Application of Graph Networks to background rejection in Imaging Air Cherenkov Telescopes

Abstract

Imaging Air Cherenkov Telescopes (IACTs) are essential to ground-based observations of gamma rays in the GeV to TeV regime. One particular challenge of ground-based gamma-ray astronomy is an effective rejection of the hadronic background. We propose a new deep-learning-based algorithm for classifying images measured using single or multiple Imaging Air Cherenkov Telescopes. We interpret the detected images as a collection of triggered sensors that can be represented by graphs and analyzed by graph convolutional networks. For images cleaned of the light from the night sky, this allows for an efficient algorithm design that bypasses the challenge of sparse images in deep learning approaches based on computer vision techniques such as convolutional neural networks. We investigate different graph network architectures and find a promising performance with improvements to previous machine-learning and deep-learning-based methods.

Published version, 22 pages, 8 figures

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Geometric deep learning: going beyond Euclidean data
• Observations of the Crab Nebula with H.E.S.S
• ParticleNet: Jet Tagging via Particle Clouds
• Deep Learning and its Application to LHC Physics
• Simulation of Imaging Atmospheric Cherenkov Telescopes with CORSIKA and sim_telarray
• A Convolutional Neural Network Neutrino Event Classifier
• Gamma-Hadron Separation in Very-High-Energy gamma-ray astronomy using a multivariate analysis method
• Application of Deep Learning methods to analysis of Imaging Atmospheric Cherenkov Telescopes data
• A Deep Learning-based Reconstruction of Cosmic Ray-induced Air Showers
• A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory
• Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCube
• The analysis of VERITAS muon images using convolutional neural networks
• Deep-Learning based Reconstruction of the Shower Maximum $X_{\max }$ using the Water-Cherenkov Detectors of the Pierre Auger Observatory
• Extraction of the Muon Signals Recorded with the Surface Detector of the Pierre Auger Observatory Using Recurrent Neural Networks
• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• Background Rejection in Atmospheric Cherenkov Telescopes using Recurrent Convolutional Neural Networks
• Deep learning with photosensor timing information as a background rejection method for the Cherenkov Telescope Array
• Identification of Patterns in Cosmic-Ray Arrival Directions using Dynamic Graph Convolutional Neural Networks
• Investigating a Deep Learning Method to Analyze Images from Multiple Gamma-ray Telescopes
• Investigations of the Systematic Uncertainties in Convolutional Neural Network Based Analysis of Atmospheric Cherenkov Telescope Data

Cited by in corpus (7)

• Improvements to monoscopic analysis for imaging atmospheric Cherenkov telescopes: Application to H.E.S.S
• Discriminating sub-TeV gamma and hadron-induced showers through their footprints
• Application of Graph Networks to a wide-field Water-Cherenkov-based Gamma-Ray Observatory
• Nonparametric signal separation in very-high-energy gamma ray observations with probabilistic neural networks
• Multi-View Deep Learning for Imaging Atmospheric Cherenkov Telescopes
• Enhancing Neutrino Reconstruction in Water-Cherenkov Air Shower Arrays Using Multi-Photosensors
• Ultra-Fast Generation of Air Shower Images for Imaging Air Cherenkov Telescopes using Generative Adversarial Networks