Background Rejection in Atmospheric Cherenkov Telescopes using Recurrent Convolutional Neural Networks

Abstract

In this work, we present a new, high performance algorithm for background rejection in imaging atmospheric Cherenkov telescopes. We build on the already popular machine-learning techniques used in gamma-ray astronomy by the application of the latest techniques in machine learning, namely recurrent and convolutional neural networks, to the background rejection problem. Use of these machine-learning techniques addresses some of the key challenges encountered in the currently implemented algorithms and helps to significantly increase the background rejection performance at all energies. We apply these machine learning techniques to the H.E.S.S. telescope array, first testing their performance on simulated data and then applying the analysis to two well known gamma-ray sources. With real observational data we find significantly improved performance over the current standard methods, with a 20-25\% reduction in the background rate when applying the recurrent neural network analysis. Importantly, we also find that the convolutional neural network results are strongly dependent on the sky brightness in the source region which has important implications for the future implementation of this method in Cherenkov telescope analysis.

11 pages, 7 figures. To be submitted to The European Physical Journal C

References in corpus (10)

• Observations of the Crab Nebula with H.E.S.S
• Background Modelling in Very-High-Energy gamma-ray Astronomy
• Implementation of the Random Forest Method for the Imaging Atmospheric Cherenkov Telescope MAGIC
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Gamma-Hadron Separation in Very-High-Energy gamma-ray astronomy using a multivariate analysis method
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Application of Deep Learning methods to analysis of Imaging Atmospheric Cherenkov Telescopes data
• A new analysis strategy for detection of faint gamma-ray sources with Imaging Atmospheric Cherenkov Telescopes
• Deep Learning for Image Sequence Classification of Astronomical Events
• Systematic Differences due to High Energy Hadronic Interaction Models in Air Shower Simulations in the 100 GeV-100 TeV Range

Cited by in corpus (9)

• Deep learning with photosensor timing information as a background rejection method for the Cherenkov Telescope Array
• First Full-Event Reconstruction from Imaging Atmospheric Cherenkov Telescope Real Data with Deep Learning
• Application of Graph Networks to background rejection in Imaging Air Cherenkov Telescopes
• Muons as a tool for background rejection in Imaging Atmospheric Cherenkov Telescope arrays
• Signal extraction in atmospheric shower arrays designed for $200\mathrm{GeV}-50\mathrm{TeV}$ $\gamma$-ray astronomy
• Improvements to monoscopic analysis for imaging atmospheric Cherenkov telescopes: Application to H.E.S.S
• Machine Learning in Gamma Astronomy
• Analysis Methods for Gamma-ray Astronomy
• Reduction of detection limit and quantification uncertainty due to interferent by neural classification with abstention