Analysis of the HiSCORE Simulated Events in TAIGA Experiment Using Convolutional Neural Networks

TL;DR

This paper explores using convolutional neural networks to analyze HiSCORE data from the TAIGA gamma-ray observatory, aiming to improve the reconstruction of air shower parameters like energy and direction.

Contribution

It introduces a CNN-based approach for analyzing HiSCORE events, providing preliminary results that compare favorably with traditional methods.

Findings

CNN can analyze HiSCORE data treating it as images

Preliminary results show promising accuracy in reconstructing air shower parameters

Comparison indicates potential advantages over traditional analysis methods

Abstract

TAIGA is a hybrid observatory for gamma-ray astronomy at high energies in range from 10 TeV to several EeV. It consists of instruments such as TAIGA-IACT, TAIGA-HiSCORE, and others. TAIGA-HiSCORE, in particular, is an array of wide-angle timing Cherenkov light stations. TAIGA-HiSCORE data enable to reconstruct air shower characteristics, such as air shower energy, arrival direction, and axis coordinates. In this report, we propose to consider the use of convolution neural networks in task of air shower characteristics determination. We use Convolutional Neural Networks (CNN) to analyze HiSCORE events, treating them like images. For this, the times and amplitudes of events recorded at HiSCORE stations are used. The work discusses a simple convolutional neural network and its training. In addition, we present some preliminary results on the determination of the parameters of air showers such as the direction and position of the shower axis and the energy of the primary particle and compare them with the results obtained by the traditional method.