A Machine Learning Suite to Halo-Galaxy Connection

Natalí S.M.de Santi, Natália V.N. Rodrigues, Antonio D. Montero-Dorta, L. Raul Abramo, Beatriz Tucci, M. Celeste Artale

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

As far as we know, galaxies form inside dark matter halos and elucidating this connection is a key element in theories of galaxy formation and evolution. In this work we propose a suite of machine learning tools to predict baryonic from halo properties in the IllustrisTNG300 magnetohydrodynamical simulation. We apply four methods: extremely randomized trees, K-nearest neighbors, light gradient boosting machine, and neural networks. Moreover, we combine the results of them in a stacked model. In addition, we apply all these methods in an augmented dataset using the synthetic minority over-sampling technique for regression with Gaussian noise, to deal with the problem of imbalanced data sets. Altogether, the ML algorithms are consistent at predicting central galaxy properties from a set of input halo properties such as halo mass, concentration, spin, and halo overdensity. For stellar mass, the Pearson correlation coefficient is 0.98, while for specific star formation rate, color, and size it is between 0.7–0.8. Lastly, the presented analysis adds evidence to previous works indicating that certain galaxy properties cannot be reproduced using halo features alone.

Original languageEnglish
Title of host publicationMachine Learning for Astrophysics - Proceedings of the ML4Astro International Conference
EditorsFilomena Bufano, Simone Riggi, Eva Sciacca, Francesco Schilliro
PublisherSpringer Science and Business Media B.V.
Pages31-34
Number of pages4
ISBN (Print)9783031341663
DOIs
Publication statusPublished - 2023
Externally publishedYes
Event1st International Conference on Machine Learning for Astrophysics, ML4ASTRO 2022 - Catania, Italy
Duration: 30 May 20221 Jun 2022

Publication series

NameAstrophysics and Space Science Proceedings
Volume60
ISSN (Print)1570-6591
ISSN (Electronic)1570-6605

Conference

Conference1st International Conference on Machine Learning for Astrophysics, ML4ASTRO 2022
Country/TerritoryItaly
CityCatania
Period30/05/221/06/22

ASJC Scopus subject areas

  • General Physics and Astronomy
  • Computer Science Applications
  • Spectroscopy
  • Space and Planetary Science
  • Nuclear and High Energy Physics

Fingerprint

Dive into the research topics of 'A Machine Learning Suite to Halo-Galaxy Connection'. Together they form a unique fingerprint.

Cite this