Identifying nearby sources of ultra-high-energy cosmic rays with deep learning
arXiv:1912.00625 · doi:10.1088/1475-7516/2020/11/005
Abstract
We present a method to analyse arrival directions of ultra-high-energy cosmic rays (UHECRs) using a classifier defined by a deep convolutional neural network trained on a HEALPix grid. To illustrate a high effectiveness of the method, we employ it to estimate prospects of detecting a large-scale anisotropy of UHECRs induced by a nearby source with an (orbital) detector having a uniform exposure of the celestial sphere and compare the results with our earlier calculations based on the angular power spectrum. A minimal model for extragalactic cosmic rays and neutrinos by Kachelrieß, Kalashev, Ostapchenko and Semikoz (2017) is assumed for definiteness and nearby active galactic nuclei Centaurus A, M82, NGC 253, M87 and Fornax A are considered as possible sources of UHECRs. We demonstrate that the proposed method drastically improves sensitivity of an experiment by decreasing the minimal required amount of detected UHECRs or the minimal detectable fraction of from-source events several times compared to the approach based on the angular power spectrum. We also test robustness of the neural networks against different models of the large-scale Galactic magnetic fields and variations of the mass composition of UHECRs, and consider situations when there are two nearby sources or the dominating source is not known a~priori. In all cases, the neural networks demonstrate good performance unless the test models strongly deviate from those used for training. The method can be readily applied to the analysis of data of the Telescope Array, the Pierre Auger Observatory and other cosmic ray experiments.
arXiv commentv2: a major extension of the 1st version, which is kept almost intact as sections 1-4; 21 pages v3: to be published in JCAP. Numbers in tables fixed, a few minor changes, conclusions unchanged. The code and trained models are available at https://github.com/okolo/ml_cr_aniso
References in corpus (20)
- HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
- Machine learning and the physical sciences
- The SIMBAD astronomical database
- A New Model of the Galactic Magnetic Field
- Observation of a Large-scale Anisotropy in the Arrival Directions of Cosmic Rays above eV
- The Galactic Magnetic Field
- CRPropa 3 - a Public Astrophysical Simulation Framework for Propagating Extraterrestrial Ultra-High Energy Particles
- Deriving global structure of the Galactic Magnetic Field from Faraday Rotation Measures of extragalactic sources
- Indication of anisotropy in arrival directions of ultra-high-energy cosmic rays through comparison to the flux pattern of extragalactic gamma-ray sources
- New limits on extragalactic magnetic fields from rotation measures
- DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
- Radio galaxies of the local universe: all-sky catalog, luminosity functions, and clustering
- Acceleration of Ultra-High Energy Cosmic Rays in the Colliding Shells of Blazars and GRBs: Constraints from the Fermi Gamma ray Space Telescope
- A minimal model for extragalactic cosmic rays and neutrinos
- Analytical models of X-shape magnetic fields in galactic halos
- Constraints from Faraday rotation on the magnetic field structure in the Galactic halo
- Convolutional Neural Networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis
- Solenoidal Improvements for the JF12 Galactic Magnetic Field Model
- Ultra-High-Energy Cosmic Rays from Low-Luminosity Active Galactic Nuclei
- Prospects of detecting a large-scale anisotropy of ultra-high-energy cosmic rays from a nearby source with the K-EUSO orbital telescope