Speaker
Description
Identification of the type of primary cosmic ray particle (e.g., light nucleus, heavy nucleus) on an individual event basis is important for cosmic ray observatories, which is crucial for understanding the origin and nature of high-energy particles of cosmic rays. In this study, we investigate the identification of primary cosmic ray particles using shower parameters, particularly focusing on the depth of shower maximum (X_max) distribution and related statistical parameters based on simulation of EAS at primary energy 〖10〗^17 eV using CORSIKA code. A machine learning approach is applied to the simulated dataset containing event-by-event measurements of X_max , shower size at depth of shower maximum, mean depth of shower maximum 〈X_max 〉, standard deviation (fluctuations) and Skewness of the depth of shower maximum distribution of extensive air showers (EAS). The model achieved high classification accuracy, demonstrating the viability of this approach for mass composition studies in cosmic ray physics.