Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 2: Machine-learning methods and computing in particle physics

AKPIK 2.6: Vortrag

Dienstag, 26. März 2019, 16:50–17:00, H10

Event reconstruction in EXO-200 using Deep Learning — •Johannes Link, Federico Bontempo, Tobias Ziegler, Gisela Anton, and Thilo Michel — Friedrich-Alexander-Universität Erlangen-Nürnberg, ECAP

The EXO-200 experiment searches for the neutrinoless double beta decay (0ν ββ) of ¹³⁶Xe using a time projection chamber (TPC) filled with enriched liquid xenon. An event taking place in the TPC leads to secondary electrons and scintillation light. The electrons drift in an electric field, where in the first plane of wires the induction signal and in the second plane of wires the collection signal is measured. In this contribution, we present an alternative approach of event reconstruction using Deep Learning methods, e.g. Convolutional Neural Networks (CNN). Raw collection and induction wire signals are used to reconstruct the energy and the position of events in the EXO-200 detector. We compare the performance of the Machine Learning approach to the conventional reconstruction in EXO-200.