Classifying Dimuons from Proton-Proton Scattering Using ML Techniques

The E1039/SpinQuest experiment at Fermi National Accelerator Laboratory uses a 120 GeV proton beam from the Main Injector, incident upon transversely polarized protons and deuterons using $NH_3$ and $ND_3$ targets, respectively. In addition to the measurement of the Sivers asymmetry in Drell-Yan \(pp\) and \(pd\) scattering from sea quarks, SpinQuest will study transverse-spin effects, particularly the transverse single-spin asymmetry (TSSA) in \( J/\psi \) production. The angular distributions from the $J/\psi$ decay could play an important role in understanding the gluon contribution to the proton spin structure. However, before making such extractions of the angular distributions, it is necessary to isolate signal events from the target from events originating at other sources and from the combinatorial background. To effectively and accurately classify the target events, it is important to generate simulated events that represent not only the tracks of interest but also the track fragments that may not be reconstructable if the acceptance of the detector is narrow. All potential track fragments and signal tracks can provide a complete picture (detector hits) of an event. Using a composition of muon tracks from the simulations we construct hit matrices for training artificial intelligence-based models. Additionally, we explore the possibility of classifying the target events of complex hit patterns in these simulated events to use in future physics analysis. An update on the current status and progress of the machine learning-based classification will be provided.