Deep learning with photosensor timing information as a background rejection method for the Cherenkov Telescope Array

Abstract

New deep learning techniques present promising new analysis methods for Imaging Atmospheric Cherenkov Telescopes (IACTs) such as the upcoming Cherenkov Telescope Array (CTA). In particular, the use of Convolutional Neural Networks (CNNs) could provide a direct event classification method that uses the entire information contained within the Cherenkov shower image, bypassing the need to Hillas parameterise the image and allowing fast processing of the data. Existing work in this field has utilised images of the integrated charge from IACT camera photomultipliers, however the majority of current and upcoming generation IACT cameras have the capacity to read out the entire photosensor waveform following a trigger. As the arrival times of Cherenkov photons from Extensive Air Showers (EAS) at the camera plane are dependent upon the altitude of their emission and the impact distance from the telescope, these waveforms contain information potentially useful for IACT event classification. In this test-of-concept simulation study, we investigate the potential for using these camera pixel waveforms with new deep learning techniques as a background rejection method, against both proton and electron induced EAS. We find that a means of utilising their information is to create a set of seven additional 2-dimensional pixel maps of waveform parameters, to be fed into the machine learning algorithm along with the integrated charge image. Whilst we ultimately find that the only classification power against electrons is based upon event direction, methods based upon timing information appear to out-perform similar charge based methods for gamma/hadron separation. We also review existing methods of event classifications using a combination of deep learning and timing information in other astroparticle physics experiments.

arXiv commentFull paper accepted in Astroparticle Physics. 39 Pages with 11 Figures. Minimal code to reproduce results in the paper available at: https://github.com/STSpencer/wavelearn_release. Some early results previously presented at ICRC2019 (doi:10.22323/1.358.0798)

References in corpus (34)

• Scikit-learn: Machine Learning in Python
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• ADADELTA: An Adaptive Learning Rate Method
• The Large Area Telescope on the Fermi Gamma-ray Space Telescope Mission
• Observations of the Crab Nebula with H.E.S.S
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• The major upgrade of the MAGIC telescopes, Part II: A performance study using observations of the Crab Nebula
• Background Modelling in Very-High-Energy gamma-ray Astronomy
• 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 Monte Carlo Template based analysis for Air-Cherenkov Arrays
• Gamma-Hadron Separation in Very-High-Energy gamma-ray astronomy using a multivariate analysis method
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Classifying Radio Galaxies with Convolutional Neural Network
• Improving the performance of the single-dish Cherenkov telescope MAGIC through the use of signal timing
• 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 new analysis method for very high definition Imaging Atmospheric Cherenkov Telescopes as applied to the CAT telescope
• Monte Carlo Performance Studies for the Site Selection of the Cherenkov Telescope Array
• Selection and 3D-Reconstruction of Gamma-Ray-induced Air Showers with a Stereoscopic System of Atmospheric Cherenkov Telescopes
• Extracting gamma-ray information from images with convolutional neural network methods on simulated Cherenkov Telescope Array data
• Machine Learning in High Energy Physics Community White Paper
• Gamma-Ray Astrophysics
• Background Rejection in Atmospheric Cherenkov Telescopes using Recurrent Convolutional Neural Networks
• Graph Neural Networks for IceCube Signal Classification
• Investigating a Deep Learning Method to Analyze Images from Multiple Gamma-ray Telescopes
• Probing Convolutional Neural Networks for Event Reconstruction in γ-Ray Astronomy with Cherenkov Telescopes
• A Compact High Energy Camera for the Cherenkov Telescope Array
• Signal recognition and background suppression by matched filters and neural networks for Tunka-Rex
• Run-Wise Simulations for Imaging Atmospheric Cherenkov Telescope Arrays
• Exploiting VERITAS Timing Information
• Estimation of the height of the first interaction in gamma-ray showers observed by Cherenkov telescopes
• Trigger and data rates expected for the CTA Observatory

Cited by in corpus (11)

• Application of Graph Networks to background rejection in Imaging Air Cherenkov Telescopes
• Deep learning techniques for Imaging Air Cherenkov Telescopes
• A search for dark matter among Fermi-LAT unidentified sources with systematic features in Machine Learning
• Application of neural networks to classification of data of the TUS orbital telescope
• Event reconstruction using pattern spectra and convolutional neural networks for the Cherenkov Telescope Array
• A new method of reconstructing images of gamma-ray telescopes applied to the LST-1 of CTAO
• 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
• Analysis Methods for Gamma-ray Astronomy
• Ultra-Fast Generation of Air Shower Images for Imaging Air Cherenkov Telescopes using Generative Adversarial Networks
• Multi-View Deep Learning for Imaging Atmospheric Cherenkov Telescopes