Speaker
Description
Charged particle multiplicity and transverse momentum distributions in proton-proton (pp) collisions at LHC are key observables for characterizing particle production as a function of collision energy and pseudorapidity. We aim to understand the correlation between particle production by modelling the relationship between particle multiplicity and its probability distribution. Charged-particle multiplicity and transverse-momentum distributions within different pseudorapidity intervals in pp collisions were simulated using the PYTHIA8 event generator with several centres of mass energies for model training. Machine learning techniques, such as Deep Neural Network (DNN) and Convolutional Neural Network (CNN) are explored to fit multiplicity distributions in high energy pp collisions and compared in their ability to predict charged particle multiplicity and transverse momentum spectra across different center of mass energies and eta intervals. The probability distributions are used to compare Model's performance. This study demonstrates the potential of neural networks for describing multidimensional particle observables in pp collisions at LHC energies.