Prediction of Location of High Energy Shower Cores using Artificial Neural Networks

Artificial Neural Network (ANN)s can be modeled for High Energy Particle analysis with special emphasis on shower core location. The work describes the use of an ANN based system which has been configured to predict locations of cores of showers in the range 1010.5 to 1020.5 eV. The system receives density values as inputs and generates coordinates of shower events recorded for values captured by 20 core positions and 80 detectors in an area of 100 meters. Twenty ANNs are trained for the purpose and the positions of shower events optimized by using cooperative ANN learning. The results derived with variations of input upto 50% show success rates in the range of 90s.

Authors:

• Gitanjali Devi
• Kandarpa Kumar Sarma
• Pranayee Datta
• Anjana Kakoti Mahanta

Keywords:

• EAS
• Shower
• Core
• ANN
• Location.

References:

[1] R. A. Mewaldt: "Cosmic Rays", Macmillan Encyclopedia of Physicsavailable
at http://www.srl.caltech.edu/personnel/dick/cos-encyc.html,
1996.
[2] R. Engel: "Theory and Phenomenology of Extensive Air
Showers", Forschungszentrum Karlsruhe, Germany- available at
http://moriond.in2p3.fr/J05/trans/sunday/engel1.pdf, 2005.
[3] D. Hanna, "Application of Neural Nets to Extensive Air-Showers",
Proceedings of the 22nd International Cosmic Ray Conference, IUPAP,
Volume 4, p: 500, 1991.
[4] J. C. Perrett and J T P M van Stekelenborg, "The applications of
neural networks in the core location analysis of extensive air showers",
Bartol Research Institute, University of Delaware, 217 Sharp Laboratory,
Newark, DE 19716, USA J. Phys. G: Nucl. Pert. Phys. 17, pp:1291-1302,
1991.
[5] H. J. Mayer, "A neural network algorithm for core location analysis at
large extended air shower arrays", Nuclear Instruments and Methods in
Physics Research, Section A: Accelerators, Spectrometers, Detectors and
Associated Equipment, Volume 317, Issues 1-2, pp. 339-345, June, 1992.
[6] P. Sommers: "Extensive Air Showers and Measurement Techniques",
Physics - Astrophysics, C. R. Acad. Sci. Paris, t. 4, Serie IV, pp. 1 - 12,
2004.
[7] A. Chilingarian, G. Gharagyozyan, S. Ghazaryan, G. Hovsepyan, E.
Mamidjanyan, L. Melkumyan, V. Romakhin, A. Vardanyan and S.
Sokhoyan: "Study of extensive air showers and primary energy spectra
by MAKET-ANI detector on mountain Aragats", Elsavier Journal of
Astroparticle Physics, vol. 28, pp. 5871, 2007.
[8] T. Wibig, "The Artificial Neural Networks as a tool for analysis of
the individual Extensive Air Showers data", Preprint submitted to Elsevier
Preprint (1 February 2008), available at http://arxiv.org/abs/hepph/
9608227v1.
[9] S. Haykin: Neural Networks A Comprehensive Foundation, 2nd ed.,
Pearson Education, New Delhi, India, 2003.
[10] R. Rojas, Neural Networks A Systematic Introduction, Springer, Berlin,
1996.