Hostname: page-component-745bb68f8f-d8cs5 Total loading time: 0 Render date: 2025-02-11T12:32:35.149Z Has data issue: false hasContentIssue false
  • English
  • Français
Accepted manuscript

WALLABY Pilot Survey: HI source-finding with a machine learning framework

Published online by Cambridge University Press:  10 February 2025

Li Wang Open the ORCID record for Li Wang [Opens in a new window] ,
O. Ivy Wong Open the ORCID record for O. Ivy Wong [Opens in a new window] ,
Tobias Westmeier Open the ORCID record for Tobias Westmeier [Opens in a new window] ,
Chandrashekar Murugeshan Open the ORCID record for Chandrashekar Murugeshan [Opens in a new window] ,
Karen Lee-Waddell Open the ORCID record for Karen Lee-Waddell [Opens in a new window] ,
Yuanzhi Cai Open the ORCID record for Yuanzhi Cai [Opens in a new window] ,
Xiu Liu ,
Austin Xiaofan Shen ,
Jonghwan Rhee  and
Helga Dénes Open the ORCID record for Helga Dénes [Opens in a new window]
...Show all authors
Li Wang*
Affiliation:
ATNF, CSIRO Space and Astronomy, P.O. Box 1130, Bentley, WA 6102, Australia
O. Ivy Wong
Affiliation:
ATNF, CSIRO Space and Astronomy, P.O. Box 1130, Bentley, WA 6102, Australia International Centre for Radio Astronomy Research (ICRAR), University of Western Australia, 35 Stirling Hwy, Crawley, WA 6009, Australia ARC Centre of Excellence for All-Sky Astrophysics in 3 Dimensions (ASTRO 3D), Australia
Tobias Westmeier
Affiliation:
International Centre for Radio Astronomy Research (ICRAR), University of Western Australia, 35 Stirling Hwy, Crawley, WA 6009, Australia ARC Centre of Excellence for All-Sky Astrophysics in 3 Dimensions (ASTRO 3D), Australia
Chandrashekar Murugeshan
Affiliation:
ATNF, CSIRO Space and Astronomy, P.O. Box 1130, Bentley, WA 6102, Australia ARC Centre of Excellence for All-Sky Astrophysics in 3 Dimensions (ASTRO 3D), Australia
Karen Lee-Waddell
Affiliation:
ATNF, CSIRO Space and Astronomy, P.O. Box 1130, Bentley, WA 6102, Australia International Centre for Radio Astronomy Research (ICRAR), University of Western Australia, 35 Stirling Hwy, Crawley, WA 6009, Australia International Centre for Radio Astronomy Research (ICRAR), Curtin University, Bentley, WA 6102, Australia
Yuanzhi Cai
Affiliation:
CSIRO Mineral Resource, 26 Dick Perry Ave, Kensington, WA 6151, Australia
Xiu Liu
Affiliation:
ATNF, CSIRO Space and Astronomy, P.O. Box 1130, Bentley, WA 6102, Australia Western Australian School of Mines: Minerals, Energy and Chemical Engineering, Curtin University, GPO Box U1987, Perth, WA 6845, Australia
Austin Xiaofan Shen
Affiliation:
ATNF, CSIRO Space and Astronomy, P.O. Box 1130, Bentley, WA 6102, Australia
Jonghwan Rhee
Affiliation:
International Centre for Radio Astronomy Research (ICRAR), University of Western Australia, 35 Stirling Hwy, Crawley, WA 6009, Australia
Helga Dénes
Affiliation:
School of Physical Sciences and Nanotechnology, Yachay Tech University, Hacienda San José S/N, 100119, Urcuquí, Ecuador
Nathan Deg
Affiliation:
Department of Physics, Engineering Physics, and Astronomy, Queen’s University, Kingston ON K7L 3N6, Canada
Peter Kamphuis
Affiliation:
Ruhr University Bochum, Faculty of Physics and Astronomy, Astronomical Institute (AIRUB), 44780 Bochum, Germany
Barbara Catinella
Affiliation:
International Centre for Radio Astronomy Research (ICRAR), University of Western Australia, 35 Stirling Hwy, Crawley, WA 6009, Australia ARC Centre of Excellence for All-Sky Astrophysics in 3 Dimensions (ASTRO 3D), Australia
*
Author for correspondence: Li Wang, Email: [email protected].
Get access Rights & Permissions [Opens in a new window]

Abstract

The data volumes generated by theWALLABY atomic Hydrogen (HI) survey using the Australian Square Kilometre Array Pathfinder (ASKAP) necessitate greater automation and reliable automation in the task of source-finding and cataloguing. To this end, we introduce and explore a novel deep learning framework for detecting low Signal-to-Noise Ratio (SNR) HI sources in an automated fashion. Specifically, our proposed method provides an automated process for separating true HI detections from false positives when used in combination with the Source Finding Application (SoFiA) output candidate catalogues. Leveraging the spatial and depth capabilities of 3D ConvolutionalNeuralNetworks (CNNs), our method is specifically designed to recognize patterns and features in three-dimensional space, making it uniquely suited for rejecting false positive sources in low SNR scenarios generated by conventional linear methods. As a result, our approach is significantly more accurate in source detection and results in considerably fewer false detections compared to previous linear statistics-based source finding algorithms. Performance tests using mock galaxies injected into real ASKAP data cubes reveal our method’s capability to achieve near-100% completeness and reliability at a relatively low integrated SNR ∼ 3 – 5. An at-scale version of this tool will greatly maximise the science output from the upcoming widefield HI surveys.

Keywords

data analysisradio linessurveys
Type
Research Article
Information
Publications of the Astronomical Society of Australia , Accepted manuscript , pp. 1 - 14
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of Astronomical Society of Australia

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)