Prompt and Non-prompt Production of Open and Hidden Charm Hadrons at the Large Hadron Collider Using Machine Learning

Abstract

The study of prompt and non-prompt production of charm hadrons is crucial to test the limits of perturbative QCD and to understand the beauty hadron production in collider experiments. In this contribution, we propose a machine learning (ML)-based method to separate the prompt and non-prompt production of open (D0) and hidden charm (J/ψ) hadrons. We employ XGBoost, LightGBM, Cat Boost, etc., ML models which take track-level information for training and prediction. For the training, we reconstruct D0→π+K- and J/ψ→μ+μ- decay channels. Further, invariant mass, pseudo-proper decay length, distance of closest approach, proper time, pseudorapidity, and transverse momentum of the decay candidates are used for the training and predictions. We obtain about 99% accuracy in the prediction from the ML models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.