Application of Graph Networks to a wide-field Water-Cherenkov-based Gamma-Ray Observatory

TL;DR

This paper explores the use of graph neural networks to enhance background rejection and energy reconstruction in water-Cherenkov gamma-ray observatories, demonstrating superior performance over traditional methods in simulations.

Contribution

It introduces the application of graph neural networks to gamma-ray data analysis, showing improved background rejection and energy resolution over existing techniques.

Findings

GNNs outperform traditional classification algorithms in background rejection.

GNNs achieve better energy resolution than template-based methods.

Simulation results indicate significant performance improvements.

Abstract

With their wide field of view and high duty cycle, water-Cherenkov-based observatories are integral to studying the very high-energy gamma-ray sky. For gamma-ray observations, precise event reconstruction and highly effective background rejection are crucial and have been continuously improving in recent years. In this work, we investigate the application of graph neural networks (GNNs) to background rejection and energy reconstruction and benchmark their performance against state-of-the-art methods. In our simulation study, we find that GNNs outperform hand-designed classification algorithms and observables in background rejection and find an improved energy resolution compared to template-based methods.