Inferring the mass of ultra-high energy cosmic rays detected with the Auger Observatory using neural networks

• Grant number: 25/00368-5
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: June 01, 2025
• End date: December 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Physics - Elementary Particle Physics and Fields
• Principal Investigator: Carola Dobrigkeit Chinellato
• Grantee: João Vítor Reginatto Akim
• Host Institution: Instituto de Física Gleb Wataghin (IFGW). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 19/10151-2 - Study of Ultra-High Energy Cosmic Rays with the Pierre Auger Observatory upgrade AugerPrime, AP.ESP

Abstract

This project is part of the research conducted by the Pierre Auger Collaboration and focuses on the development and application of advanced machine learning models to analyze data from extensive air showers initiated by cosmic rays with extreme energies, on the order of a few EeV or higher. Using the depth of the shower maximum development (Xmax) and the muon signal at ground, suitableneural networks will be devised and trained to infer the mass of the primary nucleus that originated the shower. The training of these networks will be carriedout with simulated data, allowing the models to learn how to make accurate inferences. After training, the networks will be applied to data collected by the upgraded Auger Observatory, taking advantage of the new detectors and enhancedelectronics installed with AugerPrime. In addition to the development of the models, the project includes a detailed analysis of the associated uncertainties, in particular those related to the hadronic interaction models, aiming to ensure thatthe obtained results have robust physical significance. The expected results have the potential to contribute significantly to the understanding of ultra-high energy cosmic rays.