Radio Galaxy Zoo: Giant Radio Galaxy Classification using Multi-Domain Deep Learning

Abstract

In this work, we explore the potential of multi-domain multi-branch convolutional neural networks (CNNs) for identifying comparatively rare giant radio galaxies from large volumes of survey data, such as those expected for new-generation radio telescopes like the SKA and its precursors. The approach presented here allows models to learn jointly from multiple survey inputs, in this case NVSS and FIRST, as well as incorporating numerical redshift information. We find that the inclusion of multi-resolution survey data results in correction of 39% of the misclassifications seen from equivalent single domain networks for the classification problem considered in this work. We also show that the inclusion of redshift information can moderately improve the classification of giant radio galaxies.

22 pages, 11 figures, accepted by MNRAS

References in corpus (14)

• Science with ASKAP - the Australian Square Kilometre Array Pathfinder
• Classifying Radio Galaxies with Convolutional Neural Network
• Mega parsec relativistic jets launched from an accreting supermassive blackhole in an extreme spiral galaxy
• Radio Galaxy Zoo: A Search for Hybrid Morphology Radio Galaxies
• CNN Architecture Comparison for Radio Galaxy Classification
• MIGHTEE: Are giant radio galaxies more common than we thought?
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Attention-gating for improved radio galaxy classification
• Discovery of a new, 2.2 Mpc Giant Radio Galaxy at a redshift of 0.57
• Radio Observations of the Hubble Deep Field South Region III: The 2.5, 5.2 and 8.7 GHz Catalogues and Radio Source Properties
• Single-epoch supernova classification with deep convolutional neural networks
• IGR J17488-2338: a newly discovered giant radio galaxy
• Radiation Pattern of Radio and Optical Components of Extended Radio Sources
• New Extended Radio Sources From the NVSS