Detection and classification of young stellar objects with machine learning methods

• Grant number: 24/23182-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: February 01, 2025
• End date: December 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Astronomy - Stellar Astrophysics
• Principal Investigator: Phillip Andreas Brenner Galli
• Grantee: Pedro Medeiros Merino
• Host Institution: Instituto de Astronomia, Geofísica e Ciências Atmosféricas (IAG). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 20/12518-8 - Dynamics and evolution of Young Stellar Clusters (DYSC), AP.JP

Abstract

Colour-colour diagrams are frequently used in astronomy to detect and classify young stellar objects based on their infrared excess emission. This is mostly done by imposing manual photometric selection constraints to define the locus for each object class in specific diagrams. This project aims to develop a detection and classification tool for young stellar objects based on machine-learning methods (e.g. neural networks) that will implement this task in a more objective and efficient manner. The student will compile the lists of known young stellar objects in nearby star-forming regions and the photometric data that is available, prepare a training set, implement and test classification models using free and open-source libraries designed for developing machine-learning methods. The classification tool developed in this project will be used in the future to search for the more dispersed young stellar objects over large portions of the sky in the outskirts of star-forming regions and young stellar clusters.