Mimicking the halo-galaxy connection using machine learning

Abstract

Elucidating the connection between the properties of galaxies and the properties of their hosting haloes is a key element in galaxy formation. When the spatial distribution of objects is also taken under consideration, it becomes very relevant for cosmological measurements. In this paper, we use machine learning techniques to analyse these intricate relations in the IllustrisTNG300 magnetohydrodynamical simulation, predicting baryonic properties from halo properties. We employ four different algorithms: extremely randomized trees, K-nearest neighbours, light gradient boosting machine, and neural networks, along with a unique and powerful combination of the results from all four approaches. Overall, the different algorithms produce consistent results in terms of predicting galaxy properties from a set of input halo properties that include halo mass, concentration, spin, and halo overdensity. For stellar mass, the Pearson correlation coefficient is 0.98, dropping down to 0.7-0.8 for specific star formation rate (sSFR), colour, and size. In addition, we apply, for the first time in this context, an existing data augmentation method, synthetic minority over-sampling technique for regression with Gaussian noise (SMOGN), designed to alleviate the problem of imbalanced data sets, showing that it improves the overall shape of the predicted distributions and the scatter in the halo-galaxy relations. We also demonstrate that our predictions are good enough to reproduce the power spectra of multiple galaxy populations, defined in terms of stellar mass, sSFR, colour, and size with high accuracy. Our results align with previous reports suggesting that certain galaxy properties cannot be reproduced using halo features alone.

arXiv commentMatches published version; very minor changes wrt V1

References in corpus (70)

• SMOTE: Synthetic Minority Over-sampling Technique
• Planck 2015 results. XIII. Cosmological parameters
• A Universal Density Profile from Hierarchical Clustering
• Populating a cluster of galaxies - I. Results at z=0
• E pur si muove: Galiliean-invariant cosmological hydrodynamical simulations on a moving mesh
• Introducing the Illustris Project: Simulating the coevolution of dark and visible matter in the Universe
• Simulating Galaxy Formation with the IllustrisTNG Model
• First results from the IllustrisTNG simulations: matter and galaxy clustering
• First results from the IllustrisTNG simulations: the stellar mass content of groups and clusters of galaxies
• First results from the IllustrisTNG simulations: the galaxy color bimodality
• Physical Models of Galaxy Formation in a Cosmological Framework
• Properties of galaxies reproduced by a hydrodynamic simulation
• First results from the IllustrisTNG simulations: A tale of two elements -- chemical evolution of magnesium and europium
• UniverseMachine: The Correlation between Galaxy Growth and Dark Matter Halo Assembly from z=0-10
• First results from the IllustrisTNG simulations: radio haloes and magnetic fields
• Introducing the Illustris Project: the evolution of galaxy populations across cosmic time
• Substructures in hydrodynamical cluster simulations
• A Comprehensive Analysis of Uncertainties Affecting the Stellar Mass - Halo Mass Relation for 0<z<4
• A universal angular momentum profile for galactic halos
• The Halo Occupation Distribution: Towards an Empirical Determination of the Relation Between Galaxies and Mass
• The Connection between Galaxies and their Dark Matter Halos
• Modeling Luminosity-Dependent Galaxy Clustering Through Cosmic Time
• Theoretical Challenges in Galaxy Formation
• The age dependence of halo clustering
• EMERGE - An empirical model for the formation of galaxies since $z\sim 10$
• On the environmental dependence of halo formation
• Galaxy formation in WMAP1 and WMAP7 cosmologies
• Galaxies in LCDM with Halo Abundance Matching: luminosity-velocity relation, baryonic mass-velocity relation, velocity function and clustering
• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• Halo Assembly Bias in Hierarchical Structure Formation
• nbodykit: an open-source, massively parallel toolkit for large-scale structure
• The Intermediate-Scale Clustering of Luminous Red Galaxies
• Photometric redshift estimation via deep learning
• The Impact of Assembly Bias on the Galaxy Content of Dark Matter Halos
• Halo assembly bias and the tidal anisotropy of the local halo environment
• The impact of assembly bias on the halo occupation in hydrodynamical simulations
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Modelling galaxy clustering: halo occupation distribution versus subhalo matching
• Limitations to the "basic'' HOD model and beyond
• ZOMG-I. How the cosmic web inhibits halo growth and generates assembly bias
• Revealing the galaxy-halo connection in IllustrisTNG
• Why multi-tracer surveys beat cosmic variance
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Spatial Clustering of Dark Matter Halos: Secondary Bias, Neighbor Bias, and the Influence of Massive Neighbors on Halo Properties
• Dissecting and Modelling Galaxy Assembly Bias
• Cosmic web anisotropy is the primary indicator of halo assembly bias
• Painting galaxies into dark matter halos using machine learning
• Identifying Exoplanets with Deep Learning II: Two New Super-Earths Uncovered by a Neural Network in K2 Data
• Clustering properties of $g$-selected galaxies at $z\sim 0.8$
• Machine Learning and Cosmological Simulations II: Hydrodynamical Simulations
• Extensions to models of the galaxy-halo connection
• The dependence of halo bias on age, concentration and spin
• Prediction of galaxy halo masses in SDSS DR7 via a machine learning approach
• The manifestation of secondary halo bias on the galaxy population from IllustrisTNG300
• On the influence of halo mass accretion history on galaxy properties and assembly bias
• Fourier analysis of multi-tracer cosmological surveys
• A machine learning approach to mapping baryons onto dark matter haloes using the EAGLE and C-EAGLE simulations
• An interpretable machine learning framework for dark matter halo formation
• Machine-assisted Semi-Simulation Model (MSSM): Estimating Galactic Baryonic Properties from their Dark Matter using a Machine Trained on Hydrodynamic Simulations
• Testing the Accuracy of Halo Occupation Distribution Modelling using Hydrodynamic Simulations
• A First Look at creating mock catalogs with machine learning techniques
• The physical origins of low-mass spin bias
• The Fundamental Relation between Halo Mass and Galaxy Group Properties
• The galaxy size - halo mass scaling relations and clustering properties of central and satellite galaxies
• Anisotropic halo assembly bias and redshift-space distortions
• The Formation History of Subhalos and the Evolution of Satellite Galaxies
• Estimating dust attenuation from galactic spectra. II. Stellar and gas attenuation in star-forming and diffuse ionized gas regions in MaNGA
• Classifying Stars, Galaxies and AGN in CLAUDS+HSC-SSP Using Gradient Boosted Decision Trees
• On the kinetic Sunyaev-Zel'dovich effect as an observational probe for halo spin bias
• The Multi-Tracer Optimal Estimator applied to VIPERS