Deep learning method for identifying mass composition of ultra-high-energy cosmic rays

Abstract

We introduce a novel method for identifying the mass composition of ultra-high-energy cosmic rays using deep learning. The key idea of the method is to use a chain of two neural networks. The first network predicts the type of a primary particle for individual events, while the second infers the mass composition of an ensemble of events. We apply this method to the Monte-Carlo data for the Telescope Array Surface Detectors readings, on which it yields an unprecedented low error of 7% for 4-component approximation. We also discuss the problems of applying the developed method to the experimental data, and the way they can be resolved.

arXiv comment19 pages, 5 figures

References in corpus (39)

• Adam: A Method for Stochastic Optimization
• First Observation of the Greisen-Zatsepin-Kuzmin Suppression
• Observation of the suppression of the flux of cosmic rays above 4x10^19eV
• QGSJET-II: towards reliable description of very high energy hadronic interactions
• Measurements of the Cosmic Ray Composition with Air Shower Experiments
• The surface detector array of the Telescope Array experiment
• Energy determination in the Akeno Giant Air Shower Array experiment
• Combined fit of spectrum and composition data as measured by the Pierre Auger Observatory
• Depth of Maximum of Air-Shower Profiles at the Pierre Auger Observatory: Composition Implications
• Indications of Proton-Dominated Cosmic Ray Composition above 1.6 EeV
• The Cosmic Ray Energy Spectrum Observed with the Surface Detector of the Telescope Array Experiment
• Muons in air showers at the Pierre Auger Observatory: Mean number in highly inclined events
• Testing Hadronic Interactions at Ultrahigh Energies with Air Showers Measured by the Pierre Auger Observatory
• Study of Ultra-High Energy Cosmic Ray Composition Using Telescope Array's Middle Drum Detector and Surface Array in Hybrid Mode
• A Multi-Component Measurement of the Cosmic Ray Composition Between 10^{17} eV and 10^{18} eV
• Upper limit on the diffuse flux of UHE tau neutrinos from the Pierre Auger Observatory
• Depth of Ultra High Energy Cosmic Ray Induced Air Shower Maxima Measured by the Telescope Array Black Rock and Long Ridge FADC Fluorescence Detectors and Surface Array in Hybrid Mode
• Report on Tests and Measurements of Hadronic Interaction Properties with Air Showers
• On the transition from Galactic to extragalactic cosmic-rays: spectral and composition features from two opposite scenarios
• Ultra High Energy Cosmic Rays: The disappointing model
• Probing the origin of ultra-high-energy cosmic rays with neutrinos in the EeV energy range using the Pierre Auger Observatory
• Study of muons from ultra-high energy cosmic ray air showers measured with the Telescope Array experiment
• Constraints on the diffuse photon flux with energies above $10^{18}$ eV using the surface detector of the Telescope Array experiment
• Muon content of ultra-high-energy air showers: Yakutsk data versus simulations
• Mass composition of ultra-high-energy cosmic rays with the Telescope Array Surface Detector Data
• Probing the evolution of the EAS muon content in the atmosphere with KASCADE-Grande
• Signatures of the transition from galactic to extragalactic cosmic rays
• Dethinning Extensive Air Shower Simulations
• Upper limit on the flux of photons with energies above 10^19 eV using the Telescope Array surface detector
• Mapping UHECRs deflections through the turbulent galactic magnetic field with the latest RM data
• No muon excess in extensive air showers at 100-500 PeV primary energy: EAS-MSU results
• Density of GeV muons in air showers measured with IceTop
• Muon content of extensive air showers: comparison of the energy spectra obtained by the Sydney University Giant Air-shower Recorder and by the Pierre Auger Observatory
• Deep-Learning based Reconstruction of the Shower Maximum $X_{\max }$ using the Water-Cherenkov Detectors of the Pierre Auger Observatory
• A new composition-sensitive parameter for Ultra-High Energy Cosmic Rays
• Extraction of the Muon Signals Recorded with the Surface Detector of the Pierre Auger Observatory Using Recurrent Neural Networks
• UHECR mass composition at highest energies from anisotropy of their arrival directions
• Using Deep Learning to Enhance Event Geometry Reconstruction for the Telescope Array Surface Detector
• CORSIKA Simulation of the Telescope Array Surface Detector

Cited by in corpus (1)

• Methods of machine learning for the analysis of cosmic rays mass composition with the KASCADE experiment data