tesis de maestría
Categorisation of dark photon jets using machine learning techniques
Fecha
2023Registro en:
10.7764/tesisUC/FIS/75619
Autor
Haacke Concha, Michael
Institución
Resumen
This thesis presents a search for Dark Photons decaying into two Hidden Lightest Stable Particles (HLSP) and fermions or light hadrons using ATLAS experiment data from the LHC at a center-of-mass energy of 13 TeV, with an integrated luminosity of 139.0 fb^-1. This study looks to discriminate the dark photon signal produced by a vector-boson-fusion Higgs from all backgrounds using various machine learning techniques. Among the methods tested, XGBoost emerged as the most effective, achieving a MC simulated significance of 5.88 standard deviations. This marked a substantial 22.5% improvement compared to the standard VBF analysis.