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

T: Fachverband Teilchenphysik

T 97: Data, AI, Computing, Electronics IX (AI-based Object Reconstruction)

T 97.6: Vortrag

Freitag, 4. April 2025, 10:15–10:30, VG 2.102

Exploring position reconstruction of HPGe detector events in LEGEND with a deep neural network — •Christoph Seibt¹ and Aobo Li² — ¹TU Dresden, Germany — ²UCSD, USA

LEGEND is searching for neutrinoless double-beta (0νββ) decay, using High-Purity Germanium (HPGe) crystals enriched in ⁷⁶Ge as both source and detector. With its second phase, LEGEND-1000, the experiment uses 1 ton of germanium crystals to reach a discovery potential of half-lives greater than 10²⁸ years. HPGe detectors measure pulse shapes of excellent quality, which are analyzed to reconstruct the events energy and reject background-induced events. These pulse shapes depend on the location of the events in the detector. This work leverages pulse shape topology to extract positional information, utilizing a recurrent-type neural network to overcome the limitations of classical methods. Simulated pulses from random event locations are used for training and testing. The current progress on a deep neural network for position reconstruction is displayed in this presentation. It shows the current reconstruction potential and first applications to specifying detector parameters.

This work is supported by the U.S. DOE and the NSF, the LANL, ORNL and LBNL LDRD programs; the European ERC and Horizon programs; the German DFG, BMBF, and MPG; the Italian INFN; the Polish NCN and MniSW; the Czech MEYS; the Slovak SRDA; the Swiss SNF; the UK STFC; the Canadian NSERC and CFI; the LNGS, SNOLAB, and SURF facilities.

Keywords: Machine Learning; Neutrinos; Simulation