Application of Deep Learning methods to analysis of Imaging Atmospheric Cherenkov Telescopes data

Abstract

Ground based gamma-ray observations with Imaging Atmospheric Cherenkov Telescopes (IACTs) play a significant role in the discovery of very high energy (E > 100 GeV) gamma-ray emitters. The analysis of IACT data demands a highly efficient background rejection technique, as well as methods to accurately determine the energy of the recorded gamma-ray and the position of its source in the sky. We present results for background rejection and signal direction reconstruction from first studies of a novel data analysis scheme for IACT measurements. The new analysis is based on a set of Convolutional Neural Networks (CNNs) applied to images from the four H.E.S.S. phase-I telescopes. As the H.E.S.S. cameras pixels are arranged in a hexagonal array, we demonstrate two ways to use such image data to train CNNs: by resampling the images to a square grid and by applying modified convolution kernels that conserve the hexagonal grid properties. The networks were trained on sets of Monte-Carlo simulated events and tested on both simulations and measured data from the H.E.S.S. array. A comparison between the CNN analysis to current state-of-the-art algorithms reveals a clear improvement in background rejection performance. When applied to H.E.S.S. observation data, the CNN direction reconstruction performs at a similar level as traditional methods. These results serve as a proof-of-concept for the application of CNNs to the analysis of events recorded by IACTs.

References in corpus (14)

• Observations of the Crab Nebula with H.E.S.S
• An Exceptional VHE Gamma-Ray Flare of PKS 2155-304
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• A high performance likelihood reconstruction of gamma-rays for Imaging Atmospheric Cherenkov Telescopes
• Simulation of Imaging Atmospheric Cherenkov Telescopes with CORSIKA and sim_telarray
• A Convolutional Neural Network Neutrino Event Classifier
• A Monte Carlo Template based analysis for Air-Cherenkov Arrays
• Gamma-Hadron Separation in Very-High-Energy gamma-ray astronomy using a multivariate analysis method
• H.E.S.S. Observations of PKS 2155-304
• Deep Convolutional Neural Networks as strong gravitational lens detectors
• Probes of Lorentz Violation
• The analysis of VERITAS muon images using convolutional neural networks
• Probing Convolutional Neural Networks for Event Reconstruction in γ-Ray Astronomy with Cherenkov Telescopes
• Data analysis techniques for stereo IACT systems

Cited by in corpus (46)

• Sensitivity of the Cherenkov Telescope Array to a dark matter signal from the Galactic centre
• Ultra-High-Energy Cosmic Rays: The Intersection of the Cosmic and Energy Frontiers
• A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• HexagDLy - Processing hexagonally sampled data with CNNs in PyTorch
• Event reconstruction for KM3NeT/ORCA using convolutional neural networks
• Extracting gamma-ray information from images with convolutional neural network methods on simulated Cherenkov Telescope Array data
• 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
• A convolutional neural network approach for reconstructing polarization information of photoelectric X-ray polarimeters
• Russian-German Astroparticle Data Life Cycle Initiative
• Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework
• First Full-Event Reconstruction from Imaging Atmospheric Cherenkov Telescope Real Data with Deep Learning
• 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
• The H.E.S.S. transients follow-up system
• Measurement of the Depth of Maximum of Air-Shower Profiles with energies between $10^{18.5}$ and $10^{20}$ eV using the Surface Detector of the Pierre Auger Observatory and Deep Learning
• Deep Learning for Energy Estimation and Particle Identification in Gamma-ray Astronomy
• X-ray Study of Spatial Structures in Tycho's Supernova Remnant Using Unsupervised Deep Learning
• Application of Graph Networks to background rejection in Imaging Air Cherenkov Telescopes
• Statistical Tools for Imaging Atmospheric Cherenkov Telescopes
• Deep learning techniques for Imaging Air Cherenkov Telescopes
• Studying deep convolutional neural networks with hexagonal lattices for imaging atmospheric Cherenkov telescope event reconstruction
• Impact of Satellite Trails on H.E.S.S. Astronomical Observations
• CTLearn: Deep Learning for Gamma-ray Astronomy
• Prospects for the characterization of the VHE emission from the Crab Nebula and Pulsar with the Cherenkov Telescope Array
• Energy Reconstruction in Analysis of Cherenkov Telescopes Images in TAIGA Experiment Using Deep Learning Methods
• 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
• Selection of gamma events from IACT images with deep learning methods
• Machine Learning for the EUSO-SPB2 Fluorescence Telescope Data Analysis
• The Preliminary Results on Analysis of TAIGA-IACT Images Using Convolutional Neural Networks
• Processing Images from Multiple IACTs in the TAIGA Experiment with Convolutional Neural Networks
• Particle identification in ground-based gamma-ray astronomy using convolutional neural networks
• Biologically Inspired Hexagonal Deep Learning for Hexagonal Image Generation
• Deep unsupervised domain adaptation applied to the Cherenkov Telescope Array Large-Sized Telescope
• Analysis Methods for Gamma-ray Astronomy
• Machine Learning in Gamma Astronomy
• Signal-background separation and energy reconstruction of gamma rays using pattern spectra and convolutional neural networks for the Small-Sized Telescopes of the Cherenkov Telescope Array
• Ultra-Fast Generation of Air Shower Images for Imaging Air Cherenkov Telescopes using Generative Adversarial Networks
• HexCNN: A Framework for Native Hexagonal Convolutional Neural Networks
• Multi-View Deep Learning for Imaging Atmospheric Cherenkov Telescopes
• Cats vs Dogs, Photons vs Hadrons
• Event types in H.E.S.S.: a combined analysis for different telescope types and energy ranges
• Advanced modelling of Night Sky Background light for Imaging Atmospheric Cherenkov Telescopes