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.

Matches published version; very minor changes wrt V1

References in corpus (10)

• Introducing the Illustris Project: Simulating the coevolution of dark and visible matter in the Universe
• Properties of galaxies reproduced by a hydrodynamic simulation
• Introducing the Illustris Project: the evolution of galaxy populations across cosmic time
• Photometric redshift estimation via deep learning
• Spatial Clustering of Dark Matter Halos: Secondary Bias, Neighbor Bias, and the Influence of Massive Neighbors on Halo Properties
• Identifying Exoplanets with Deep Learning II: Two New Super-Earths Uncovered by a Neural Network in K2 Data
• On the influence of halo mass accretion history on galaxy properties and assembly bias
• A machine learning approach to mapping baryons onto dark matter haloes using the EAGLE and C-EAGLE simulations
• 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