Astronomical source detection in radio continuum maps with deep neural networks

TL;DR

This paper introduces a deep learning-based source finder for radio continuum maps, significantly improving detection accuracy and classification of astronomical sources in large-scale surveys like ASKAP EMU.

Contribution

The authors developed a Mask R-CNN based source finder tailored for radio images, enhancing detection and classification capabilities over existing methods.

Findings

Detection completeness above 85%

Reliability around 65%

Classification precision/recall above 90%

Abstract

Source finding is one of the most challenging tasks in upcoming radio continuum surveys with SKA precursors, such as the Evolutionary Map of the Universe (EMU) survey of the Australian SKA Pathfinder (ASKAP) telescope. The resolution, sensitivity, and sky coverage of such surveys is unprecedented, requiring new features and improvements to be made in existing source finders. Among them, reducing the false detection rate, particularly in the Galactic plane, and the ability to associate multiple disjoint islands into physical objects. To bridge this gap, we developed a new source finder, based on the Mask R-CNN object detection framework, capable of both detecting and classifying compact, extended, spurious, and poorly imaged sources in radio continuum images. The model was trained using ASKAP EMU data, observed during the Early Science and pilot survey phase, and previous radio survey data, taken with the VLA and ATCA telescopes. On the test sample, the final model achieves an overall detection completeness above 85\%, a reliability of $\sim$65\%, and a classification precision/recall above 90\%. Results obtained for all source classes are reported and discussed.