Göttingen 2025 – wissenschaftliches Programm

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

T: Fachverband Teilchenphysik

T 75: Neutrino Astronomy IV

T 75.6: Vortrag

Donnerstag, 3. April 2025, 17:30–17:45, VG 1.105

Advanced Northern Tracks Selection using a Graph Convolutional Neural Network for the IceCube Neutrino Observatory: Background Rejection — •Philipp Behrens, Jakob Böttcher, Shuyang Deng, Lasse Düser, Philipp Fürst, Leon Hamacher, Michael Handt, Lars Marten, Philipp Soldin, and Christopher Wiebusch for the IceCube collaboration — III. Physikalisches Institut, RWTH Aachen University, Aachen, Deutschland

The IceCube Neutrino Observatory is a large neutrino detector located in the ice at the geographic South Pole. It detects atmospheric and astrophysical neutrinos by Cherenkov radiation emitted by secondary particles with more than 5000 photomultipliers. A main challenge is the efficient distinction between neutrinos and air-shower-induced muons. The Advanced Northern Tracks Selection (ANTS) improves this classification using a deep graph convolutional neural network, capturing the node-like structure of the geometric arrangement of the photomultipliers inside the detector, as well as the raw sensor data. Using this architecture, both local and global features are learned. This work focuses on the evaluation and enhancement of the neural network architecture with respect to the background rejection of air-shower-induced muons.

Keywords: IceCube; Advanced Northern Track Selection; Neutrino Astronomy; Deep Learning