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.
Recommended Citation
"Identification Of Proton And Gamma In LHAASO-KM2A Simulation Data With Deep Learning Algorithms," Proceedings of Science, vol. 395, article no. 741, Sissa Medialab Srl, Mar 2022.
The definitive version is available at https://doi.org/10.22323/1.395.0741
Department(s)
Physics
Publication Status
Open Access
International Standard Serial Number (ISSN)
1824-8039
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2025 Sissa Medialab Srl, All rights reserved.
Publication Date
18 Mar 2022

Comments
National Natural Science Foundation of China, Grant 11947404