A Robust and Efficient Deep Learning Method for Dynamical Mass Measurements of Galaxy Clusters

Abstract

We demonstrate the ability of convolutional neural networks (CNNs) to mitigate systematics in the virial scaling relation and produce dynamical mass estimates of galaxy clusters with remarkably low bias and scatter. We present two models, CNN${}_{1D}$ and CNN${}_{2D}$, which leverage this deep learning tool to infer cluster masses from distributions of member galaxy dynamics. Our first model, CNN${}_{\text{1D}}$, infers cluster mass directly from the distribution of member galaxy line-of-sight velocities. Our second model, CNN${}_{\text{2D}}$, extends the input space of CNN${}_{\text{1D}}$ to learn on the joint distribution of galaxy line-of-sight velocities and projected radial distances. We train each model as a regression over cluster mass using a labeled catalog of realistic mock cluster observations generated from the MultiDark simulation and UniverseMachine catalog. We then evaluate the performance of each model on an independent set of mock observations selected from the same simulated catalog. The CNN models produce cluster mass predictions with lognormal residuals of scatter as low as $0.132$ dex, greater than a factor of 2 improvement over the classical $M$-$\sigma$ power-law estimator. Furthermore, the CNN model reduces prediction scatter relative to similar machine learning approaches by up to $17\%$ while executing in drastically shorter training and evaluation times (by a factor of 30) and producing considerably more robust mass predictions (improving prediction stability under variations in galaxy sampling rate by $30\%$).

arXiv comment22 pages, 10 figures, 4 tables, accepted for publication at ApJ

References in corpus (47)

• Planck 2013 results. XVI. Cosmological parameters
• The cosmological simulation code GADGET-2
• The Rockstar Phase-Space Temporal Halo Finder and the Velocity Offsets of Cluster Cores
• Observational Probes of Cosmic Acceleration
• UniverseMachine: The Correlation between Galaxy Growth and Dark Matter Halo Assembly from z=0-10
• Cosmological Parameters from Observations of Galaxy Clusters
• MultiDark simulations: the story of dark matter halo concentrations and density profiles
• Tracing cosmic evolution with clusters of galaxies
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Measurement of areas on a sphere using Fibonacci and latitude-longitude lattices
• Virial Scaling of Massive Dark Matter Halos: Why Clusters Prefer a High Normalization Cosmology
• Weighing the Giants IV: Cosmology and Neutrino Mass
• Mass estimation in the outer regions of galaxy clusters
• Infall Regions of Galaxy Clusters
• Evidence for X-ray emission from a large-scale filament of galaxies ?
• Weighing the Giants - III. Methods and Measurements of Accurate Galaxy Cluster Weak-Lensing Masses
• Dark Energy Survey Year 1 Results: Weak Lensing Mass Calibration of redMaPPer Galaxy Clusters
• MAMPOSSt: Modelling Anisotropy and Mass Profiles of Observed Spherical Systems. I. Gaussian 3D velocities
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Weighing the Giants V: Galaxy Cluster Scaling Relations
• Toward Unbiased Galaxy Cluster Masses from Line of Sight Velocity Dispersions
• The DEEP2 Galaxy Redshift Survey: First results on galaxy groups
• Cluster Galaxy Dynamics and the Effects of Large Scale Environment
• Correlations of Richness and Global Properties in Galaxy Clusters
• Galaxy Cluster Mass Reconstruction Project: II. Quantifying scatter and bias using contrasting mock catalogues
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Galaxy Cluster Mass Reconstruction Project: I. Methods and first results on galaxy-based techniques
• Interloper treatment in dynamical modelling of galaxy clusters
• A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
• Galaxy Cluster Mass Estimation from Stacked Spectroscopic Analysis
• Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning
• Velocity Anisotropy and Shape Bias in the Caustic Technique
• Prediction of galaxy halo masses in SDSS DR7 via a machine learning approach
• An application of machine learning techniques to galaxy cluster mass estimation using the MACSIS simulations
• Constraining the Mass-Richness Relationship of redMaPPer Clusters with Angular Clustering
• Galaxy Cluster Mass Reconstruction Project: III. The impact of dynamical substructure on cluster mass estimates
• Galaxy Cluster Mass Reconstruction Project - IV. Understanding the effects of imperfect membership on cluster mass estimation
• Chandra Measurements of a Complete Sample of X-ray Luminous Galaxy Clusters: The Luminosity-Mass Relation
• Non-Gaussian velocity distributions - The effect on virial mass estimates of galaxy groups
• Phase-space shapes of clusters and rich groups of galaxies
• Influence of Projection in Cluster Cosmology Studies
• GalWeight: A New and Effective Weighting Technique for Determining Galaxy Cluster and Group Membership
• Non-Gaussian Scatter in Cluster Scaling Relations
• The XXL Survey: XXIII. The Mass Scale of XXL Clusters from Ensemble Spectroscopy
• Effect of asphericity in caustic mass estimates of galaxy clusters
• Spatial Anisotropy of Galaxy Kinematics in Sloan Digital Sky Survey Galaxy Clusters
• The Cluster-EAGLE project: a comparison of dynamical mass estimators using simulated clusters

Cited by in corpus (55)

• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• The CAMELS project: public data release
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Dynamical mass inference of galaxy clusters with neural flows
• Machine learning constraints on deviations from general relativity from the large scale structure of the Universe
• Cosmology Intertwined: A Review of the Particle Physics, Astrophysics, and Cosmology Associated with the Cosmological Tensions and Anomalies
• Machine Learning improved fits of the sound horizon at the baryon drag epoch
• A Deep Learning Approach to Infer Galaxy Cluster Masses from Planck Compton$-y$ parameter maps
• Machine learning forecasts of the cosmic distance duality relation with strongly lensed gravitational wave events
• Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
• A deep learning view of the census of galaxy clusters in IllustrisTNG
• The search for galaxy cluster members with deep learning of panchromatic HST imaging and extensive spectroscopy
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• The Dynamical Mass of the Coma Cluster from Deep Learning
• A Method to Distinguish Quiescent and Dusty Star-forming Galaxies with Machine Learning
• SHAPing the Gas: Understanding Gas Shapes in Dark Matter Haloes with Interpretable Machine Learning
• Approximate Bayesian Uncertainties on Deep Learning Dynamical Mass Estimates of Galaxy Clusters
• What to expect from dynamical modelling of cluster haloes II. Investigating dynamical state indicators with Random Forest
• Effective cosmic density field reconstruction with convolutional neural network
• Aging Halos: Implications of the Magnitude Gap on Conditional Statistics of Stellar and Gas Properties of Massive Halos
• The Uchuu-UniverseMachine dataset: Galaxies in and around Clusters
• The Three Hundred project: A Machine Learning method to infer clusters of galaxies mass radial profiles from mock Sunyaev-Zel'dovich maps
• DeepSZ: Identification of Sunyaev-Zel'dovich Galaxy Clusters using Deep Learning
• Deep learning for Sunyaev-Zel'dovich detection in Planck
• Testing the $\Lambda$CDM paradigm with growth rate data and machine learning
• Machine learning cosmic inflation
• Benchmarks and Explanations for Deep Learning Estimates of X-ray Galaxy Cluster Masses
• Euclid Preparation XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong lensing events
• Using machine learning to compress the matter transfer function $T(k)$
• Galaxies and Halos on Graph Neural Networks: Deep Generative Modeling Scalar and Vector Quantities for Intrinsic Alignment
• The Importance of Being Interpretable: Toward An Understandable Machine Learning Encoder for Galaxy Cluster Cosmology
• Painting baryons onto N-body simulations of galaxy clusters with image-to-image deep learning
• Galaxy stellar and total mass estimation using machine learning
• Cosmology with Galaxy Cluster Properties using Machine Learning
• Machine learning unveils the linear matter power spectrum of modified gravity
• A deep learning approach to halo merger tree construction
• 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
• Identifying Galaxy Cluster Mergers with Deep Neural Networks using Idealized Compton-y and X-ray maps
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• Galaxy mass profiles with convolutional neural networks
• Inferring halo masses with Graph Neural Networks
• Mass scaling relations for dark halos from an analytic universal outer density profile
• Estimating Cluster Masses from SDSS Multi-band Images with Transfer Learning
• Galaxy Velocity Bias in Cosmological Simulations: Towards Percent-level Calibration
• Cluster optical depth and pairwise velocity estimation using machine learning
• Deriving accurate galaxy cluster masses using X-ray thermodynamic profiles and graph neural networks
• Estimating the triaxiality of massive clusters from 2D observables in MillenniumTNG with machine learning
• Beyond single tracers: CNN-based inference of galaxy mass profiles from combined gas and stellar kinematics
• Generating Galaxy Clusters Mass Density Maps from Mock Multiview Images via Deep Learning
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• $G_3$ -- interacting scalar tensor dark energy
• AutoEnRichness: A hybrid empirical and analytical approach for estimating the richness of galaxy clusters
• A probabilistic deep learning model to distinguish cusps and cores in dwarf galaxies