Deep Learning for small bodies in the Solar System in the era of the LSST survey

• Grant number: 25/01469-0
• Support Opportunities: Regular Research Grants
• Start date: July 01, 2025
• End date: June 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Astronomy - Solar System Astronomy
• Principal Investigator: Valerio Carruba
• Grantee: Valerio Carruba
• Host Institution: Faculdade de Engenharia (FEG). Universidade Estadual Paulista (UNESP). Campus de Guaratinguetá. Guaratinguetá , SP, Brazil
• Associated researchers: Evgeny Smirnov ; Rita de Cássia Domingos ; Safwan Aljbaae

Abstract

The research proposal aims to use machine learning, including large language models, to analyze large datasets of smaller bodies in the Solar System, coming from the upcoming "Rubin Observatory Legacy Survey of Space and Time" (LSST). The research will focus on three main areas: main-belt asteroids in resonances, asteroids co-orbital with terrestrial planets (with an emphasis on Venus, where 11 new co-orbital asteroids were recently identified by the group), and trans-Neptunian objects in retrograde motion . Traditional orbital dynamics methods will be combined with machine learning techniques such as convolutional neural networks and vision transformers to classify and analyze these celestial bodies. (AU)