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 2.5: Vortrag

Dienstag, 26. März 2019, 16:40–16:50, H10

Refining the EXO-200 detector simulation using GANs — •Federico Bontempo, Johannes Link, Tobias Ziegler, Gisela Anton, and Thilo Michel — Friedrich-Alexander-Universität Erlangen-Nürnberg, ECAP

The EXO-200 experiment searches for the neutrinoless double beta (0νββ) decay of ¹³⁶Xe with a single-phase liquid xenon (LXe) time projection chamber (TPC) filled with enriched LXe. The TPC provides the deposited energy of events in LXe together with their 3D position. A GEANT4 Monte Carlo (MC) simulation is used to model the physics interactions and the resulting detector response. These simulations are crucial for most physics analyses. In this study, we apply Deep Learning methods, esp. Generative Adversarial Networks (GAN), to improve the MC simulations by reducing potential imprecisions compared to measurements. Improvements pave the way for applying other Deep Learning based methods that rely on an accurate detector modelling.