Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Deep learning for morphological identification of extended radio galaxies using weak labels

Journal Article · · Publications of the Astronomical Society of Australia
DOI:https://doi.org/10.1017/pasa.2023.46· OSTI ID:2419772

Abstract

The present work discusses the use of a weakly-supervised deep learning algorithm that reduces the cost of labelling pixel-level masks for complex radio galaxies with multiple components. The algorithm is trained on weak class-level labels of radio galaxies to get class activation maps (CAMs). The CAMs are further refined using an inter-pixel relations network (IRNet) to get instance segmentation masks over radio galaxies and the positions of their infrared hosts. We use data from the Australian Square Kilometre Array Pathfinder (ASKAP) telescope, specifically the Evolutionary Map of the Universe (EMU) Pilot Survey, which covered a sky area of 270 square degrees with an RMS sensitivity of 25–35$$\mu$$Jy beam$$^{-1}$$. We demonstrate that weakly-supervised deep learning algorithms can achieve high accuracy in predicting pixel-level information, including masks for the extended radio emission encapsulating all galaxy components and the positions of the infrared host galaxies. We evaluate the performance of our method using mean Average Precision (mAP) across multiple classes at a standard intersection over union (IoU) threshold of 0.5. We show that the model achieves a mAP$$_{50}$$of 67.5% and 76.8% for radio masks and infrared host positions, respectively. The network architecture can be found at the following link:https://github.com/Nikhel1/Gal-CAM

Research Organization:
Univ. of Pittsburgh, PA (United States)
Sponsoring Organization:
USDOE Office of Science (SC)
DOE Contract Number:
SC0007914
OSTI ID:
2419772
Journal Information:
Publications of the Astronomical Society of Australia, Journal Name: Publications of the Astronomical Society of Australia Vol. 40; ISSN 1323-3580
Publisher:
CSIRO
Country of Publication:
United States
Language:
English

References (16)

Radio Galaxy Zoo: using semi-supervised learning to leverage large unlabelled data sets for radio galaxy classification under data set shift journal April 2022
Group Normalization book January 2018
Radio Galaxy Classification: #Tags, Not Boxes journal October 2021
Attention-gating for improved radio galaxy classification journal December 2020
A Stochastic Approximation Method journal September 1951
Feature guided training and rotational standardization for the morphological classification of radio galaxies journal April 2023
Morphological classification of compact and extended radio galaxies using convolutional neural networks and data augmentation techniques journal May 2021
Cataloguing the radio-sky with unsupervised machine learning: a new approach for the SKA era journal July 2020
Radio Galaxy Zoo: machine learning for radio source host galaxy cross-identification journal May 2018
The Morphology of Extragalactic Radio Sources of High and Low Luminosity journal April 1974
Radio Galaxy Zoo: compact and extended radio source classification with deep learning journal January 2018
Unveiling the rarest morphologies of the LOFAR Two-metre Sky Survey radio source population with self-organised maps journal January 2021
Australian SKA Pathfinder: A High-Dynamic Range Wide-Field of View Survey Telescope journal August 2009
Evolutionary Map of the Universe: Tracing Clusters to High Red-shift journal December 2011
CNN architecture comparison for radio galaxy classification journal February 2021
The Expanded very Large Array: a new Telescope for new Science journal August 2011

Similar Records

Discovery of the most luminous quasar of the last 9 Gyr
Journal Article · 2021 · Publications of the Astronomical Society of Australia · OSTI ID:1981807

Large gyro-orbit model of ion velocity distribution in plasma near a wall in a grazing-angle magnetic field
Journal Article · 2021 · Journal of Plasma Physics · OSTI ID:1850057

Towards fast and accurate predictions of radio frequency power deposition and current profile via data-driven modelling: applications to lower hybrid current drive
Journal Article · 2022 · Journal of Plasma Physics · OSTI ID:1882254

Related Subjects