Identification of proton and gamma in LHAASO-KM2A simulation data with deep learning algorithms

the LHAASO Collaboration

Identification of proton and gamma in LHAASO-KM2A simulation data with deep learning algorithms

the LHAASO Collaboration

Research output: Contribution to journal › Conference article › peer-review

Abstract

Identification of proton and gamma plays an essential role in ultra-high energy gamma-ray astronomy with LHAASO-KM2A. In this work, two neural networks (deep neural networks (DNN) and graph neural networks (GNN)) are applied to distinguish proton and gamma in the LHAASOKM2A simulation data. The receiver operating characteristic (ROC) curves are used to evaluate the quality of the model. Both KM2A-DNN and KM2A-GNN models give higher Area Under Curve (AUC) scores than the traditional baseline model.

Original language	English
Article number	741
Journal	Proceedings of Science
Volume	395
State	Published - 18 Mar 2022
Externally published	Yes
Event	37th International Cosmic Ray Conference, ICRC 2021 - Virtual, Berlin, Germany Duration: 12 Jul 2021 → 23 Jul 2021

Cite this

@article{a55a91306476437fab762604f55e8b78,

title = "Identification of proton and gamma in LHAASO-KM2A simulation data with deep learning algorithms",

abstract = "Identification of proton and gamma plays an essential role in ultra-high energy gamma-ray astronomy with LHAASO-KM2A. In this work, two neural networks (deep neural networks (DNN) and graph neural networks (GNN)) are applied to distinguish proton and gamma in the LHAASOKM2A simulation data. The receiver operating characteristic (ROC) curves are used to evaluate the quality of the model. Both KM2A-DNN and KM2A-GNN models give higher Area Under Curve (AUC) scores than the traditional baseline model.",

author = "\{the LHAASO Collaboration\} and F. Zhang and Zhu, \{F. R.\} and Liu, \{S. M.\} and Hao, \{Y. C.\} and C. He and J. Hou and Z. Li and Zhen Cao and F. Aharonian and Q. An and Axikegu and Bai, \{L. X.\} and Bai, \{Y. X.\} and Bao, \{Y. W.\} and D. Bastieri and Bi, \{X. J.\} and Bi, \{Y. J.\} and H. Cai and Cai, \{J. T.\} and Zhe Cao and J. Chang and Chang, \{J. F.\} and Chen, \{B. M.\} and Chen, \{E. S.\} and J. Chen and Liang Chen and Liang Chen and Long Chen and Chen, \{M. J.\} and Chen, \{M. L.\} and Chen, \{Q. H.\} and Chen, \{S. H.\} and Chen, \{S. Z.\} and Chen, \{T. L.\} and Chen, \{X. L.\} and Y. Chen and N. Cheng and Cheng, \{Y. D.\} and Cui, \{S. W.\} and Cui, \{X. H.\} and Cui, \{Y. D.\} and \{D'Ettorre Piazzoli\}, B. and Dai, \{B. Z.\} and Dai, \{H. L.\} and Dai, \{Z. G.\} and Danzengluobu and \{della Volpe\}, D. and Dong, \{X. J.\} and Duan, \{K. K.\} and Geng, \{L. S.\}",

note = "Publisher Copyright: {\textcopyright} Copyright owned by the author(s) under the terms of the Creative Commons.; 37th International Cosmic Ray Conference, ICRC 2021 ; Conference date: 12-07-2021 Through 23-07-2021",

year = "2022",

month = mar,

day = "18",

language = "英语",

volume = "395",

journal = "Proceedings of Science",

issn = "1824-8039",

publisher = "Sissa Medialab Srl",

}

TY - JOUR

T1 - Identification of proton and gamma in LHAASO-KM2A simulation data with deep learning algorithms

AU - the LHAASO Collaboration

AU - Zhang, F.

AU - Zhu, F. R.

AU - Liu, S. M.

AU - Hao, Y. C.

AU - He, C.

AU - Hou, J.

AU - Li, Z.

AU - Cao, Zhen

AU - Aharonian, F.

AU - An, Q.

AU - Axikegu,

AU - Bai, L. X.

AU - Bai, Y. X.

AU - Bao, Y. W.

AU - Bastieri, D.

AU - Bi, X. J.

AU - Bi, Y. J.

AU - Cai, H.

AU - Cai, J. T.

AU - Cao, Zhe

AU - Chang, J.

AU - Chang, J. F.

AU - Chen, B. M.

AU - Chen, E. S.

AU - Chen, J.

AU - Chen, Liang

AU - Chen, Long

AU - Chen, M. J.

AU - Chen, M. L.

AU - Chen, Q. H.

AU - Chen, S. H.

AU - Chen, S. Z.

AU - Chen, T. L.

AU - Chen, X. L.

AU - Chen, Y.

AU - Cheng, N.

AU - Cheng, Y. D.

AU - Cui, S. W.

AU - Cui, X. H.

AU - Cui, Y. D.

AU - D'Ettorre Piazzoli, B.

AU - Dai, B. Z.

AU - Dai, H. L.

AU - Dai, Z. G.

AU - Danzengluobu,

AU - della Volpe, D.

AU - Dong, X. J.

AU - Duan, K. K.

AU - Geng, L. S.

PY - 2022/3/18

Y1 - 2022/3/18

N2 - Identification of proton and gamma plays an essential role in ultra-high energy gamma-ray astronomy with LHAASO-KM2A. In this work, two neural networks (deep neural networks (DNN) and graph neural networks (GNN)) are applied to distinguish proton and gamma in the LHAASOKM2A simulation data. The receiver operating characteristic (ROC) curves are used to evaluate the quality of the model. Both KM2A-DNN and KM2A-GNN models give higher Area Under Curve (AUC) scores than the traditional baseline model.

AB - Identification of proton and gamma plays an essential role in ultra-high energy gamma-ray astronomy with LHAASO-KM2A. In this work, two neural networks (deep neural networks (DNN) and graph neural networks (GNN)) are applied to distinguish proton and gamma in the LHAASOKM2A simulation data. The receiver operating characteristic (ROC) curves are used to evaluate the quality of the model. Both KM2A-DNN and KM2A-GNN models give higher Area Under Curve (AUC) scores than the traditional baseline model.

UR - https://www.scopus.com/pages/publications/85123976685

M3 - 会议文章

AN - SCOPUS:85123976685

SN - 1824-8039

VL - 395

JO - Proceedings of Science

JF - Proceedings of Science

M1 - 741

T2 - 37th International Cosmic Ray Conference, ICRC 2021

Y2 - 12 July 2021 through 23 July 2021

ER -

Identification of proton and gamma in LHAASO-KM2A simulation data with deep learning algorithms

Abstract

Other files and links

Fingerprint

Cite this