A deep learning view of the census of galaxy clusters in IllustrisTNG

Abstract

The origin of the diverse population of galaxy clusters remains an unexplained aspect of large-scale structure formation and cluster evolution. We present a novel method of using X-ray images to identify cool core (CC), weak cool core (WCC), and non cool core (NCC) clusters of galaxies, that are defined by their central cooling times. We employ a convolutional neural network, ResNet-18, which is commonly used for image analysis, to classify clusters. We produce mock Chandra X-ray observations for a sample of 318 massive clusters drawn from the IllustrisTNG simulations. The network is trained and tested with low resolution mock Chandra images covering a central 1 Mpc square for the clusters in our sample. Without any spectral information, the deep learning algorithm is able to identify CC, WCC, and NCC clusters, achieving balanced accuracies (BAcc) of 92%, 81%, and 83%, respectively. The performance is superior to classification by conventional methods using central gas densities, with an average BAcc = 81%, or surface brightness concentrations, giving BAcc = 73%. We use Class Activation Mapping to localize discriminative regions for the classification decision. From this analysis, we observe that the network has utilized regions from cluster centers out to r~300 kpc and r~500 kpc to identify CC and NCC clusters, respectively. It may have recognized features in the intracluster medium that are associated with AGN feedback and disruptive major mergers.

arXiv commentAccepted for publication in MNRAS

References in corpus (60)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Observational Evidence of AGN Feedback
• Introducing the Illustris Project: Simulating the coevolution of dark and visible matter in the Universe
• First results from the IllustrisTNG simulations: matter and galaxy clustering
• First results from the IllustrisTNG simulations: the stellar mass content of groups and clusters of galaxies
• First results from the IllustrisTNG simulations: the galaxy color bimodality
• First results from the IllustrisTNG simulations: A tale of two elements -- chemical evolution of magnesium and europium
• First results from the IllustrisTNG simulations: radio haloes and magnetic fields
• First Results from the TNG50 Simulation: Galactic outflows driven by supernovae and black hole feedback
• Shocks and cold fronts in galaxy clusters
• Updated Atomic Data and Calculations for X-ray Spectroscopy
• Planck 2015 results. XXIV. Cosmology from Sunyaev-Zeldovich cluster counts
• Constraints on Cosmological Parameters from Future Galaxy Cluster Surveys
• What is a Cool-Core Cluster? A Detailed Analysis of the Cores of the X-ray Flux-Limited HIFLUGCS Cluster Sample
• Turbulent Heating in Galaxy Clusters Brightest in X-rays
• Scaling Properties of a Complete X-ray Selected Galaxy Group Sample
• An Entropy Threshold for Strong H-alpha and Radio Emission in the Cores of Galaxy Clusters
• Regulation of star formation in giant galaxies by precipitation, feedback, and conduction
• The Cool-Core Bias in X-ray Galaxy Cluster Samples I: Method And Application To HIFLUGCS
• Searching for Cool Core Clusters at High redshift
• Cool Core Clusters from Cosmological Simulations
• Identity Mappings in Deep Residual Networks
• Quantifying the Morphologies and Dynamical Evolution of Galaxy Clusters. II. Application to a Sample of ROSAT Clusters
• The Growth of Cool Cores and Evolution of Cooling Properties in a Sample of 83 Galaxy Clusters at 0.3 < z < 1.2 Selected from the SPT-SZ Survey
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• X-ray cavities in a sample of 83 SPT-selected clusters of galaxies: Tracing the evolution of AGN feedback in clusters of galaxies out to z=1.2
• The Remarkable Similarity of Massive Galaxy Clusters From z~0 to z~1.9
• Mapping small-scale temperature and abundance structures in the core of the Perseus cluster
• A Very Deep Chandra Observation of the Galaxy Group NGC 5813: AGN Shocks, Feedback, and Outburst History
• The fraction of cool-core clusters in X-ray vs. SZ samples using Chandra observations
• X-Ray morphological analysis of the Planck ESZ clusters
• Galaxy Morphology Classification with Deep Convolutional Neural Networks
• The cool core state of Planck SZ-selected clusters versus X-ray selected samples: evidence for cool core bias
• Chandra Temperature Map of Abell 754 and Constraints on Thermal Conduction
• Investigating the velocity structure and X-ray observable properties of simulated galaxy clusters with PHOX
• The duty cycle of radio-mode feedback in complete samples of clusters
• The uniformity and time-invariance of the intra-cluster metal distribution in galaxy clusters from the IllustrisTNG simulations
• A census of cool core galaxy clusters in IllustrisTNG
• The Onset of Thermally Unstable Cooling from the Hot Atmospheres of Giant Galaxies in Clusters - Constraints on Feedback Models
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• The impact of mergers on relaxed X-ray clusters - III. Effects on compact cool cores
• Conduction and the Star-Formation Threshold in Brightest Cluster Galaxies
• A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
• Rhapsody-G simulations I: the cool cores, hot gas and stellar content of massive galaxy clusters
• A Robust and Efficient Deep Learning Method for Dynamical Mass Measurements of Galaxy Clusters
• Back and forth from cool core to non-cool core: clues from radio-halos
• Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning
• Gas sloshing regulates and records the evolution of the Fornax Cluster
• Using X-Ray Morphological Parameters to Strengthen Galaxy Cluster Mass Estimates via Machine Learning
• Buoyant AGN bubbles in the quasi-isothermal potential of NGC 1399
• Extended X-ray study of M49: the frontier of the Virgo Cluster
• The polytropic state of the intracluster medium in the X-COP cluster sample
• Using deep Residual Networks to search for galaxy-Lyα emitter lens candidates based on spectroscopic-selection
• Removing Cool Cores and Central Metallicity Peaks in Galaxy Clusters with Powerful AGN Outbursts
• Weak lensing shear estimation beyond the shape-noise limit: a machine learning approach
• Neural network-based preprocessing to estimate the parameters of the X-ray emission of a single-temperature thermal plasma
• Chandra Observation of Abell 1142: A Cool-Core Cluster Lacking a Central Brightest Cluster Galaxy?
• X-ray cavities in the hot corona of the lenticular galaxy NGC~4477
• Mass Estimation of Galaxy Clusters with Deep Learning I: Sunyaev-Zel'dovich Effect
• The first astrophysical result of HISAKI: a search for the EUV He I lines a massive cool core cluster at z=0.7

Cited by in corpus (12)

• Deep Learning-Based Super-Resolution and De-Noising for XMM-Newton Images
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• The eROSITA view of the Abell 3391/95 field: The Northern Clump. The largest infalling structure in the longest known gas filament observed with eROSITA, XMM-Newton, and Chandra
• What to expect from dynamical modelling of cluster haloes II. Investigating dynamical state indicators with Random Forest
• Artificial Neural Network classification of asteroids in the M1:2 mean-motion resonance with Mars
• Contrastive Cross-Modal Pre-Training: A General Strategy for Small Sample Medical Imaging
• AGN feedback duty cycle in Planck SZ selected clusters using Chandra observations
• ERGO-ML: Comparing IllustrisTNG and HSC galaxy images via contrastive learning
• Galaxy stellar and total mass estimation using machine learning
• Identifying Galaxy Cluster Mergers with Deep Neural Networks using Idealized Compton-y and X-ray maps
• Estimating Cluster Masses from SDSS Multi-band Images with Transfer Learning
• Optical Wavelength Guided Self-Supervised Feature Learning For Galaxy Cluster Richness Estimate