Speaker
Mary Calljeja
(Queen's University)
Description
In the search for neutrinoless double-beta decay, germanium detectors are a valuable tool. It is of interest to unterstand the position and energy of interactions inside the detectors. An accurate reconstruction of interaction position inside a detector is important for event characterization and background rejection. Novel approaches, such as machine learning, can complement or further improve traditional methods . In my talk, I will discuss the basics of machine learning from germanium detector data, along with my work to reconstruct the position of event interaction. Lastly, I will highlight the machine learning work done within our lab to calculate drift time and pole zero correction.
