DATA ANALYSIS IN HIGH ENERGY PHYSICS USING MACHINE LEARNING METHODS

• Grant number: 25/02154-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: April 01, 2025
• End date: November 30, 2025
• Field of knowledge: Physical Sciences and Mathematics - Physics - Elementary Particle Physics and Fields
• Principal Investigator: Jun Takahashi
• Grantee: Matheus Guilherme Miotto
• Host Institution: Instituto de Física Gleb Wataghin (IFGW). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

In high-energy physics analyses, simulated Monte Carlo (MC) datasets are widely used to refine selection criteria and improve the efficiency of real data analysis from experiments. These datasets are generated through MC simulations, which model the topological and kinematic properties of particles produced in relativistic heavy-ion collisions, ensuring consistency with real data. However, MC simulations are computationally expensive and time-consuming. Therefore, this scientific initiation research project explores data analysis on simulated MC datasets of high-energy heavy-ion collisions using Machine Learning (ML) methods. The goal is to optimize conventional high-energy physics analyses and enhance data analysis frameworks for rare observable searches, ultimately reducing the cost of MC simulations. Specifically, we focus on reconstructing particles by measuring secondary decays using generative ML models to synthesize data consistent with real observations. The simulated datasets for this study will be provided by the Experimental Hadronic Physics Group (HadrEx) in collaboration with the ALICE experiment at the Large Hadron Collider (LHC). The generative models employed include Variational Autoencoders (VAE), Conditional Tabular Generative Adversarial Networks (CTGAN), and Probabilistic Denoising Diffusion Models (DDPM). This research not only contributes to advancements in standard analyses in high-energy physics but also complements the student's academic training, preparing them for postgraduate studies in the field.