Deep Learning generated observations of galaxy clusters from dark-matter-only simulations

Abstract

Hydrodynamical simulations play a fundamental role in modern cosmological research, serving as a crucial bridge between theoretical predictions and observational data. However, due to their computational intensity, these simulations are currently constrained to relatively small volumes. Therefore, this study investigates the feasibility of utilising dark matter-only simulations to generate observable maps of galaxy clusters using a deep learning approach based on the U-Net architecture. We focus on reconstructing Compton-y parameter maps (SZ maps) and bolometric X-ray surface brightness maps (X-ray maps) from total mass density maps. We leverage data from \textsc{The Three Hundred} simulations, selecting galaxy clusters ranging in mass from $10^{13.5}{h}^{-1}{M}_{\odot }\le M_{200}\le 10^{15.5}{h}^{-1}{M}_{\odot }$. Despite the machine learning models being independent of baryonic matter assumptions, a notable limitation is their dependency on the underlying physics of hydrodynamical simulations. To evaluate the reliability of our generated observable maps, we employ various metrics and compare the observable-mass scaling relations. For clusters with masses greater than $2\times 10^{14}{h}^{-1}{M}_{\odot }$, the predictions show excellent agreement with the ground-truth datasets, with percentage errors averaging (0.5 $\pm$ 0.1)\% for the parameters of the scaling laws.

16 pages, 13 Figures. Accepted in RASTI

References in corpus (97)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Planck 2015 results. XIII. Cosmological parameters
• Seven-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Interpretation
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• scikit-image: Image processing in Python
• A Fundamental Relation Between Supermassive Black Holes and Their Host Galaxies
• Cosmological Parameters from Observations of Galaxy Clusters
• GIZMO: A New Class of Accurate, Mesh-Free Hydrodynamic Simulation Methods
• Simba: Cosmological Simulations with Black Hole Growth and Feedback
• Halo occupation numbers and galaxy bias
• MultiDark simulations: the story of dark matter halo concentrations and density profiles
• The Dark Side of the Halo Occupation Distribution
• Ahf: Amiga's Halo Finder
• Formation of Galaxy Clusters
• Modeling Luminosity-Dependent Galaxy Clustering Through Cosmic Time
• Linking halo mass to galaxy luminosity
• Wasserstein GAN
• Cosmological Constraints from the SDSS maxBCG Cluster Catalog
• Improving galaxy morphologies for SDSS with Deep Learning
• Generative Moment Matching Networks
• Galacticus: A Semi-Analytic Model of Galaxy Formation
• Halo assembly bias and its effects on galaxy clustering
• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• A Kernel Method for the Two-Sample Problem
• The Three Hundred project: a large catalogue of theoretically modelled galaxy clusters for cosmological and astrophysical applications
• Cool Core Clusters from Cosmological Simulations
• The SPTpol Extended Cluster Survey
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• Quantifying baryon effects on the matter power spectrum and the weak lensing shear correlation
• Cosmological simulations of galaxy clusters
• Gas Clumping in the Outskirts of Lambda-CDM 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
• Evidence for AGN Feedback in Galaxy Clusters and Groups
• Automated Transient Identification in the Dark Energy Survey
• The eROSITA Final Equatorial-Depth Survey (eFEDS): Catalog of galaxy clusters and groups
• Non-Gaussian information from weak lensing data via deep learning
• The Physics of Galaxy Cluster Outskirts
• The MUSIC of Galaxy Clusters I: Baryon properties and Scaling Relations of the thermal Sunyaev-Zel'dovich Effect
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• The Three Hundred Project: Backsplash galaxies in simulations of clusters
• The Three Hundred Project: Dynamical state of galaxy clusters and morphology from multi-wavelength synthetic maps
• \textsc{The Three Hundred} project: The \textsc{Gizmo-Simba} run
• How baryons affect halos and large-scale structure: a unified picture from the Simba simulation
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Mapping and characterisation of cosmic filaments in galaxy cluster outskirts: strategies and forecasts for observations from simulations
• A Robust and Efficient Deep Learning Method for Dynamical Mass Measurements of Galaxy Clusters
• The DIANOGA simulations of galaxy clusters: characterizing star formation in proto-clusters
• Super-resolution of multispectral satellite images using convolutional neural networks
• Cosmological Constraints from Galaxy Clusters and Groups in the eROSITA Final Equatorial Depth Survey
• The ThreeHundred: the structure and properties of cosmic filaments in the outskirts of galaxy clusters
• The Three Hundred Project: The evolution of galaxy cluster density profiles
• Classifying the Large Scale Structure of the Universe with Deep Neural Networks
• Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning
• The Three Hundred Project: Ram pressure and gas content of haloes and subhaloes in the phase-space plane
• Identifying Reionization Sources from 21cm Maps using Convolutional Neural Networks
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• A machine learning approach to mapping baryons onto dark matter haloes using the EAGLE and C-EAGLE simulations
• 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
• The Three Hundred project: shapes and radial alignment of satellite, infalling, and backsplash galaxies
• Cosmic filaments in galaxy cluster outskirts: quantifying finding filaments in redshift space
• Shocks in the Stacked Sunyaev-Zel'dovich Profiles of Clusters I: Analysis with the Three Hundred Simulations
• A study of the hydrostatic mass bias dependence and evolution within The Three Hundred clusters
• Machine Learning Applied to the Reionization History of the Universe in the 21 cm Signal
• The redshift evolution of X-ray and Sunyaev-Zel'dovich scaling relations in the FABLE simulations
• A Deep Learning Approach to Infer Galaxy Cluster Masses from Planck Compton$-y$ parameter maps
• A First Look at creating mock catalogs with machine learning techniques
• The Three Hundred Project: the stellar and gas profiles
• Euclid preparation. XXXII. Evaluating the weak lensing cluster mass biases using the Three Hundred Project hydrodynamical simulations
• From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
• Machine Learning methods to estimate observational properties of galaxy clusters in large volume cosmological N-body simulations
• What to expect from dynamical modelling of cluster haloes II. Investigating dynamical state indicators with Random Forest
• The Three Hundred: Cluster Dynamical States and Relaxation Time Scale
• Generating Synthetic Cosmological Data with GalSampler
• Constraining the cross-section of dark matter with giant radial arcs in galaxy clusters
• The Three Hundred project: A Machine Learning method to infer clusters of galaxies mass radial profiles from mock Sunyaev-Zel'dovich maps
• What to expect from dynamical modelling of cluster haloes I. The information content of different dynamical tracers
• MultiDark-Clusters: Galaxy Cluster Mock Light-Cones, eROSITA and the Cluster Power Spectrum
• The Three Hundred project: connection between star formation quenching and dynamical evolution in and around simulated galaxy clusters
• Brightest Cluster Galaxies Trace Weak Lensing Mass Bias and Halo Triaxiality in The Three Hundred Project
• Hybrid analytic and machine-learned baryonic property insertion into galactic dark matter haloes
• Reconsidering the dynamical states of galaxy clusters using PCA and UMAP
• A Brief Review of Domain Adaptation
• The dynamic stage of clusters and its influence on the stellar populations of galaxies
• Emulating Sunyaev-Zeldovich Images of Galaxy Clusters using Auto-Encoders
• Painting baryons onto N-body simulations of galaxy clusters with image-to-image deep learning
• The Three Hundred project: Estimating the dependence of gas filaments on the mass of galaxy clusters
• CHEX-MATE: A non-parametric deep learning technique to deproject and deconvolve galaxy cluster X-ray temperature profiles
• Galaxy clusters as probes for cosmology and dark matter
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Scaling relations of clusters and groups, and their evolution
• Identifying Galaxy Cluster Mergers with Deep Neural Networks using Idealized Compton-y and X-ray maps
• Galaxy pairs in The Three Hundred simulations II: studying bound ones and identifying them via machine learning
• The Three Hundred Project: The stellar angular momentum evolution of cluster galaxies
• Galaxy cluster mass bias from projected mass maps: The Three Hundred-NIKA2 LPSZ twin samples