Galaxy cluster mass estimation with deep learning and hydrodynamical simulations

Abstract

We evaluate the ability of Convolutional Neural Networks (CNNs) to predict galaxy cluster masses in the BAHAMAS hydrodynamical simulations. We train four separate single-channel networks using: stellar mass, soft X-ray flux, bolometric X-ray flux, and the Compton $y$ parameter as observational tracers, respectively. Our training set consists of $\sim$4800 synthetic cluster images generated from the simulation, while an additional $\sim$3200 images form a validation set and a test set, each with 1600 images. In order to mimic real observation, these images also contain uncorrelated structures located within 50 Mpc in front and behind clusters and seen in projection, as well as instrumental systematics including noise and smoothing. In addition to CNNs for all the four observables, we also train a `multi-channel' CNN by combining the four observational tracers. The learning curves of all the five CNNs converge within 1000 epochs. The resulting predictions are especially precise for halo masses in the range $10^{13.25}{M}_{\odot }<M<10^{14.5}{M}_{\odot }$, where all five networks produce mean mass biases of order $\approx$1\% with a scatter of $\lesssim$20\%. The network trained with Compton $y$ parameter maps yields the most precise predictions. We interpret the network's behaviour using two diagnostic tests to determine which features are used to predict cluster mass. The CNN trained with stellar mass images detect galaxies (not surprisingly), while CNNs trained with gas-based tracers utilise the shape of the signal to estimate cluster mass.

14 pages, 11 figures, 2 tables, Accepted for Publication on MNRAS

References in corpus (45)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• The Seventh Data Release of the Sloan Digital Sky Survey
• Nine-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Parameter Results
• Constraints on the relationship between stellar mass and halo mass at low and high redshift
• Cosmological Parameters from Observations of Galaxy Clusters
• Analytic model for galaxy and dark matter clustering
• Halo occupation numbers and galaxy bias
• Tracing cosmic evolution with clusters of galaxies
• The physics driving the cosmic star formation history
• Galaxy Clusters Discovered via the Sunyaev-Zel'dovich Effect in the 2500-square-degree SPT-SZ survey
• Galaxy cluster X-ray luminosity scaling relations from a representative local sample (REXCESS)
• New constraints on the evolution of the stellar-to-dark matter connection: a combined analysis of galaxy-galaxy lensing, clustering, and stellar mass functions from z=0.2 to z=1
• The BAHAMAS project: Calibrated hydrodynamical simulations for large-scale structure cosmology
• Planck 2015 results. XXIV. Cosmology from Sunyaev-Zeldovich cluster counts
• The Canadian Cluster Comparison Project: detailed study of systematics and updated weak lensing masses
• On the Accuracy of Weak Lensing Cluster Mass Reconstructions
• Cosmological constraints from the X-ray gas mass fraction in relaxed lensing clusters observed with Chandra
• CLASH: Weak-Lensing Shear-and-Magnification Analysis of 20 Galaxy Clusters
• Weighing the Giants - I. Weak-lensing masses for 51 massive galaxy clusters: project overview, data analysis methods and cluster images
• Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
• LoCuSS: Comparison of Observed X-ray and Lensing Galaxy Cluster Scaling Relations with Simulations
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Mapping stellar content to dark matter halos using galaxy clustering and galaxy-galaxy lensing in the SDSS DR7
• Planck 2015 results. XXII. A map of the thermal Sunyaev-Zeldovich effect
• Cosmological simulations of galaxy clusters
• The BAHAMAS project: the CMB--large-scale structure tension and the roles of massive neutrinos and galaxy formation
• Gas Clumping in the Outskirts of Lambda-CDM Clusters
• The Lx-Yx Relation: Using Galaxy Cluster X-Ray Luminosity as a Robust, Low Scatter Mass Proxy
• Evidence for AGN Feedback in Galaxy Clusters and Groups
• Machine Learning in Astronomy: a practical overview
• LoCuSS: Testing hydrostatic equilibrium in galaxy clusters
• The impact of baryons on massive galaxy clusters: halo structure and cluster mass estimates
• Fast cosmic web simulations with generative adversarial networks
• Mock weak lensing analysis of simulated galaxy clusters: bias and scatter in mass and concentration
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Weak lensing measurement of galaxy clusters in the CFHTLS-Wide survey
• Measuring cluster masses with CMB lensing: a statistical approach
• The Atacama Cosmology Telescope: Beam Measurements and the Microwave Brightness Temperatures of Uranus and Saturn
• An application of machine learning techniques to galaxy cluster mass estimation using the MACSIS simulations
• The galaxy cluster Ysz-Lx and Ysz-M relations from the WMAP 5-yr data
• Using X-Ray Morphological Parameters to Strengthen Galaxy Cluster Mass Estimates via Machine Learning
• Center-Excised X-ray Luminosity as an Efficient Mass Proxy for Future Galaxy Cluster Surveys
• Multiwavelength cluster mass estimates and machine learning
• An analysis of galaxy cluster mis-centring using cosmological hydrodynamic simulations
• Mass Estimation of Galaxy Clusters with Deep Learning I: Sunyaev-Zel'dovich Effect

Cited by in corpus (29)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• The CAMELS project: public data release
• Pushing automated morphological classifications to their limits with the Dark Energy Survey
• A Deep Learning Approach to Infer Galaxy Cluster Masses from Planck Compton$-y$ parameter maps
• Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• What to expect from dynamical modelling of cluster haloes II. Investigating dynamical state indicators with Random Forest
• Massive Dark Matter Halos at High Redshift: Implications for Observations in the JWST Era
• Inferring galaxy dark halo properties from visible matter with Machine Learning
• The Three Hundred project: A Machine Learning method to infer clusters of galaxies mass radial profiles from mock Sunyaev-Zel'dovich maps
• Benchmarks and Explanations for Deep Learning Estimates of X-ray Galaxy Cluster Masses
• Mass Estimation of Planck Galaxy Clusters using Deep Learning
• Cosmology with Galaxy Cluster Properties using Machine Learning
• An approach to cold dark matter deviation and the $H_0$ tension problem by using machine learning
• CHEX-MATE: A non-parametric deep learning technique to deproject and deconvolve galaxy cluster X-ray temperature profiles
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Intrinsic mass-richness relation of clusters from THE THREE HUNDRED hydrodynamic simulations
• Identifying Galaxy Cluster Mergers with Deep Neural Networks using Idealized Compton-y and X-ray maps
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• A Generative Model for Realistic Galaxy Cluster X-ray Morphologies
• Inferring halo masses with Graph Neural Networks
• Deriving accurate galaxy cluster masses using X-ray thermodynamic profiles and graph neural networks
• Cluster optical depth and pairwise velocity estimation using machine learning
• AutoEnRichness: A hybrid empirical and analytical approach for estimating the richness of galaxy clusters
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• Estimating the triaxiality of massive clusters from 2D observables in MillenniumTNG with machine learning
• The life and times of dark matter haloes: what will I be when I grow up?
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods
• Generating Galaxy Clusters Mass Density Maps from Mock Multiview Images via Deep Learning