Deep-CEE I: Fishing for Galaxy Clusters with Deep Neural Nets

Abstract

We introduce Deep-CEE (Deep Learning for Galaxy Cluster Extraction and Evaluation), a proof of concept for a novel deep learning technique, applied directly to wide-field colour imaging to search for galaxy clusters, without the need for photometric catalogues. This technique is complementary to traditional methods and could also be used in combination with them to confirm galaxy cluster candidates. We use a state-of-the-art probabilistic algorithm, adapted to localize and classify galaxy clusters from other astronomical objects in SDSS imaging. As there is an abundance of labelled data for galaxy clusters from previous classifications in publicly available catalogues, we do not need to rely on simulated data. This means we keep our training data as realistic as possible, which is advantageous when training a deep learning algorithm. Ultimately, we will apply our model to surveys such as LSST and Euclid to probe wider and deeper into unexplored regions of the Universe. This will produce large samples of both high redshift and low mass clusters, which can be utilized to constrain both environment-driven galaxy evolution and cosmology.

arXiv commentAccepted by MNRAS on 2nd October 2019. 18 pages; doi:10.1093/mnras/stz2936

References in corpus (63)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• Planck 2015 results. XIII. Cosmological parameters
• An overview of gradient descent optimization algorithms
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• SDSS-III: Massive Spectroscopic Surveys of the Distant Universe, the Milky Way Galaxy, and Extra-Solar Planetary Systems
• The Ninth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-III Baryon Oscillation Spectroscopic Survey
• The Eighth Data Release of the Sloan Digital Sky Survey: First Data from SDSS-III
• Activation Functions: Comparison of trends in Practice and Research for Deep Learning
• A Cosmology Calculator for the World Wide Web
• SparsePak: A Formatted Fiber Field Unit for The WIYN Telescope Bench Spectrograph. I. Design, Construction, and Calibration
• redMaPPer I: Algorithm and SDSS DR8 Catalog
• Galaxy Clusters Discovered via the Sunyaev-Zel'dovich Effect in the 2500-square-degree SPT-SZ survey
• The 10 Meter South Pole Telescope
• The ROSAT Brightest Cluster Sample (BCS) - I. The compilation of the sample and the cluster log N-log S distribution
• The ROSAT-ESO Flux Limited X-ray (REFLEX) Galaxy Cluster Survey. V. The cluster catalogue
• A New Method For Galaxy Cluster Detection I: The Algorithm
• A MaxBCG Catalog of 13,823 Galaxy Clusters from the Sloan Digital Sky Survey
• The Average Mass-to-Light Profile of Galaxy Clusters
• Planck 2013 results. XXIX. Planck catalogue of Sunyaev-Zeldovich sources
• MACS: A quest for the most massive galaxy clusters in the universe
• A catalog of 132,684 clusters of galaxies identified from Sloan Digital Sky Survey III
• The Red-Sequence Cluster Survey I: The Survey and Cluster Catalogs for Patches RCS0926+37 and RCS1327+29
• The redMaPPer Galaxy Cluster Catalog From DES Science Verification Data
• Galaxy Clusters Selected with the Sunyaev-Zel'dovich Effect from 2008 South Pole Telescope Observations
• Galaxy clusters discovered with a Sunyaev-Zel'dovich effect survey
• Fast R-CNN
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• LoCuSS: Subaru Weak Lensing Study of 30 Galaxy Clusters
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• The XMM Cluster Survey: Optical analysis methodology and the first data release
• The Atacama Cosmology Telescope: The Two-Season ACTPol Sunyaev-Zel'dovich Effect Selected Cluster Catalog
• Precision measurement of the integrated luminosity of the data taken by BESIII at center of mass energies between 3.810 GeV and 4.600 GeV
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• First Results On Shear-Selected Clusters From the Deep Lens Survey: Optical Imaging, Spectroscopy, and X-ray Followup
• Speed/accuracy trade-offs for modern convolutional object detectors
• The Bright End of the z~9 and z~10 UV Luminosity Functions using all five CANDELS Fields
• The XXL Survey XX: The 365 cluster catalogue
• Galaxy Morphology Classification with Deep Convolutional Neural Networks
• Substructure and dynamical state of 2092 rich clusters of galaxies derived from photometric data
• Weak lensing cosmology with convolutional neural networks on noisy data
• Thresholding Classifiers to Maximize F1 Score
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• The Imprint of Reionization on the Star Formation Histories of Dwarf Galaxies
• Deep Convolutional Neural Networks as strong gravitational lens detectors
• Instance-aware Semantic Segmentation via Multi-task Network Cascades
• A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
• Near-infrared evolution of brightest cluster galaxies in the most X-ray luminous clusters since z=1
• The central 1000 AU of a pre-stellar core revealed with ALMA. I. 1.3 mm continuum observations
• Using Convolutional Neural Networks to identify Gravitational Lenses in Astronomical images
• Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning
• Multiscale probability mapping: groups, clusters and an algorithmic search for filaments in SDSS
• Euclid Mission: building of a Reference Survey
• Testing Convolutional Neural Networks for finding strong gravitational lenses in KiDS
• Planck intermediate results. XXVII. High-redshift infrared galaxy overdensity candidates and lensed sources discovered by Planck and confirmed by Herschel-SPIRE
• The 2XMMi/SDSS Galaxy Cluster Survey I. The first cluster sample and X-ray luminosity-temperature relation
• An application of machine learning techniques to galaxy cluster mass estimation using the MACSIS simulations
• Learning non-maximum suppression
• Generative deep fields: arbitrarily sized, random synthetic astronomical images through deep learning
• Photometric Redshift Analysis using Supervised Learning Algorithms and Deep Learning
• Taming the Cross Entropy Loss

Cited by in corpus (8)

• YOLO-CL: Galaxy cluster detection in the SDSS with deep machine learning
• Quasar Sightline and Galaxy Evolution (QSAGE) survey -- II. Galaxy overdensities around UV luminous quasars at z=1-2
• Constraining cosmological parameters using void statistics from the SDSS survey
• YOLO-CL cluster detection in the Rubin/LSST DC2 simulation
• Z-Sequence: Photometric redshift predictions for galaxy clusters with sequential random k-nearest neighbours
• The Final Frontier: Deep Learning in Space
• AutoEnRichness: A hybrid empirical and analytical approach for estimating the richness of galaxy clusters
• Deep Convolutional Transform Learning -- Extended version