Machine Learning and Cosmological Simulations I: Semi-Analytical Models
arXiv:1510.06402 · doi:10.1093/mnras/stv2310
Abstract
We present a new exploratory framework to model galaxy formation and evolution in a hierarchical universe by using machine learning (ML). Our motivations are two-fold: (1) presenting a new, promising technique to study galaxy formation, and (2) quantitatively analyzing the extent of the influence of dark matter halo properties on galaxies in the backdrop of semi-analytical models (SAMs). We use the influential Millennium Simulation and the corresponding Munich SAM to train and test various sophisticated machine learning algorithms (k-Nearest Neighbors, decision trees, random forests and extremely randomized trees). By using only essential dark matter halo physical properties for haloes of and a partial merger tree, our model predicts the hot gas mass, cold gas mass, bulge mass, total stellar mass, black hole mass and cooling radius at z = 0 for each central galaxy in a dark matter halo for the Millennium run. Our results provide a unique and powerful phenomenological framework to explore the galaxy-halo connection that is built upon SAMs and demonstrably place ML as a promising and a computationally efficient tool to study small-scale structure formation.
arXiv commentAccepted for publication in MNRAS. 19 pages, 20 figures, 4 tables
References in corpus (65)
- Scikit-learn: Machine Learning in Python
- Galactic Stellar and Substellar Initial Mass Function
- The cosmological simulation code GADGET-2
- The Global Schmidt Law in Star Forming Galaxies
- Simulating the joint evolution of quasars, galaxies and their large-scale distribution
- The many lives of active galactic nuclei: cooling flows, black holes and the luminosities and colours of galaxies
- The EAGLE project: Simulating the evolution and assembly of galaxies and their environments
- Populating a cluster of galaxies - I. Results at z=0
- The broken hierarchy of galaxy formation
- Introducing the Illustris Project: Simulating the coevolution of dark and visible matter in the Universe
- The Formation of Galactic Disks
- Hierarchical Galaxy Formation
- The hierarchical formation of the brightest cluster galaxies
- Physical Models of Galaxy Formation in a Cosmological Framework
- From dwarf spheroidals to cDs: Simulating the galaxy population in a LCDM cosmology
- Constraints on the relationship between stellar mass and halo mass at low and high redshift
- A Semi-Analytic Model for the Co-evolution of Galaxies, Black Holes, and Active Galactic Nuclei
- Semi-Analytic Modelling of Galaxy Formation: The Local Universe
- The formation history of elliptical galaxies
- A Comprehensive Analysis of Uncertainties Affecting the Stellar Mass - Halo Mass Relation for 0<z<4
- Halos and galaxies in the standard cosmological model: results from the Bolshoi simulation
- Galaxy bimodality versus stellar mass and environment
- A Recipe for Galaxy Formation Shaun Cole
- Rotation-invariant convolutional neural networks for galaxy morphology prediction
- Boosted Decision Trees as an Alternative to Artificial Neural Networks for Particle Identification
- A primer on hierarchical galaxy formation: the semi-analytical approach
- Connecting Galaxies, Halos, and Star Formation Rates Across Cosmic Time
- Scaling relations for galaxy clusters in the Millennium-XXL simulation
- Mergers and Bulge Formation in Lambda-CDM: Which Mergers Matter?
- Dynamical Friction and Galaxy Merging Timescales
- Properties of Galactic Outflows: Measurements of the Feedback from Star Formation
- Data Mining and Machine Learning in Astronomy
- Chemical enrichment of the intra-cluster and intergalactic medium in a hierarchical galaxy formation model
- Galacticus: A Semi-Analytic Model of Galaxy Formation
- The Baryonic Assembly of Dark Matter Halos
- TPZ : Photometric redshift PDFs and ancillary information by using prediction trees and random forests
- The MORGANA model for the rise of galaxies and active nuclei
- Simulations of the galaxy population constrained by observations from z=3 to the present day: implications for galactic winds and the fate of their ejecta
- Semi-analytical model of galaxy formation with high-resolution N-body simulations
- Disk galaxies at Z=0 and at High Redshift: an explanation of the observed evolution of damped Ly-alpha systems
- Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
- Effects of AGN feedback on LCDM galaxies
- A New Parallel N-body Gravity Solver: TPM
- Cluster Galaxies Die Hard
- ArborZ: Photometric Redshifts Using Boosted Decision Trees
- The Parameter Space of Galaxy Formation
- SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
- Robust Machine Learning Applied to Astronomical Datasets I: Star-Galaxy Classification of the SDSS DR3 Using Decision Trees
- Gas cooling in simulations of the formation of the galaxy population
- Estimation of stellar atmospheric parameters from SDSS/SEGUE spectra
- A Comparison of Semi-Analytic and Smoothed Particle Hydrodynamics Galaxy Formation
- Modelling and interpreting the dependence of clustering on the spectral energy distributions of galaxies
- Dark Sky Simulations: Early Data Release
- Monte Carlo Markov Chain Parameter Estimation in Semi-Analytic Models of Galaxy Formation
- A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
- A semi-analytic model comparison - gas cooling and galaxy mergers
- Robust Machine Learning Applied to Astronomical Datasets II: Quantifying Photometric Redshifts for Quasars Using Instance-Based Learning
- The Stellar Mass Components of Galaxies: Comparing Semi-Analytical Models with Observation
- A Hybrid Ensemble Learning Approach to Star-Galaxy Classification
- The galaxy - dark matter halo connection: which galaxy properties are correlated with the host halo mass?
- A First Look at creating mock catalogs with machine learning techniques
- Comparison of the VIMOS-VLT Deep Survey with the Munich semi-analytical model - I. Magnitude counts, redshift distribution, colour bimodality, and galaxy clustering
- A semi-analytic model comparison: testing cooling models against hydrodynamical simulations
- Comparison of the VIMOS-VLT Deep Survey with the Munich semi-analytical model. II. The colour-density relation up to z=1.5
- Learning Nonlinear Functions Using Regularized Greedy Forest
Cited by in corpus (35)
- Star-galaxy Classification Using Deep Convolutional Neural Networks
- General Relativity and Cosmology: Unsolved Questions and Future Directions
- Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
- Unveiling phase transitions with machine learning
- Analysing the 21cm signal from the Epoch of Reionization with artificial neural networks
- Applications and Techniques for Fast Machine Learning in Science
- Distinguishing standard and modified gravity cosmologies with machine learning
- Machine learning cosmological structure formation
- GalaxyNet: Connecting galaxies and dark matter haloes with deep neural networks and reinforcement learning in large volumes
- Machine Learning and Cosmological Simulations II: Hydrodynamical Simulations
- A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected From The Best-Heckman Sample
- Deep Transfer Learning for Star Cluster Classification: I. Application to the PHANGS-HST Survey
- Prediction of galaxy halo masses in SDSS DR7 via a machine learning approach
- A machine learning approach to mapping baryons onto dark matter haloes using the EAGLE and C-EAGLE simulations
- Machine-assisted Semi-Simulation Model (MSSM): Estimating Galactic Baryonic Properties from their Dark Matter using a Machine Trained on Hydrodynamic Simulations
- : Learning Galaxy Properties from Merger Trees
- Towards a radially-resolved semi-analytic model for the evolution of disc galaxies tuned with machine learning
- A deep learning model to emulate simulations of cosmic reionization
- Generating Synthetic Cosmological Data with GalSampler
- Inferring physical properties of galaxies from their emission line spectra
- Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
- Multiwavelength cluster mass estimates and machine learning
- Multi-Epoch Machine Learning 1: Unravelling Nature vs Nurture for Galaxy Formation
- Hybrid analytic and machine-learned baryonic property insertion into galactic dark matter haloes
- Learning to Inflate
- Not Hydro: Using Neural Networks to estimate galaxy properties on a Dark-Matter-Only simulation
- Approximations to galaxy star formation rate histories: properties and uses of two examples
- A New Constraint on the Nuclear Equation of State from Statistical Distributions of Compact Remnants of Supernovae
- A Machine Learning Approach to Galaxy-LSS Classification I: Imprints on Halo Merger Trees
- A machine learning approach for identifying the counterparts of submillimetre galaxies and applications to the GOODS-North field
- Unsupervised Star Galaxy Classification with Cascade Variational Auto-Encoder
- A sparse regression approach for populating dark matter halos and subhalos with galaxies
- JERALD: high-fidelity dark matter, stellar mass and neutral hydrogen maps from fast N-body simulations
- Predicting halo occupation and galaxy assembly bias with machine learning
- Model-Independent Quantum Phases Classifier