Hostname: page-component-7b7567c8c-fvjsw Total loading time: 0 Render date: 2026-11-15T22:39:08.808Z Has data issue: false hasContentIssue false
  • English
  • Français

Deep Radio Image Segmentation

Published online by Cambridge University Press:  01 August 2025

Hattie StewartOpen the ORCID record for Hattie Stewart[Opens in a new window],
Mark Birkinshaw and
Jason Yeung
Hattie Stewart*
Affiliation:
University of BristolRutherford Appleton Laboratory
Mark Birkinshaw
Affiliation:
University of Bristol
Jason Yeung
Affiliation:
Rutherford Appleton Laboratory
*
email: hattie.stewart@bristol.ac.uk
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

We show that the U-Net neural network architecture provides an efficient and effective way of locating sources in SKA Data Challenge datasets. The improved performance relative to PyBDSF is quantified and U-Net is proposed as an efficient source finder for real radio surveys.

Keywords

Radio SurveysMachine LearningSquare Kilometre Array

Information

Type
Poster Paper
Information
Proceedings of the International Astronomical Union , Volume 19 , Symposium S368: Machine Learning in Astronomy: Possibilities and Pitfalls , August 2023, pp. 127 - 128
Check for updates
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of International Astronomical Union

References

Bonaldi, A., An, T., Brüggen, M., et al. 2021, MNRAS, 500, 3821 Google Scholar
Mohan, N. & Rafferty, D. 2015, Python Blob Detection and Source Finder, Astrophysics Source Code Library, ascl:1502.007Google Scholar
Ronneberger, O., Fischer, P. & Brox, T. 2015 in: Navab, N. et al. (eds.), Medical Image Computing and Computer-Assisted Intervention, Lecture Notes in Computer Science 9351, p. 234 (Springer)Google Scholar