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

T: Fachverband Teilchenphysik

T 10: Neutrino Astronomy I

T 10.1: Vortrag

Montag, 31. März 2025, 16:45–17:00, VG 1.105

Classification of incoming neutrino events in IceCube using machine learning — •Sophie Loipolder, Rasmus Ørsøe, and Chiara Bellenghi for the IceCube collaboration — Technical University of Munich, Munich, Germany

In neutrino telescopes, event topologies differ depending on the neutrino flavor, the energy and the interaction type. For the reconstruction of the energy and direction of an incoming event, it is best to know the event type in advance to apply the suitable reconstruction algorithm for the respective topology.

This presentation discusses the development and implementation of a neural network-based classifier designed to improve the identification of event topologies in IceCube, a neutrino telescope located at the South Pole. Considering the continuous advances in machine learning, this approach aims to enhance the performance of existing methods currently in use for the classification of real-time neutrino event topologies.

Keywords: neutrinos; IceCube; machine learning; classification