Machine Learning Application to Potential Discovery of Dark Matter Vector isotriplet in Muon Colliders.
Muon Colliders, Machine Learning, Dark Matter, Standard Model
The Standard Model (SM) of elementary particles successfully describes all known particles and their interactions, apart from gravitational interaction. Despite its recognized success, the SM still has some gaps in the description of the microscopic world and cosmological properties of the universe, such as the nature of Dark Matter (DM). Therefore, it is a great challenge of Particle Physics to search for a candidate particle for DM. A widely accepted hypothesis is that the DM is made up of weakly interacting massive particles (WIMP's). Many models have been proposed considering the inclusion of WIMP candidates, in order to extend the SM symmetry group. In this dissertation, we intend to study a simple extension of the SM that adds as the only new component, a massive spin 1 field, known as the Dark Matter Vector Isotriplet Model (DMVIM). This model has two free parameters: the mass of the vector field and a Higgs coupling. Therefore, it is intended to address the potential of discovery of DM particles through the implementation of DMVIM in future Muon colliders. For the separation of events of interest and background events, a new strategy based on Machine Learning (ML) techniques will be used.