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

  • 43 views

  • 0 favorites

  • <p>ICRC</p>

    ICRC

  • 1391 media
  • uploaded June 25, 2021

Discussion timeslot (ZOOM-Meeting): 13. July 2021 - 12:00
ZOOM-Meeting URL: https://desy.zoom.us/j/98542982538
ZOOM-Meeting ID: 98542982538
ZOOM-Meeting Passcode: ICRC2021
Corresponding Session: https://icrc2021-venue.desy.de/channel/52-Analysis-Methods-Catalogues-Community-Tools-Machine-Learning-GAD-GAI/64
Live-Stream URL: https://icrc2021-venue.desy.de/livestream/Discussion-04/5

Abstract:
'The Large High Altitude Air Shower Observatory (LHAASO), is a multi-component experiment located at Daocheng (4410 m a.s.l.), Sichuan province, P.R. China. The identification of gamma rays from protons is an important foundation and premise for gamma ray research. In this paper, we use deep learning algorithm to extract the key features of events directly based on a large amount of original information, and explore the identification power of gamma rays from protons of LHAASO experiment. The Convolutional Neural Network(CNN), Deep Neural Networks(DNN) and Graph Neural Networksxa0(GNN) are trained and tested based on a large number of simulation events respectively. Compared with the traditional methods, we have found that the trained CNN, DNN and GNN models all have improvements in the effect of proton and gamma discrimination.'

Authors: F Zhang
Co-Authors: C He | Y.C Hao | J Hou | F.R Zhu
Collaboration: Lhaaso

Indico-ID: 941
Proceeding URL: https://pos.sissa.it/395/741

Tags:
Presenter: F Zhang

Additional files