Experimental Verification of a Convolutional Neural Network Separation Method in TeV Gamma-Ray Observations by the Tibet ASγ Experiment

Abstract Since 1990, the Tibet AS$\gamma$ experiment has been observing gamma rays and cosmic rays with energies greater than several TeV using a surface air shower array. An underground muon detector (MD) array operating since 2014 enables us to significantly discriminate between gamma rays and cosmic rays by counting the number of muons in the air showers. However, discrimination with only the air shower array is challenging. We developed a convolutional neural network (CNN)-based method to improve the sensitivity of gamma-ray measurement data recorded by only the air shower array. The area-under-the-curve values of the CNN method for gamma rays generated by a Monte Carlo (MC) simulation assuming a gamma-ray source (Crab Nebula) were 0.75 at $\sim$10 TeV and 0.83 at $\sim$100 TeV. The detection significances of gamma rays were improved by factors of 1.232 $\pm$ 0.007 at $\sim$10 TeV and 1.557 $\pm$ 0.022 at $\sim$100 TeV. For verification, we applied the proposed method to experimental data including high-purity gamma-ray-like events in the direction of the Crab Nebula, acquired using both arrays. The distributions of gamma-ray-like properties obtained from the CNN were in good agreement with the MC Simulation, with reduced $\chi ^2$ values of 0.507–1.57, corresponding to an upper cumulative probability of 0.120–0.871.

Authors

Institutions

Publication Details

Journal
Progress of Theoretical and Experimental Physics
Published
2025-09-24
DOI
https://doi.org/10.1093/ptep/ptaf127
Primary Topic
Astrophysics and Cosmic Phenomena
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Experimental Verification of a Convolutional Neural Network Separation Method in TeV Gamma-Ray Observations by the Tibet ASγ Experiment

T. Sako, Takao Saito, Yuxuan Li, W Y Chen et al.
Progress of Theoretical and Experimental Physics
Astrophysics and Cosmic Phenomena
article

Experimental Verification of a Convolutional Neural Network Separation Method in TeV Gamma-Ray Observations by the Tibet ASγ Experiment

T. Sako, Takao Saito, Yuxuan Li, W Y Chen, Y. H. Lin, Yuhong Zhou, Y. W. Bao, Qian Wu, S. P. Zhao, Yoshiaki Nakamura, Y. Katayose, J S Liu, Ying Guo, Yong Chen, T. Sako, L Y Liu, Y. H. Meng, J. L. Zhang, Jing Huang, X. B. Qu, Y. H. Tan, Congzhan Liu, Yongqiang Zhang, Wangdui, Q. Q. Shi, Jia Yin, C. C. Ning, Yu Masuda, Z. T. He, K. Kasahara, H. Y. Jia, C. F. Feng, Y. Hayashi, G. M. Le, R. Usui, C. Kato, K. Hibino, Yuzhen Feng, W. Liu, W J Li, Yong Guo, Yifeng Wang, N. Tateyama, Seiji Ozawa, L. M. Zhai, M. Amenomori, L. K. Ding, Labaciren Labaciren, Cirennima, H. Wu, Xuan Qian, S. Okukawa, Jing Shao, M. Anzorena, T. Makishima, Yasuo Noguchi, K. Kawata, Kun Hu, H. Sugimoto, Jinlong Xu, H. H. He, Xiaowei Qian, K. Fujita, Q. B. Gou, K. Munakata, A Shiomi, X. R. Meng, Shin‐ichiro Kato, M. Matsumoto, M. Kozai, Kai Fang, S. Wang, H. Q. Lu, L. Xue, T. L. Chen, F. Sugimoto, Yuanqing Yao, D. Chen, H. Nanjo, Mario Shibata, W. Takano, H J Li, Yu You, A F Li, Xu Chen, Ying Zhang, Hongming Zhang, Hao Wang, Shixuan Wang, Peng Jiang, Hiroshi Tsuchiya, S. W. Cui, Qi Gao, X. X. Zhou, Yingxin Zhang, J. Fang, Zhongshan Yang, T. Kawashima, Shuki Torii, Chun Han, Akira Mizuno, R. Murillo Garcia, M. Nishizawa, M. Takita, Zhaoyang Feng, X. Zhang, K. Hara, X. J. Bi, S. Udo, M. Y. Liu, Haibing Hu, M. Ohnishi, Danzengluobu, Shinpei Matsuhashi, M. Sakata, Z. Y. Feng, Tadao Shibasaki, Zhaxisangzhu, H. B. Hu, N. Hotta, Y. Yokoe, A. F. Yuan, X Y Zhang, H.-B. Jin, G. Imaizumi, Liang Jiang, B. Liu, G. Yamagishi
article en

Abstract

Abstract Since 1990, the Tibet AS$\gamma$ experiment has been observing gamma rays and cosmic rays with energies greater than several TeV using a surface air shower array. An underground muon detector (MD) array operating since 2014 enables us to significantly discriminate between gamma rays and cosmic rays by counting the number of muons in the air showers. However, discrimination with only the air shower array is challenging. We developed a convolutional neural network (CNN)-based method to improve the sensitivity of gamma-ray measurement data recorded by only the air shower array. The area-under-the-curve values of the CNN method for gamma rays generated by a Monte Carlo (MC) simulation assuming a gamma-ray source (Crab Nebula) were 0.75 at $\sim$10 TeV and 0.83 at $\sim$100 TeV. The detection significances of gamma rays were improved by factors of 1.232 $\pm$ 0.007 at $\sim$10 TeV and 1.557 $\pm$ 0.022 at $\sim$100 TeV. For verification, we applied the proposed method to experimental data including high-purity gamma-ray-like events in the direction of the Crab Nebula, acquired using both arrays. The distributions of gamma-ray-like properties obtained from the CNN were in good agreement with the MC Simulation, with reduced $\chi ^2$ values of 0.507–1.57, corresponding to an upper cumulative probability of 0.120–0.871.

Progress of Theoretical and Experimental PhysicsVol. 2025(10)
Japan Atomic Energy Agency (JP), University of Science and Technology of China (CN), Centre National de la Recherche Scientifique (FR), Shinshu University (JP), Tibet University (CN), China Meteorological Administration (CN), Hirosaki University (JP), Waseda University (JP), Konan University (JP), Hefei University of Technology (CN), Shibaura Institute of Technology (JP), Yokohama National University (JP), National Institute of Informatics (JP), Shonan Institute of Technology (JP), Chinese Academy of Sciences (CN), Utsunomiya University (JP), Nagano Prefectural Ueda Senior High School (JP), Institut d'Astrophysique de Paris (FR), Purple Mountain Observatory (CN), Sorbonne Université (FR), Kanagawa University (JP), Shandong Management University (CN), Institute of Particle Physics (CA), Shangdong Agriculture and Engineering University (CN), Institute of Space Sciences (ES), Taishan University (CN), Shinshu University Hospital (JP), Astronomy and Space (AU), Research Organization of Information and Systems (JP), Tokyo Metropolitan Industrial Technology Research Institute (JP), China University of Petroleum, East China (CN), National Astronomical Observatories (CN), University of Chinese Academy of Sciences (CN), Southwest Jiaotong University (CN), College of Industrial Technology (JP), Shandong Agricultural University (CN), The University of Tokyo (JP), Nanjing University (CN), National Institute of Information and Communications Technology (JP), Hebei Normal University (CN)
Openalex Percentile: Top 86%
Astrophysics and Cosmic Phenomena
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.