Artificial Neural Networks for cosmic gamma-ray propagation in the Universe

Abstract

We explore the potential of an artificial neural network (ANN) based method intelligence to probe the propagation of cosmic $\gamma$-ray photons in the extragalactic Universe. The journey of $\gamma$-rays emitted from a distant source like blazar to the observer at the Earth is impeded by the absorption through the interaction with the extragalactic background light (EBL), leading to an electron-positron pair production. This process dominates for gamma ray photons with energy above 10 GeV propagating over the cosmological distances. The effect of $\gamma$-ray attenuation is characterized by a physical quantity called \emph{optical depth}, which strongly depends on the $\gamma$-ray photon energy, redshift of the source, and density of the EBL photons. We estimate the optical depth values for $\gamma$-ray energies above 10 GeV emitted from the sources at redshifts in the range 0.01 to 1 using three different and most promising EBL models. These optical depth estimates are randomly divided into two data sets for training and testing of the ANN using energy, redshift as inputs and optical depth as output. The optimization of ANN-performance for each EBL model employs standard back-propagation (BP) and radial-basis function (RBF) algorithms. The performance of the ANN model using the RBF is found to be superior to the BP method. In particular, the RBF-ANN with 40 neurons in the hidden layer corresponding to the EBL model proposed by Finke et al. (2010) shows the best performance for the propagation of $\gamma$-rays in the Universe.

arXiv comment23 Pages, 6 Tables, 6 Figures, Accepted for Publication in New Astronomy Journal

References in corpus (36)

• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• The extragalactic optical-infrared background radiations, their time evolution and the cosmic photon-photon opacity
• The Cosmic Infrared Background: Measurements and Implications
• Extragalactic Background Light Inferred from AEGIS Galaxy SED-type Fractions
• The COBE Diffuse Infrared Background Experiment Search for the Cosmic Infrared Background: I. Limits and Detections
• Modeling the Extragalactic Background Light from Stars and Dust
• Very-High-Energy Gamma Rays from a Distant Quasar: How Transparent Is the Universe?
• Intergalactic Photon Spectra from the Far IR to the UV Lyman Limit for $0<z<6$ and the Optical Depth of the Universe to High Energy Gamma-Rays
• Evidence for a new light spin-zero boson from cosmological gamma-ray propagation?
• Search for Spectral Irregularities due to Photon-Axionlike-Particle Oscillations With the Fermi Large Area Telescope
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• The Extragalactic Background Light and the Gamma-ray Opacity of the Universe
• Probabilistic Random Forest: A machine learning algorithm for noisy datasets
• The extragalactic background light revisited and the cosmic photon-photon opacity
• A $\gamma$-ray determination of the Universe's star-formation history
• Indications for a pair-production anomaly from the propagation of VHE gamma-rays
• Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
• Neural computation as a tool for galaxy classification : methods and examples
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Wide Field Imaging. I. Applications of Neural Networks to object detection and star/galaxy classification
• Limits on the extragalactic background light in the Fermi era
• A GeV-TeV Measurement of the Extragalactic Background Light
• Gamma-rays from Blazars and the Extragalactic Background Light
• Cascade photons as test of protons in UHECR
• A method for setting upper limits to the extragalactic background light with Fermi-LAT and TeV observations of blazars
• Importance of axion-like particles for very-high-energy astrophysics
• Comparative performance of some popular ANN algorithms on benchmark and function approximation problems
• Is the Universe More Transparent to Gamma Rays Than Previously Thought?
• Testing CIBER cosmic infrared background measurements and axionlike particles with observations of TeV blazars
• Modelling the dusty universe I: Introducing the artificial neural network and first applications to luminosity and colour distributions
• Intrinsic VHE Gamma-ray spectra of Blazars as a probe for Extragalactic Background Light
• Constraining the star formation rate with the extragalactic background light
• Extragalactic background light models and GeV-TeV observation of blazars
• Artificial Neural Network based gamma-hadron segregation methodology for TACTIC telescope
• Redshifted broad absorption line quasars found via machine-learned spectral similarity
• Probing the evolution of the EBL photon density out to $z\sim 1$ via $\gamma$-ray propagation measurements with Fermi

Cited by in corpus (1)

• Classification of the \emph{Fermi}-LAT Blazar Candidates of Uncertain type using eXtreme Gradient Boosting