GraphNeT: Graph neural networks for neutrino telescope event reconstruction

• Published in: arXiv.org
• Main Authors: Søgaard, Andreas, Ørsøe, Rasmus F, Bozianu, Leon, Holm, Morten, Iversen, Kaare Endrup, Guggenmos, Tim, Martin Ha Minh, Eller, Philipp, Petersen, Troels C
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 21.10.2022
• Subjects: Graph neural networks; Neutrinos; Particle physics; Reconstruction; Telescopes

GraphNeT is an open-source python framework aimed at providing high quality, user friendly, end-to-end functionality to perform reconstruction tasks at neutrino telescopes using graph neural networks (GNNs). GraphNeT makes it fast and easy to train complex models that can provide event reconstructio...