A Neural Network Approach for Selecting Track-like Events in Fluorescence Telescope Data

TL;DR

This paper demonstrates how a simple convolutional neural network can effectively identify track-like events in fluorescence telescope data used for detecting ultra-high energy cosmic rays, aiding astrophysical research.

Contribution

The paper introduces a neural network method specifically designed for selecting track-like events in fluorescence telescope data, improving detection efficiency.

Findings

Neural network accurately identifies track-like events.

Method improves event selection in fluorescence telescope data.

Applicable to current and future cosmic ray detection experiments.

Abstract

In 2016-2017, TUS, the world's first experiment for testing the possibility of registering ultra-high energy cosmic rays (UHECRs) by their fluorescent radiation in the night atmosphere of Earth was carried out. Since 2019, the Russian-Italian fluorescence telescope (FT) Mini-EUSO ("UV Atmosphere") has been operating on the ISS. The stratospheric experiment EUSO-SPB2, which will employ an FT for registering UHECRs, is planned for 2023. We show how a simple convolutional neural network can be effectively used to find track-like events in the variety of data obtained with such instruments.