GraphNeT: Graph neural networks for neutrino telescope event reconstruction

TL;DR

GraphNeT introduces a flexible, open-source framework utilizing graph neural networks to achieve fast, high-quality event reconstruction across various neutrino telescopes, enabling real-time analysis and broad applicability.

Contribution

The paper presents GraphNeT, a comprehensive Python framework that simplifies training and deploying GNNs for neutrino event reconstruction with state-of-the-art performance.

Findings

GNNs in GraphNeT outperform traditional methods in speed and accuracy.

Framework is adaptable to various detector configurations.

Enables real-time event reconstruction for neutrino telescopes.

Abstract

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 reconstruction with state-of-the-art performance, for arbitrary detector configurations, with inference times that are orders of magnitude faster than traditional reconstruction techniques. GNNs from GraphNeT are flexible enough to be applied to data from all neutrino telescopes, including future projects such as IceCube extensions or P-ONE. This means that GNN-based reconstruction can be used to provide state-of-the-art performance on most reconstruction tasks in neutrino telescopes, at real-time event rates, across experiments and physics analyses, with vast potential impact for neutrino and astro-particle physics.