Using X-Ray Morphological Parameters to Strengthen Galaxy Cluster Mass Estimates via Machine Learning

Abstract

We present a machine learning approach for estimating galaxy cluster masses, trained using both Chandra and eROSITA mock X-ray observations of 2,041 clusters from the Magneticum simulations. We train a random forest regressor, an ensemble learning method based on decision tree regression, to predict cluster masses using an input feature set. The feature set uses core-excised X-ray luminosity and a variety of morphological parameters, including surface brightness concentration, smoothness, asymmetry, power ratios, and ellipticity. The regressor is cross-validated and calibrated on a training sample of 1,615 clusters (80% of sample), and then results are reported as applied to a test sample of 426 clusters (20% of sample). This procedure is performed for two different mock observation series in an effort to bracket the potential enhancement in mass predictions that can be made possible by including dynamical state information. The first series is computed from idealized Chandra-like mock cluster observations, with high spatial resolution, long exposure time (1 Ms), and the absence of background. The second series is computed from realistic-condition eROSITA mocks with lower spatial resolution, short exposures (2 ks), instrument effects, and background photons modeled. We report a 20% reduction in the mass estimation scatter when either series is used in our random forest model compared to a standard regression model that only employs core-excised luminosity. The morphological parameters that hold the highest feature importance are smoothness, asymmetry, and surface brightness concentration. Hence, these parameters, which encode the dynamical state of the cluster, can be used to make more accurate predictions of cluster masses in upcoming surveys, offering a crucial step forward for cosmological analyses.

12 pages, 5 figures, 3 tables. Accepted to ApJ

References in corpus (74)

• Scikit-learn: Machine Learning in Python
• Seven-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Interpretation
• Populating a cluster of galaxies - I. Results at z=0
• Dark Energy Survey Year 1 Results: Cosmological Constraints from Galaxy Clustering and Weak Lensing
• Substructures in hydrodynamical cluster simulations
• The Relationship Between Stellar Light Distributions of Galaxies and their Formation Histories
• Formation of Galaxy Clusters
• A New Non-Parametric Approach to Galaxy Morphological Classification
• Galaxy cluster X-ray luminosity scaling relations from a representative local sample (REXCESS)
• Galaxy morphology to I=25 mag in the Hubble Deep Field
• Testing X-ray Measurements of Galaxy Clusters with Cosmological Simulations
• A New Robust Low-Scatter X-ray Mass Indicator for Clusters of Galaxies
• Scaling relations for galaxy clusters in the Millennium-XXL simulation
• Planck 2015 results. XXIV. Cosmology from Sunyaev-Zeldovich cluster counts
• Residual Gas Motions in the Intracluster Medium and Bias in Hydrostatic Measurements of Mass Profiles of Clusters
• Haloes gone MAD: The Halo-Finder Comparison Project
• eROSITA Science Book: Mapping the Structure of the Energetic Universe
• The Canadian Cluster Comparison Project: detailed study of systematics and updated weak lensing masses
• Systematics in the X-ray Cluster Mass Estimators
• Weighing the Giants IV: Cosmology and Neutrino Mass
• The galaxy cluster mass scale and its impact on cosmological constraints from the cluster population
• Weighing the Giants - I. Weak-lensing masses for 51 massive galaxy clusters: project overview, data analysis methods and cluster images
• Connecting Angular Momentum and Galactic Dynamics: The complex Interplay between Spin, Mass, and Morphology
• Cosmological Constraints from Galaxy Clusters in the 2500 square-degree SPT-SZ Survey
• Halo mass function: Baryon impact, fitting formulae and implications for cluster cosmology
• The Cool-Core Bias in X-ray Galaxy Cluster Samples I: Method And Application To HIFLUGCS
• On the nature of hydrostatic equilibrium in galaxy clusters
• Searching for Cool Core Clusters at High redshift
• SZ effects in the Magneticum Pathfinder Simulation: Comparison with the Planck, SPT, and ACT results
• Universal thermodynamic properties of the intracluster medium over two decades in radius in the X-COP sample
• A refined sub-grid model for black hole accretion and AGN feedback in large cosmological simulations
• Non-thermal pressure support in X-COP galaxy clusters
• The X-ray cluster survey with eROSITA: forecasts for cosmology, cluster physics and primordial non-Gaussianity
• XMM-Newton and Chandra Cross Calibration Using HIFLUGCS Galaxy Clusters: Systematic Temperature Differences and Cosmological Impact
• Hydrodynamic Simulation of Non-thermal Pressure Profiles of Galaxy Clusters
• Quantifying the Morphologies and Dynamical Evolution of Galaxy Clusters. I. The Method
• The Lx-Yx Relation: Using Galaxy Cluster X-Ray Luminosity as a Robust, Low Scatter Mass Proxy
• Planck early results. IX. XMM-Newton follow-up for validation of Planck cluster candidates
• Hydrostatic mass profiles in X-COP galaxy clusters
• The FABLE simulations: A feedback model for galaxies, groups and clusters
• HIFLUGCS: Galaxy cluster scaling relations between X-ray luminosity, gas mass, cluster radius, and velocity dispersion
• Origin and properties of dual and offset active galactic nuclei in a cosmological simulation at z=2
• Weighing Galaxy Clusters with Gas. II. On the Origin of Hydrostatic Mass Bias in LambdaCDM Galaxy Clusters
• X-Ray morphological analysis of the Planck ESZ clusters
• The Co-Evolution of Total Density Profiles and Central Dark Matter Fractions in Simulated Early-Type Galaxies
• Investigating the velocity structure and X-ray observable properties of simulated galaxy clusters with PHOX
• Cosmology and Astrophysics from Relaxed Galaxy Clusters I: Sample Selection
• Dark Energy from the Thermal Sunyaev Zeldovich Power Spectrum
• The impact of baryons on massive galaxy clusters: halo structure and cluster mass estimates
• LoCuSS: The Sunyaev-Zel'dovich Effect and Weak Lensing Mass Scaling Relation
• Cosmological constraints from Planck galaxy clusters with CMB lensing mass bias calibration
• Cosmology and astrophysics from relaxed galaxy clusters - IV: Robustly calibrating hydrostatic masses with weak lensing
• Sunyaev-Zel'dovich Effect and X-ray Scaling Relations from Weak-Lensing Mass Calibration of 32 SPT Selected Galaxy Clusters
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Temperature Structure of the Intra-Cluster Medium from SPH and AMR simulations
• Analytical model for non-thermal pressure in galaxy clusters - III. Removing the hydrostatic mass bias
• A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
• Weighing Galaxy Clusters with Gas. I. On the Methods of Computing Hydrostatic Mass Bias
• Observing simulated galaxy clusters with PHOX: a novel X-ray photon simulator
• Constraining galaxy cluster temperatures and redshifts with eROSITA survey data
• Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning
• Forecasts on dark energy from the X-ray cluster survey with eROSITA: constraints from counts and clustering
• Synthetic simulations of the extragalactic sky seen by eROSITA. I. Pre-launch selection functions from Monte-Carlo simulations
• Prediction of galaxy halo masses in SDSS DR7 via a machine learning approach
• Substructure and Scatter in the Mass-Temperature Relations of Simulated Clusters
• An application of machine learning techniques to galaxy cluster mass estimation using the MACSIS simulations
• Mass Calibration of Optically Selected DES clusters using a Measurement of CMB-Cluster Lensing with SPTpol Data
• Center-Excised X-ray Luminosity as an Efficient Mass Proxy for Future Galaxy Cluster Surveys
• The Fundamental Relation between Halo Mass and Galaxy Group Properties
• Reconciling Planck cluster counts and cosmology? Chandra/XMM instrumental calibration and hydrostatic mass bias
• New constraints on the mass bias of galaxy clusters from the power spectra of the thermal Sunyaev-Zeldovich effect and cosmic shear
• Covariance in the Thermal SZ-Weak Lensing Mass Scaling Relation of Galaxy Clusters
• Multiwavelength cluster mass estimates and machine learning
• Cluster Cosmology with the Velocity Distribution Function of the HeCS-SZ Sample

Cited by in corpus (27)

• Spatially-Resolved Spectroscopic Properties of Low-Redshift Star-Forming Galaxies
• The Three Hundred Project: Dynamical state of galaxy clusters and morphology from multi-wavelength synthetic maps
• Galaxy cluster mass estimation with deep learning and hydrodynamical simulations
• The Three Hundred Project: quest of clusters of galaxies morphology and dynamical state through Zernike Polynomials
• Gas distribution from clusters to filaments in IllustrisTNG
• A deep learning view of the census of galaxy clusters in IllustrisTNG
• 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
• Aging Halos: Implications of the Magnitude Gap on Conditional Statistics of Stellar and Gas Properties of Massive Halos
• Scatter in Sunyaev--Zel'dovich effect scaling relations explained by inter-cluster variance in mass accretion histories
• DeepSZ: Identification of Sunyaev-Zel'dovich Galaxy Clusters using Deep Learning
• Predicting the redshift of gamma-ray loud AGNs using supervised machine learning
• Deep learning for Sunyaev-Zel'dovich detection in Planck
• KLLR: A scale-dependent, multivariate model class for regression analysis
• Benchmarks and Explanations for Deep Learning Estimates of X-ray Galaxy Cluster Masses
• Emulating Sunyaev-Zeldovich Images of Galaxy Clusters using Auto-Encoders
• The Importance of Being Interpretable: Toward An Understandable Machine Learning Encoder for Galaxy Cluster Cosmology
• A Machine Learning Approach to Enhancing eROSITA Observations
• Identifying Galaxy Cluster Mergers with Deep Neural Networks using Idealized Compton-y and X-ray maps
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• The probability distribution of 3-D shapes of galaxy clusters from 2-D X-ray images
• Inferring halo masses with Graph Neural Networks
• Cluster optical depth and pairwise velocity estimation using machine learning
• Deriving accurate galaxy cluster masses using X-ray thermodynamic profiles and graph neural networks
• Do gas-poor galaxy clusters have different galaxy populations? The positive covariance of hot and cold baryons
• Estimating the triaxiality of massive clusters from 2D observables in MillenniumTNG with machine learning
• Random Forests applied to High Precision Photometry Analysis with Spitzer IRAC