Hostname: page-component-8448b6f56d-mp689 Total loading time: 0 Render date: 2024-04-24T19:04:56.248Z Has data issue: false hasContentIssue false
  • English
  • Français

The analysis of VERITAS muon images using convolutional neural networks

Published online by Cambridge University Press:  30 May 2017

Qi Feng ,
Tony T. Y. Lin  and
for the VERITAS Collaboration
Qi Feng*
Affiliation:
Physics Department, McGill University, Montreal, QC H3A 2T8, Canada
Tony T. Y. Lin
Affiliation:
Physics Department, McGill University, Montreal, QC H3A 2T8, Canada
for the VERITAS Collaboration
Affiliation:
http://veritas.sao.arizona.edu/
*
†qi.feng2@mcgill.ca
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Imaging atmospheric Cherenkov telescopes (IACTs) are sensitive to rare gamma-ray photons, buried in the background of charged cosmic-ray (CR) particles, the flux of which is several orders of magnitude greater. The ability to separate gamma rays from CR particles is important, as it is directly related to the sensitivity of the instrument. This gamma-ray/CR-particle classification problem in IACT data analysis can be treated with the rapidly-advancing machine learning algorithms, which have the potential to outperform the traditional box-cut methods on image parameters. We present preliminary results of a precise classification of a small set of muon events using a convolutional neural networks model with the raw images as input features. We also show the possibility of using the convolutional neural networks model for regression problems, such as the radius and brightness measurement of muon events, which can be used to calibrate the throughput efficiency of IACTs.

Keywords

Data analysisclassificationconvolutional neural networksregression.
Type
Contributed Papers
Information
Proceedings of the International Astronomical Union , Volume 12 , Symposium S325: Astroinformatics , October 2016 , pp. 173 - 179
Copyright
Copyright © International Astronomical Union 2017 

References

Abadi, M., Agarwal, A., Barham, P., et al. 2016, arXiv:1603.04467Google Scholar
Acero, F., Aharonian, F., Akhperjanian, A. G., et al. 2009, Science, 326, 1080 CrossRefGoogle Scholar
Aharonian, F. A., Chilingarian, A. A., Konopelko, A. K., & Plyasheshnikov, A. V. 1991, Nuclear Instruments and Methods in Physics Research A, 302, 522 CrossRefGoogle Scholar
Albert, J., Aliu, E., Anderhub, H., et al. 2008, Nuclear Instruments and Methods in Physics Research A, 588, 424 CrossRefGoogle Scholar
Aliu, E., Anderhub, H., Antonelli, L. A., et al. 2009, Astroparticle Physics, 30, 293 Google Scholar
Brun, R. & Rademakers, F. 1997, Nuclear Instruments and Methods in Physics Research A, 389, 81 CrossRefGoogle Scholar
Cardenzana, J. V., for the VERITAS Collaboration 2015, arXiv:1508.07310Google Scholar
Christiansen, J., VERITAS Collaboration 2012, American Institute of Physics Conference Series, 1505, 709 Google Scholar
Chollet, F. 2013, keras GitHub repository, https://github.com/fchollet/keras Google Scholar
Cogan, P. 2008, Proc. International Cosmic Ray Conference, 3, 1385 Google Scholar
Hillas, A. M. 1985, International Cosmic Ray Conference, 3Google Scholar
Holder, J. 2011, International Cosmic Ray Conference, 12, 137 Google Scholar
Kingma, D. & Ba, J. 2014, arXiv:1412.6980Google Scholar
Krause, M., Pueschel, E., & Maier, G., 2016, submitted to Astroparticle Physics Google Scholar
Krizhevsky, A., Sutskever, I., & Hinton, G. E., Advances in Neural Information Processing Systems, 2012, pp. 1097–1105.Google Scholar
Lemoine-Goumard, M., Degrange, B., & Tluczykont, M. 2006, Astroparticle Physics, 25, 195 CrossRefGoogle Scholar
Park, N., for the VERITAS Collaboration 2015, arXiv:1508.07070Google Scholar
Reynolds, P. T. 1993, Irish Astronomical Journal, 21, 118 Google Scholar
Simmons, B. D., Lintott, C., Willett, K. W., et al. 2016, arXiv:1610.03070Google Scholar
Simonyan, K. & Zisserman, A. 2014, arXiv:1409.1556Google Scholar
Staszak, D., for the VERITAS Collaboration 2015, arXiv:1508.06597Google Scholar
S. Vincent for the VERITAS Collaboration 2015, arXiv:1509.01980Google Scholar