Göttingen 2025 – wissenschaftliches Programm

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

T: Fachverband Teilchenphysik

T 10: Neutrino Astronomy I

T 10.2: Vortrag

Montag, 31. März 2025, 17:00–17:15, VG 1.105

Machine Learning Tools for IceCube-Gen2 — •Francisco Javier Vara Carbonell and Alexander Kappes for the IceCube-Gen2 collaboration — Universität Münster, Institut für Kernphysik

Machine learning tools, especially neural networks, have triggered a revolution in many areas, including neutrino astronomy. They have great potential for future neutrino telescopes such as IceCube-Gen2 with a large number of small photomultipliers. Neural networks are well suited to tackle high-dimensional problems and can naturally incorporate the segmentation of these new optical sensors. Moreover, they have a fast inference time compared to conventional algorithms, which enables the processing of the high event rates expected from IceCube-Gen2. This talk will present potential applications of neural networks in IceCube-Gen2 in areas such as simulation, event reconstruction and noise reduction, covering the current state of their development and implementation.

Keywords: IceCube-Gen2; Neural Networks; Simulation; Reconstruction