eCite Digital Repository

Radio Galaxy Zoo: CLARAN - a deep learning classifier for radio morphologies

Citation

Wu, C and Wong, OI and Rudnick, L and Shabala, SS and Alger, MJ and Banfield, JK and Ong, CS and White, SV and Garon, AF and Norris, RP and Andernach, H and Tate, J and Lukic, V and Tang, H and Schawinski, K and Diakogiannis, FI, Radio Galaxy Zoo: CLARAN - a deep learning classifier for radio morphologies, Monthly Notices of the Royal Astronomical Society, 482, (1) pp. 1211-1230. ISSN 0035-8711 (2018) [Refereed Article]


Preview
PDF
4Mb
  

Copyright Statement

Copyright 2018 The Authors. This article has been accepted for publication in Monthly Notices of the Royal Astronomical Society ©:2018. Published by Oxford University Press on behalf of the Royal Astronomical Society. All rights reserved.

DOI: doi:10.1093/mnras/sty2646

Abstract

The upcoming next-generation large area radio continuum surveys can expect tens of millions of radio sources, rendering the traditional method for radio morphology classification through visual inspection unfeasible. We present CLARAN - Classifying Radio sources Automatically with Neural networks - a proof-of-concept radio source morphology classifier based upon the Faster Region-based Convolutional Neutral Networks method. Specifically, we train and test CLARAN on the FIRST and WISE (Wide-field Infrared Survey Explorer) images from the Radio Galaxy Zoo Data Release 1 catalogue. CLARAN provides end users with automated identification of radio source morphology classifications from a simple input of a radio image and a counterpart infrared image of the same region. CLARAN is the first open-source, end-to-end radio source morphology classifier that is capable of locating and associating discrete and extended components of radio sources in a fast (<200 ms per image) and accurate (≥90 per cent) fashion. Future work will improve CLARAN’s relatively lower success rates in dealing with multisource fields and will enable CLARAN to identify sources on much larger fields without loss in classification accuracy.

Item Details

Item Type:Refereed Article
Keywords:methods: numerical, methods: statistical, techniques: image processing, galaxies: active, radio continuum: galaxies
Research Division:Physical Sciences
Research Group:Astronomical and Space Sciences
Research Field:Cosmology and Extragalactic Astronomy
Objective Division:Expanding Knowledge
Objective Group:Expanding Knowledge
Objective Field:Expanding Knowledge in the Physical Sciences
UTAS Author:Shabala, SS (Dr Stas Shabala)
ID Code:130384
Year Published:2018
Web of Science® Times Cited:5
Deposited By:Mathematics and Physics
Deposited On:2019-01-23
Last Modified:2019-03-13
Downloads:5 View Download Statistics

Repository Staff Only: item control page