Analysis, and machine learning anomaly detection of the VELO-LHCb calibration

Abstract

Silicon detectors are an extraordinary piece of equipment that has become the cornerstone of research in modern high energy physics. They are becoming increasingly useful in medical research as well. LHCbs VELO detector is itself, a microstrip silicon vertex detector. It is the heart of LHCb spectrometer and plays a vital role in the reconstruction of particle tracks. The data gathered by VELO is used in LHCb studies of CP violation and heavy flavour physics. This work presents the studies on the calibration parameters of the VELO-LHCb. The inference from the analysis, with the use of probabilistic programming, is then used to create a machine learning based anomaly detection system in the space of VELO calibration.