Speaker
Manbing Li
(Universite de Geneve (CH))
Description
The Dark Matter Particle Explorer (DAMPE) is a space-based cosmic-ray observatory capable of measuring cosmic-ray electrons and positrons (CREs) with high precision up to 10 TeV. However, at multi-TeV energies, the low CRE rate necessitates an extended acceptance, including non-fiducial events. To recover these events, we introduce a Convolutional Neural Network (CNN) trained on calorimeter shower images to distinguish electrons from protons out15 side the fiducial volume. This approach extends DAMPE’s accep16 tance and improves CREs statistics. The CNN’s robustness again stshower leakage makes it a powerful tool for high-energy cosmic-ray studies, enhancing DAMPE’s cosmic-ray observations.
Author
Manbing Li
(Universite de Geneve (CH))
