- XI. Evaluation of supervised neural networks for strong-lens searches in ground-based imaging surveys
• AI-driven spatio-temporal engine for finding gravitationally lensed type Ia supernovae
• Finding quadruply imaged quasars with machine learning. I. Methods
• Classification algorithms applied to structure formation simulations
• The GALAH survey: Characterization of emission-line stars with spectral modelling using autoencoders
• Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping
• Enhanced Astronomical Source Classification with Integration of Attention Mechanisms and Vision Transformers
• Developing a Victorious Strategy to the Second Strong Gravitational Lensing Data Challenge
• Anisotropic strong lensing as a probe of dark matter self-interactions
• DeepGraviLens: a Multi-Modal Architecture for Classifying Gravitational Lensing Data
• CzSL: Learning from citizen science, experts and unlabelled data in astronomical image classification
• Dark Matter Subhalos, Strong Lensing and Machine Learning
• An efficient unsupervised classification model for galaxy morphology: Voting clustering based on coding from ConvNeXt large model
• Euclid preparation. LXVII. Deep learning true galaxy morphologies for weak lensing shear bias calibration
• Harvesting the Lyα forest with convolutional neural networks
• Model order reduction with neural networks: Application to laminar and turbulent flows
• Extracting the X-ray reverberation response functions from the AGN light curves using an autoencoder
• Automatic morphological classification of galaxies: convolutional autoencoder and bagging-based multiclustering model
• Deciphering galaxy images using machine vision -- Combining variational autoencoder and principal component analysis for feature extraction
• Periodic Astrometric Signal Recovery through Convolutional Autoencoders
• Lenses In VoicE (LIVE): Searching for strong gravitational lenses in the VOICE@VST survey using Convolutional Neural Networks
• Assessing Galaxy Rotation Kinematics: Insights from Convolutional Neural Networks on Velocity Variations
• Sifting the debris: Patterns in the SNR population with unsupervised ML methods
• Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources