Mu2e Straw Tracker Background Removal Using Machine Learning

The primary goal of the Fermilab Mu2e Experiment is to search for charged lepton flavor violation through muon-to-electron conversion in the field of the nucleus without producing neutrinos. Documenting this muon decay process would confirm the charged-lepton equivalent to neutrino oscillation. Muon-to-electron conversion has not yet been observed experimentally, but the Mu2e detector hopes to become the first to record this rare conversion using increased production of muons at the Fermilab muon campus. Achieving this goal would have a significant impact by demonstrating a clear signature of new physics beyond the Standard Model, advancing analysis opportunities as scientists strive to understand interactions between fundamental particles.

In this poster I will demonstrate improvement on detector sensitivity through enhanced momentum resolution. This is achieved by implementing an optimized track reconstruction algorithm trained using machine learning to reduce background hits erroneously included in signal tracks during the track reconstruction process.