CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding

Abstract

Galaxy-scale strong gravitational lensing is not only a valuable probe of the dark matter distribution of massive galaxies, but can also provide valuable cosmological constraints, either by studying the population of strong lenses or by measuring time delays in lensed quasars. Due to the rarity of galaxy-scale strongly lensed systems, fast and reliable automated lens finding methods will be essential in the era of large surveys such as LSST, Euclid, and WFIRST. To tackle this challenge, we introduce CMU DeepLens, a new fully automated galaxy-galaxy lens finding method based on Deep Learning. This supervised machine learning approach does not require any tuning after the training step which only requires realistic image simulations of strongly lensed systems. We train and validate our model on a set of 20,000 LSST-like mock observations including a range of lensed systems of various sizes and signal-to-noise ratios (S/N). We find on our simulated data set that for a rejection rate of non-lenses of 99%, a completeness of 90% can be achieved for lenses with Einstein radii larger than 1.4" and S/N larger than 20 on individual $g$-band LSST exposures. Finally, we emphasize the importance of realistically complex simulations for training such machine learning methods by demonstrating that the performance of models of significantly different complexities cannot be distinguished on simpler simulations. We make our code publicly available at https://github.com/McWilliamsCenter/CMUDeepLens .

12 pages, 9 figures, submitted to MNRAS

References in corpus (15)

• Improving neural networks by preventing co-adaptation of feature detectors
• Wide-Field InfrarRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA 2015 Report
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• H0LiCOW V. New COSMOGRAIL time delays of HE0435-1223: $H_0$ to 3.8% precision from strong lensing in a flat $\Lambda$CDM model
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• The CFHTLS Strong Lensing Legacy Survey: I. Survey overview and T0002 release sample
• RingFinder: automated detection of galaxy-scale gravitational lenses in ground-based multi-filter imaging data
• Models of the Cosmic Horseshoe Gravitational Lens
• Arcfinder: An algorithm for the automatic detection of gravitational arcs
• A PCA-based automated finder for galaxy-scale strong lenses
• A Neural Network Gravitational Arc Finder based on the Mediatrix filamentation Method
• A method to search for strong galaxy-galaxy lenses in optical imaging surveys
• Extensive light profile fitting of galaxy-scale strong lenses

Cited by in corpus (130)

• Machine learning and the physical sciences
• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• A SHARP view of H0LiCOW: $H_0$ from three time-delay gravitational lens systems with adaptive optics imaging
• Learning to Predict the Cosmological Structure Formation
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• The Strong Gravitational Lens Finding Challenge
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Finding strong lenses in CFHTLS using convolutional neural networks
• Finding high-redshift strong lenses in DES using convolutional neural networks
• Finding Strong Gravitational Lenses in the DESI DECam Legacy Survey
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Discovering New Strong Gravitational Lenses in the DESI Legacy Imaging Surveys
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Deep Convolutional Neural Networks as strong gravitational lens detectors
• Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
• HOLISMOKES -- II. Identifying galaxy-scale strong gravitational lenses in Pan-STARRS using convolutional neural networks
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• What can Machine Learning tell us about the background expansion of the Universe?
• LensExtractor: A Convolutional Neural Network in Search of Strong Gravitational Lenses
• A Robust and Efficient Deep Learning Method for Dynamical Mass Measurements of Galaxy Clusters
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• COSMOGRAIL XVII: Time delays for the quadruply imaged quasar PG 1115+080
• Identification of Low Surface Brightness Tidal Features in Galaxies Using Convolutional Neural Networks
• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• Strong lens systems search in the Dark Energy Survey using Convolutional Neural Networks
• Photometry of high-redshift blended galaxies using deep learning
• High-quality strong lens candidates in the final Kilo Degree survey footprint
• HOLISMOKES. VI. New galaxy-scale strong lens candidates from the HSC-SSP imaging survey
• Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
• Mining for Strong Gravitational Lenses with Self-supervised Learning
• Gaia GraL: Gaia DR2 Gravitational Lens Systems. III. A systematic blind search for new lensed systems
• Fast Point Spread Function Modeling with Deep Learning
• Strong gravitational lensing and microlensing of supernovae
• HOLISMOKES. VIII. High-redshift, strong-lens search in the Hyper Suprime-Cam Subaru Strategic Program
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Testing Convolutional Neural Networks for finding strong gravitational lenses in KiDS
• KiDS-SQuaD II: Machine learning selection of bright extragalactic objects to search for new gravitationally lensed quasars
• The use of convolutional neural networks for modelling large optically-selected strong galaxy-lens samples
• Using convolutional neural networks to predict galaxy metallicity from three-color images
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3
• Galaxy cluster mass estimation with deep learning and hydrodynamical simulations
• HOLISMOKES -- IV. Efficient mass modeling of strong lenses through deep learning
• Constraining the microlensing effect on time delays with new time-delay prediction model in $H_0$ measurements
• Machine Learning Applied to the Reionization History of the Universe in the 21 cm Signal
• Sensitivity of strong lensing observations to dark matter substructure: a case study with Euclid
• A deep learning view of the census of galaxy clusters in IllustrisTNG
• Strong lens modelling: comparing and combining Bayesian neural networks and parametric profile fitting
• CASI: A Convolutional Neural Network Approach for Shell Identification
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Identification of tidal features in deep optical galaxy images with Convolutional Neural Networks
• Approximate Bayesian Uncertainties on Deep Learning Dynamical Mass Estimates of Galaxy Clusters
• Quasar microlensing light curve analysis using deep machine learning
• 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 $z\sim 5$
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• A machine learning based approach to gravitational lens identification with the International LOFAR Telescope
• Automatic detection of low surface brightness galaxies from SDSS images
• New Strong Gravitational Lenses from the DESI Legacy Imaging Surveys Data Release 9
• Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size
• Identification of BASS DR3 Sources as Stars, Galaxies and Quasars by XGBoost
• Comparison of Observed Galaxy Properties with Semianalytic Model Predictions using Machine Learning
• 21st Century Statistical and Computational Challenges in Astrophysics
• Automated Lensing Learner: Automated Strong Lensing Identification with a Computer Vision Technique
• The impact of human expert visual inspection on the discovery of strong gravitational lenses
• Using deep Residual Networks to search for galaxy-Lyα emitter lens candidates based on spectroscopic-selection
• Identification of Galaxy-Galaxy Strong Lens Candidates in the DECam Local Volume Exploration Survey Using Machine Learning
• HOLISMOKES -- IX. Neural network inference of strong-lens parameters and uncertainties from ground-based images
• Finding Strong Gravitational Lenses Through Self-Attention
• HOLISMOKES -- X. Comparison between neural network and semi-automated traditional modeling of strong lenses
• Discovering strongly lensed quasar candidates with catalogue-based methods from DESI Legacy Surveys
• An extended catalog of galaxy-galaxy strong gravitational lenses discovered in DES using convolutional neural networks
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• The DES Bright Arcs Survey: Candidate Strongly Lensed Galaxy Systems from the Dark Energy Survey 5,000 Sq. Deg. Footprint
• Models of gravitational lens candidates from Space Warps CFHTLS
• Detection of Strongly Lensed Arcs in Galaxy Clusters with Transformers
• 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
• Deep Learning in Wide-field Surveys: Fast Analysis of Strong Lenses in Ground-based Cosmic Experiments
• Identification of Grand-design and Flocculent Spirals from SDSS using Convolutional Neural network
• Assessment of astronomical images using combined machine learning models
• Galaxy stellar and total mass estimation using machine learning
• A Bayesian Approach to Strong Lens Finding in the Era of Wide-area Surveys
• Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks
• Gaia GraL II - Gaia DR2 Gravitational Lens Systems: The Known Multiply Imaged Quasars
• Deep Transfer Learning for Classification of Variable Sources
• Resolving the Vicinity of Supermassive Black Holes with Gravitational Microlensing
• Serendipitous discovery of a strong-lensed galaxy in integral field spectroscopy from MUSE
• HOLISMOKES XIII: Strong-lens candidates at all mass scales and their environments from the Hyper-Suprime Cam and deep learning
• Developing a Victorious Strategy to the Second Strong Gravitational Lensing Data Challenge
• A Comparative Study of Convolutional Neural Networks for the Detection of Strong Gravitational Lensing
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• Uncovering Tidal Treasures: Automated Classification of Faint Tidal Features in DECaLS Data
• Deep Learning Blazar Classification based on Multi-frequency Spectral Energy Distribution Data
• Convolutional Neural Networks for Spectroscopic Redshift Estimation on Euclid Data
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Searching for galaxy-scale strong-lenses in galaxy clusters with deep networks -- I: methodology and network performance
• COOL-LAMPS II. Characterizing the Size and Star Formation History of a Bright Strongly Lensed Early-Type Galaxy at Redshift 1.02
• Investigation of stellar magnetic activity using variational autoencoder based on low-resolution spectroscopic survey
• Lessons from a blind study of simulated lenses: image reconstructions do not always reproduce true convergence
• Variational Inference for Deblending Crowded Starfields
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• AGNet: Weighing Black Holes with Deep Learning
• Analysis of Ring Galaxies Detected Using Deep Learning with Real and Simulated Data
• The COSMOS-Web Lens Survey (COWLS) III: forecasts versus data
• Searching for Sub-Second Stellar Variability with Wide-Field Star Trails and Deep Learning
• A proof-of-concept neural network for inferring parameters of a black hole from partial interferometric images of its shadow
• HOLISMOKES XV. Search for strong gravitational lenses combining ground-based and space-based imaging
• HOLISMOKES XVI: Lens search in HSC-PDR3 with a neural network committee and post-processing for false-positive removal
• Searching for strong lensing by late-type galaxies in UNIONS
• The Galaxy Activity, Torus, and Outflow Survey (GATOS). Black hole mass estimation using machine learning
• A Modular Deep Learning Pipeline for Galaxy-Scale Strong Gravitational Lens Detection and Modeling
• Transformers as Strong Lens Detectors- From Simulation to Surveys
• Reducing false positives in strong lens detection through effective augmentation and ensemble learning
• Galaxies OBserved as Low-luminosity Identified Nebulae (GOBLIN): a catalog of 43,000 high-probability dwarf galaxy candidates in the UNIONS survey
• Estimating Cluster Masses from SDSS Multi-band Images with Transfer Learning
• Search for strong galaxy-galaxy lensing in SDSS-III BOSS
• AGNet: Weighing Black Holes with Machine Learning
• Sparse logistic regression for RR Lyrae vs binaries classification
• Exotic Image Formation in Strong Gravitational Lensing by Clusters of Galaxies -- III: Statistics with HUDF
• Gaia GraL: Gaia gravitational lens systems IX. Using XGBoost to explore the Gaia Focused Product Release GravLens catalogue
• Timing the last major merger of galaxy clusters with large halo sparsity
• Determining the Dark Matter distribution in galaxies with Deep Learning
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• Sifting the debris: Patterns in the SNR population with unsupervised ML methods