A Deep Learning Approach to Improving the Arrival-Direction Accuracy of Gamma-Ray Air-Shower Measurements with the Tibet-III Air-Shower Array
Abstract
The Tibet ASγ experiment observes cosmic gamma rays from several teraelectron volts to the petaelectron volt range using an array of ground-based surface air-shower detectors (Tibet-III), which is composed of plastic scintillators. The arrival direction is conventionally reconstructed by fitting the shower front to detector hit-timing data, and the resulting angular resolution is approximately 0.5∘ to 0.2∘ in the energy range from 10 to 100 TeV. In this study, to further improve the directional reconstruction accuracy, we developed a new arrival-direction reconstruction method that integrates a convolutional neural network (CNN) with the conventional method. Evaluations using gamma-ray events generated by Monte Carlo simulations show that the angular resolution is improved by approximately 10\,\%--15\,\% compared with that achieved with the conventional method. In addition, this performance improvement shows little dependence on the zenith angle up to 40∘. The proposed method provides a performance gain equivalent to increasing the Tibet-III array, which consists of approximately 600 detectors, by roughly 150 to 200 detectors.
Related
- Improving cosmological distance measurements at high redshift using Lyman-Alpha forest BAO reconstruction
- HyQ-LC: Improving Light-Curve Classification with Hybrid Quantum--Classical Learning
- Learning JWST. I. A Foundation Model for New Population Discoveries and Morphology-Aware Photometric Redshift Measurements in the JADES Survey
- Photon arrival time lags in 3D radiative transfer with SKIRT
- KKR 18: A Late Arrival Galaxy?
BibTeX
@misc{okukawa2026deep,
title = {{A Deep Learning Approach to Improving the Arrival-Direction Accuracy of Gamma-Ray Air-Shower Measurements with the Tibet-III Air-Shower Array}},
author = {S. Okukawa and M. Kobayashi and K. Hara and K. Hibino and Y. Katayose and K. Kawata and M. Ohnishi and T. K. Sako and T. Sako and A. Shiomi and M. Takita},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.09736},
eprint = {2610.09736},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.09736},
}
RIS
TY - UNPB
TI - A Deep Learning Approach to Improving the Arrival-Direction Accuracy of Gamma-Ray Air-Shower Measurements with the Tibet-III Air-Shower Array
AU - S. Okukawa
AU - M. Kobayashi
AU - K. Hara
AU - K. Hibino
AU - Y. Katayose
AU - K. Kawata
AU - M. Ohnishi
AU - T. K. Sako
AU - T. Sako
AU - A. Shiomi
AU - M. Takita
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.09736
UR - https://arxiv.org/abs/2610.09736
AB - The Tibet ASγ experiment observes cosmic gamma rays from several teraelectron volts to the petaelectron volt range using an array of ground-based surface air-shower detectors (Tibet-III), which is composed of plastic scintillators. The arrival direction is conventionally reconstructed by fitting the shower front to detector hit-timing data, and the resulting angular resolution is approximately 0.5^∘ to 0.2^∘ in the energy range from 10 to 100 TeV. In this study, to further improve the directional reconstruction accuracy, we developed a new arrival-direction reconstruction method that integrates a convolutional neural network (CNN) with the conventional method. Evaluations using gamma-ray events generated by Monte Carlo simulations show that the angular resolution is improved by approximately 10\,\%--15\,\% compared with that achieved with the conventional method. In addition, this performance improvement shows little dependence on the zenith angle up to 40^∘. The proposed method provides a performance gain equivalent to increasing the Tibet-III array, which consists of approximately 600 detectors, by roughly 150 to 200 detectors.
ER -