Machine Learning and Cosmological Simulations II: Hydrodynamical Simulations

Abstract

We extend a machine learning (ML) framework presented previously to model galaxy formation and evolution in a hierarchical universe using N-body + hydrodynamical simulations. In this work, we show that ML is a promising technique to study galaxy formation in the backdrop of a hydrodynamical simulation. We use the Illustris Simulation to train and test various sophisticated machine learning algorithms. By using only essential dark matter halo physical properties and no merger history, our model predicts the gas mass, stellar mass, black hole mass, star formation rate, $g-r$ color, and stellar metallicity fairly robustly. Our results provide a unique and powerful phenomenological framework to explore the galaxy-halo connection that is built upon a solid hydrodynamical simulation. The promising reproduction of the listed galaxy properties demonstrably place ML as a promising and a significantly more computationally efficient tool to study small-scale structure formation. We find that ML mimics a full-blown hydrodynamical simulation surprisingly well in a computation time of mere minutes. The population of galaxies simulated by ML, while not numerically identical to Illustris, is statistically and physically robust and follows the same fundamental observational constraints. Machine learning offers an intriguing and promising technique to create quick mock galaxy catalogs in the future.

20 pages, 27 figures, 6 tables. Accepted to MNRAS

References in corpus (18)

• The EAGLE project: Simulating the evolution and assembly of galaxies and their environments
• Introducing the Illustris Project: Simulating the coevolution of dark and visible matter in the Universe
• Physical Models of Galaxy Formation in a Cosmological Framework
• Properties of galaxies reproduced by a hydrodynamic simulation
• Introducing the Illustris Project: the evolution of galaxy populations across cosmic time
• A unified model for AGN feedback in cosmological simulations of structure formation
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• The Illustris simulation: the evolving population of black holes across cosmic time
• A primer on hierarchical galaxy formation: the semi-analytical approach
• The Illustris Simulation: Public Data Release
• The Cannon: A data-driven approach to stellar label determination
• A Simple Technique for Predicting High-Redshift Galaxy Evolution
• Robust Machine Learning Applied to Astronomical Datasets I: Star-Galaxy Classification of the SDSS DR3 Using Decision Trees
• Estimation of stellar atmospheric parameters from SDSS/SEGUE spectra
• Dark Sky Simulations: Early Data Release
• A Hybrid Ensemble Learning Approach to Star-Galaxy Classification
• Machine Learning and Cosmological Simulations I: Semi-Analytical Models
• The galaxy - dark matter halo connection: which galaxy properties are correlated with the host halo mass?

Cited by in corpus (45)

• General Relativity and Cosmology: Unsolved Questions and Future Directions
• The Dust-to-Gas and Dust-to-Metals Ratio in Galaxies from z=0-6
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• AI-assisted super-resolution cosmological simulations
• 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
• Painting galaxies into dark matter halos using machine learning
• GalaxyNet: Connecting galaxies and dark matter haloes with deep neural networks and reinforcement learning in large volumes
• Learning the Relationship between Galaxies Spectra and their Star Formation Histories using Convolutional Neural Networks and Cosmological Simulations
• 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
• Robust Field-level Likelihood-free Inference with Galaxies
• Machine-assisted Semi-Simulation Model (MSSM): Estimating Galactic Baryonic Properties from their Dark Matter using a Machine Trained on Hydrodynamic Simulations
• From Dark Matter to Galaxies with Convolutional Networks
• A deep learning model to emulate simulations of cosmic reionization
• Machine Learning for Observational Cosmology
• The scatter in the galaxy-halo connection: a machine learning analysis
• Machine Learning methods to estimate observational properties of galaxy clusters in large volume cosmological N-body simulations
• Generating Synthetic Cosmological Data with GalSampler
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs
• 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
• How the Galaxy-Halo Connection Depends on Large-Scale Environment
• SHAMe-SF: Predicting the clustering of star-forming galaxies with an enhanced abundance matching model
• Classification algorithms applied to structure formation simulations
• Learning to Inflate
• Not Hydro: Using Neural Networks to estimate galaxy properties on a Dark-Matter-Only simulation
• High-fidelity reproduction of central galaxy joint distributions with Neural Networks
• Approximations to galaxy star formation rate histories: properties and uses of two examples
• Field-level simulation-based inference with galaxy catalogs: the impact of systematic effects
• A Machine Learning Approach to Galaxy-LSS Classification I: Imprints on Halo Merger Trees
• Analysis of Dark Matter Halo Structure Formation in $N$-body Simulations with Machine Learning
• Machine Learning the Fates of Dark Matter Subhalos: A Fuzzy Crystal Ball
• Multi-Epoch Machine Learning 2: Identifying physical drivers of galaxy properties in simulations
• A sparse regression approach for populating dark matter halos and subhalos with galaxies
• Predicting halo occupation and galaxy assembly bias with machine learning
• JERALD: high-fidelity dark matter, stellar mass and neutral hydrogen maps from fast N-body simulations
• Insights into the dependence of galaxy properties on the environment with explainable machine learning models
• CosmoGLINT: Cosmological Generative Model for Line Intensity Mapping with Transformer
• Model-Independent Quantum Phases Classifier
• Mimicking the halo-galaxy connection using machine learning
• Populating Galaxies Into Halos Via Machine Learning on the Simba Simulation