A neural network classifier for electron identification on the DAMPE experiment

Abstract

The Dark Matter Particle Explorer (DAMPE) is a space-borne particle detector and cosmic ray observatory in operation since 2015, designed to probe electrons and gamma rays from a few GeV to 10 TeV energy, as well as cosmic protons and nuclei up to 100 TeV. Among the main scientific objectives is the precise measurement of the cosmic electron+positron flux, which due to the very large proton background in orbit requires a powerful particle identification method. In the past decade, the field of machine learning has provided us the needed tools. This paper presents a neural network based approach to cosmic electron identification and proton rejection and showcases its performances based on simulated Monte Carlo data. The neural network reaches significantly lower background than the classical, cut-based method for the same detection efficiency, especially at highest energies. A good matching between simulations and real data completes the picture.

19 pages, 12 figures, accepted for publication in Journal of Instrumentation (JINST)

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Particle Dark Matter: Evidence, Candidates and Constraints
• Dark Matter Candidates from Particle Physics and Methods of Detection
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• cuDNN: Efficient Primitives for Deep Learning
• Direct detection of a break in the teraelectronvolt cosmic-ray spectrum of electrons and positrons
• Deep Learning and its Application to LHC Physics
• The DArk Matter Particle Explorer mission
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• Measurement of the cosmic-ray proton spectrum from 40 GeV to 100 TeV with the DAMPE satellite
• The Most Likely Sources of High Energy Cosmic-Ray Electrons in Supernova Remnants
• $e^{\pm }$ Excesses in the Cosmic Ray Spectrum and Possible Interpretations
• Deep Convolutional Neural Networks as strong gravitational lens detectors
• The on-orbit calibration of DArk Matter Particle Explorer
• Internal alignment and position resolution of the silicon tracker of DAMPE determined with orbit data
• Offline software for the DAMPE experiment
• A machine learning method to separate cosmic ray electrons from protons from 10 to 100 GeV using DAMPE data

Cited by in corpus (3)

• A deep learning method for the trajectory reconstruction of cosmic rays with the DAMPE mission
• An Unsupervised Machine Learning Method for Electron--Proton Discrimination of the DAMPE Experiment
• Energy Reconstruction of Non-fiducial Electron-Positron Events in the DAMPE Experiment Using Convolutional Neural Networks