2025/04/13 by R. Sahoo, Suraj Prasad, Sahoo, Raghunath +7
Physics and Astronomy · #FOS: Physical sciences #High Energy Physics - Experiment (hep-ex) #High Energy Physics - Phenomenology (hep-ph) #High Energy Physics - Theory (hep-th) #High-Energy Particle Collisions Research #Nuclear Experiment (nucl-ex) #Nuclear Theory (nucl-th) #Particle Detector Development and Performance #Particle physics theoretical and experimental studies
paper · pdf · doi:10.48550/arxiv.2504.09541
openalex publication_date 2025/04/13 · openalex created_date 2025/10/14 · openalex updated_date 2026/07/28
In this contribution, we use machine learning (ML) based models to separate the prompt and non-prompt production of heavy flavour hadrons, such as D0 and J/ψ, in proton-proton collisions at LHC energies. For this purpose, we use PYTHIA~8 to generate events, which provides a good qualitative agreement with experimental measurements of charm hadron production. The input features for the ML models are experimentally measurable. The prediction accuracy of the ML models used in this study reaches up to 99%. The ML models can be useful in providing precise track-level identification, which is not possible in experiments with traditional methods. The contribution also discusses future applications of the ML models to understand the production of prompt and non-prompt heavy quark hadrons.