Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Application of pattern spectra and convolutional neural networks to the analysis of simulated Cherenkov Telescope Array data

Aschersleben, J. ; Peletier, R. F. ; Vecchi, M. ; Wilkinson, M. H. F. ; Carlile, C. LU ; Dravins, D. LU orcid and Zmija, A. (2022) 37th International Cosmic Ray Conference In Proceedings of Science 395.
Abstract
The Cherenkov Telescope Array (CTA) will be the next generation gamma-ray observatory and will be the major global instrument for very-high-energy astronomy over the next decade, offering 5 − 10 × better flux sensitivity than current generation gamma-ray telescopes. Each telescope will provide a snapshot of gamma-ray induced particle showers by capturing the induced Cherenkov emission at ground level. The simulation of such events provides images that can be used as training data for convolutional neural networks (CNNs) to determine the energy of the initial gamma rays. Compared to other state-of-the-art algorithms, analyses based on CNNs promise to further enhance the performance to be achieved by CTA. Pattern spectra are commonly used... (More)
The Cherenkov Telescope Array (CTA) will be the next generation gamma-ray observatory and will be the major global instrument for very-high-energy astronomy over the next decade, offering 5 − 10 × better flux sensitivity than current generation gamma-ray telescopes. Each telescope will provide a snapshot of gamma-ray induced particle showers by capturing the induced Cherenkov emission at ground level. The simulation of such events provides images that can be used as training data for convolutional neural networks (CNNs) to determine the energy of the initial gamma rays. Compared to other state-of-the-art algorithms, analyses based on CNNs promise to further enhance the performance to be achieved by CTA. Pattern spectra are commonly used tools for image classification and provide the distributions of the shapes and sizes of various objects comprising an image. The use of relatively shallow CNNs on pattern spectra would automatically select relevant combinations of features within an image, taking advantage of the 2D nature of pattern spectra. In this work, we generate pattern spectra from simulated gamma-ray events instead of using the raw images themselves in order to train our CNN for energy reconstruction. This is different from other relevant learning and feature selection methods that have been tried in the past. Thereby, we aim to obtain a significantly faster and less computationally intensive algorithm, with minimal loss of performance. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0) (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
author collaboration
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Convolution, Cosmic rays, Cosmology, Feature extraction, Neural networks, Particle size analysis, Telescopes, Cherenkov emissions, Cherenkov telescope arrays, Convolutional neural network, Current generation, Gamma ray observatories, Gamma ray telescope, Gamma-rays, Ground level, Pattern spectrum, Very high energies, Gamma rays
host publication
37th International Cosmic Ray Conference (ICRC2021) - GAI - Gamma Ray Indirect
series title
Proceedings of Science
volume
395
article number
697
conference name
37th International Cosmic Ray Conference
conference location
Berlin, Germany
conference dates
2021-07-12 - 2021-07-23
external identifiers
  • scopus:85145018470
ISSN
1824-8039
DOI
10.22323/1.395.0697
language
English
LU publication?
yes
id
46ecd678-6cc8-4ee2-a732-d7afa7bb7b54
date added to LUP
2023-01-16 13:38:10
date last changed
2024-04-17 20:33:32
@inproceedings{46ecd678-6cc8-4ee2-a732-d7afa7bb7b54,
  abstract     = {{The Cherenkov Telescope Array (CTA) will be the next generation gamma-ray observatory and will be the major global instrument for very-high-energy astronomy over the next decade, offering 5 − 10 × better flux sensitivity than current generation gamma-ray telescopes. Each telescope will provide a snapshot of gamma-ray induced particle showers by capturing the induced Cherenkov emission at ground level. The simulation of such events provides images that can be used as training data for convolutional neural networks (CNNs) to determine the energy of the initial gamma rays. Compared to other state-of-the-art algorithms, analyses based on CNNs promise to further enhance the performance to be achieved by CTA. Pattern spectra are commonly used tools for image classification and provide the distributions of the shapes and sizes of various objects comprising an image. The use of relatively shallow CNNs on pattern spectra would automatically select relevant combinations of features within an image, taking advantage of the 2D nature of pattern spectra. In this work, we generate pattern spectra from simulated gamma-ray events instead of using the raw images themselves in order to train our CNN for energy reconstruction. This is different from other relevant learning and feature selection methods that have been tried in the past. Thereby, we aim to obtain a significantly faster and less computationally intensive algorithm, with minimal loss of performance. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0)}},
  author       = {{Aschersleben, J. and Peletier, R. F. and Vecchi, M. and Wilkinson, M. H. F. and Carlile, C. and Dravins, D. and Zmija, A.}},
  booktitle    = {{37th International Cosmic Ray Conference (ICRC2021) - GAI - Gamma Ray Indirect}},
  issn         = {{1824-8039}},
  keywords     = {{Convolution; Cosmic rays; Cosmology; Feature extraction; Neural networks; Particle size analysis; Telescopes; Cherenkov emissions; Cherenkov telescope arrays; Convolutional neural network; Current generation; Gamma ray observatories; Gamma ray telescope; Gamma-rays; Ground level; Pattern spectrum; Very high energies; Gamma rays}},
  language     = {{eng}},
  series       = {{Proceedings of Science}},
  title        = {{Application of pattern spectra and convolutional neural networks to the analysis of simulated Cherenkov Telescope Array data}},
  url          = {{http://dx.doi.org/10.22323/1.395.0697}},
  doi          = {{10.22323/1.395.0697}},
  volume       = {{395}},
  year         = {{2022}},
}