A machine learning approach for mass composition analysis with TALE-SD data

Ryuhei Arimura

doi:10.1051/epjconf/202328302011

EPJ

a
b
c
d
e
ap
st
h
plus
ds
pv
ti
qt
am
n

Proceedings

Open Access

EPJ Web of Conferences 283, 02011 (2023)
https://doi.org/10.1051/epjconf/202328302011

A machine learning approach for mass composition analysis with TALE-SD data

Ryuhei Arimura^* on behalf of the Telescope Array Collaboration (a complete list of authors can be found at the end of the proceedings)

Graduate School of Science, Osaka City University, Osaka, Japan

^* Corresponding author: m21sa003@st.osaka-cu.ac.jp

Published online: 28 April 2023

Abstract

The TALE experiment is a Telescope Array Low-energy Extension constructed to observe cosmic rays with energies down to 10^16.5 to clarify the origin of the second knee and the energy of the galactic to extragalactic CRs transition. TALE consists of 10 high-elevation fluorescence detectors and 80 scintillation counters in an area of 21 km². The key of data interpretation is the mass composition of cosmic rays, and we report on a machine learning approach of mass composition analysis that utilizes waveform data of TALE scintillation counters.

© The Authors, published by EDP Sciences, 2023

This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.