Galaxy population synthesis with machine learning techniques

• Grant number: 19/05355-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: June 01, 2019
• End date: May 31, 2020
• Field of knowledge: Physical Sciences and Mathematics - Astronomy - Extragalactic Astrophysics
• Principal Investigator: Laerte Sodré Junior
• Grantee: Vitor Martins Cernic
• Host Institution: Instituto de Astronomia, Geofísica e Ciências Atmosféricas (IAG). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

This project aims to apply machine learning techniques (ML) to spectral synthesis of galaxies. We will use the results of a new application of the STARLIGHT software to a sample of more than 200 thousand galaxies realized by Werle et al. (2019). These results innovate because the synthesis is made taking into account the UV emission of the galaxies, which improves the estimation of stellar populations properties. These results will serve as the basis for the creation of a training set that will be used to train ML algorithms that will, initially, be applied to the study of Stripe 82 galaxies observed by the S-PLUS photometric survey.