An application of machine learning techniques to galaxy cluster mass estimation using the MACSIS simulations

Abstract

Machine learning (ML) techniques, in particular supervised regression algorithms, are a promising new way to use multiple observables to predict a cluster's mass or other key features. To investigate this approach we use the \textsc{MACSIS} sample of simulated hydrodynamical galaxy clusters to train a variety of ML models, mimicking different datasets. We find that compared to predicting the cluster mass from the $\sigma -M$ relation, the scatter in the predicted-to-true mass ratio is reduced by a factor of 4, from $0.130\pm 0.004$ dex ($\simeq 35$ per cent) to $0.031\pm 0.001$ dex ($\simeq 7$ per cent) when using the same, interloper contaminated, spectroscopic galaxy sample. Interestingly, omitting line-of-sight galaxy velocities from the training set has no effect on the scatter when the galaxies are taken from within $r_{200c}$. We also train ML models to reproduce estimated masses derived from mock X-ray and weak lensing analyses. While the weak lensing masses can be recovered with a similar scatter to that when training on the true mass, the hydrostatic mass suffers from significantly higher scatter of $\simeq 0.13$ dex ($\simeq 35$ per cent). Training models using dark matter only simulations does not significantly increase the scatter in predicted cluster mass compared to training on simulated clusters with hydrodynamics. In summary, we find ML techniques to offer a powerful method to predict masses for large samples of clusters, a vital requirement for cosmological analysis with future surveys.

arXiv commentSubmitted to MNRAS, 12 pages, 7 figures, example pipeline can be found here: https://github.com/TomArmitage/ML_Template

References in corpus (60)

• Scikit-learn: Machine Learning in Python
• The cosmological simulation code GADGET-2
• Populating a cluster of galaxies - I. Results at z=0
• Planck 2013 results. I. Overview of products and scientific results
• Chandra sample of nearby relaxed galaxy clusters: mass, gas fraction, and mass-temperature relation
• Observational Probes of Cosmic Acceleration
• Cosmological Parameters from Observations of Galaxy Clusters
• Substructures in hydrodynamical cluster simulations
• The effect of photo-ionization on the cooling rates of enriched, astrophysical plasmas
• Formation of Galaxy Clusters
• Cosmological simulations of the growth of supermassive black holes and feedback from active galactic nuclei: method and tests
• The physics driving the cosmic star formation history
• Chandra Cluster Cosmology Project II: Samples and X-ray Data Reduction
• Galaxy cluster X-ray luminosity scaling relations from a representative local sample (REXCESS)
• On the relation between the Schmidt and Kennicutt-Schmidt star formation laws and its implications for numerical simulations
• Planck 2013 results. XX. Cosmology from Sunyaev-Zeldovich cluster counts
• The BAHAMAS project: Calibrated hydrodynamical simulations for large-scale structure cosmology
• The spin and shape of dark matter haloes in the Millennium simulation of a LambdaCDM universe
• Simulating galactic outflows with kinetic supernova feedback
• Residual Gas Motions in the Intracluster Medium and Bias in Hydrostatic Measurements of Mass Profiles of Clusters
• The Canadian Cluster Comparison Project: detailed study of systematics and updated weak lensing masses
• Evolution of galaxy stellar masses and star formation rates in the EAGLE simulations
• The distribution of stellar mass in the low-redshift Universe
• Data Mining and Machine Learning in Astronomy
• Galaxy And Mass Assembly (GAMA): The galaxy stellar mass function at z < 0.06
• Virial Scaling of Massive Dark Matter Halos: Why Clusters Prefer a High Normalization Cosmology
• The Structure and Dynamical Evolution of Dark Matter Halos
• On the Accuracy of Weak Lensing Cluster Mass Reconstructions
• The massive end of the luminosity and stellar mass functions: Dependence on the fit to the light profile
• Weighing the Giants IV: Cosmology and Neutrino Mass
• The relation between velocity dispersion and mass in simulated clusters of galaxies: dependence on the tracer and the baryonic physics
• Joint Analysis of Cluster Observations: II. Chandra/XMM-Newton X-ray and Weak Lensing Scaling Relations for a Sample of 50 Rich Clusters of Galaxies
• The Cluster-EAGLE project: global properties of simulated clusters with resolved galaxies
• Lensing and X-ray mass estimates of clusters (SIMULATION)
• Calibration of the galaxy cluster M_500-Y_X relation with XMM-Newton
• Weak Lensing Measurement of the Mass--Richness Relation of SDSS redMaPPer Clusters
• Hydrodynamic Simulation of Non-thermal Pressure Profiles of Galaxy Clusters
• Mass Calibration and Cosmological Analysis of the SPT-SZ Galaxy Cluster Sample Using Velocity Dispersion ${\sigma }_v$ and X-ray $Y_{\text{X}}$ Measurements
• Detailed cluster lensing profiles at large radii and the impact on cluster weak lensing studies
• Weighing the Giants V: Galaxy Cluster Scaling Relations
• Toward Unbiased Galaxy Cluster Masses from Line of Sight Velocity Dispersions
• HIFLUGCS: Galaxy cluster scaling relations between X-ray luminosity, gas mass, cluster radius, and velocity dispersion
• redMaPPer IV: Photometric Membership Identification of Cluster Galaxies with 1% Precision
• The redshift evolution of massive galaxy clusters in the MACSIS simulations
• LoCuSS: Calibrating Mass-Observable Scaling Relations for Cluster Cosmology with Subaru Weak Lensing Observations
• Correlations of Richness and Global Properties in Galaxy Clusters
• The impact of baryons on massive galaxy clusters: halo structure and cluster mass estimates
• Baryon Content of Massive Galaxy Clusters at z=0-0.6
• Galaxy Cluster Mass Reconstruction Project: I. Methods and first results on galaxy-based techniques
• A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
• Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning
• The competition between confinement and ram pressure and its implications for galaxies in groups and clusters
• The Cluster-EAGLE project: velocity bias and the velocity dispersion - mass relation of cluster galaxies
• Brighter galaxy bias: underestimating the velocity dispersions of galaxy clusters
• Testing the galaxy cluster mass-observable relations at z = 1 with XMM-Newton and Chandra observations of XLSSJ022403.9-041328
• Using Velocity Dispersion to Estimate Halo Mass: Is the Local Group in Tension with $\Lambda$CDM?
• Cosmology with velocity dispersion counts: an alternative to measuring cluster halo masses
• Kernels on Sample Sets via Nonparametric Divergence Estimates
• The Cluster-EAGLE project: a comparison of dynamical mass estimators using simulated clusters
• Measurement of Galaxy Cluster Integrated Comptonization and Mass Scaling Relations with the South Pole Telescope

Cited by in corpus (30)

• Machine learning and the physical sciences
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Identification of Young Stellar Object candidates in the $Gaia$ DR2 x AllWISE catalogue with machine learning methods
• A Robust and Efficient Deep Learning Method for Dynamical Mass Measurements of Galaxy Clusters
• Prediction of galaxy halo masses in SDSS DR7 via a machine learning approach
• Galaxy cluster mass estimation with deep learning and hydrodynamical simulations
• Dynamical mass inference of galaxy clusters with neural flows
• The Role of Machine Learning in the Next Decade of Cosmology
• Using X-Ray Morphological Parameters to Strengthen Galaxy Cluster Mass Estimates via Machine Learning
• Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
• The Fundamental Relation between Halo Mass and Galaxy Group Properties
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• Estimation of Impact Parameter and Transverse Spherocity in heavy-ion collisions at the LHC energies using Machine Learning
• 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
• Multiwavelength cluster mass estimates and machine learning
• Deep-CEE I: Fishing for Galaxy Clusters with Deep Neural Nets
• Large-scale structures in the $\Lambda$CDM Universe: network analysis and machine learning
• Galaxy cluster rotation revealed in the MACSIS simulations with the kinetic Sunyaev-Zeldovich effect
• Galaxy stellar and total mass estimation using machine learning
• Cosmology with Galaxy Cluster Properties using Machine Learning
• CHEX-MATE: A non-parametric deep learning technique to deproject and deconvolve galaxy cluster X-ray temperature profiles
• Identifying Galaxy Cluster Mergers with Deep Neural Networks using Idealized Compton-y and X-ray maps
• Halo Properties from Observable Measures of Environment: I. Halo and Subhalo Masses
• Inferring halo masses with Graph Neural Networks
• Mass scaling relations for dark halos from an analytic universal outer density profile
• Predicting halo occupation and galaxy assembly bias with machine learning
• Success of Machine Learning algorithms in Dynamical Mass Measurements of Galaxy Clusters
• Predicting Halo Formation Time Using Machine Learning
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods