Cataloging the radio-sky with unsupervised machine learning: a new approach for the SKA era

Abstract

We develop a new analysis approach towards identifying related radio components and their corresponding infrared host galaxy based on unsupervised machine learning methods. By exploiting PINK, a self-organising map algorithm, we are able to associate radio and infrared sources without the a priori requirement of training labels. We present an example of this method using $894,415$ images from the FIRST and WISE surveys centred towards positions described by the FIRST catalogue. We produce a set of catalogues that complement FIRST and describe 802,646 objects, including their radio components and their corresponding AllWISE infrared host galaxy. Using these data products we (i) demonstrate the ability to identify objects with rare and unique radio morphologies (e.g. 'X'-shaped galaxies, hybrid FR-I/FR-II morphologies), (ii) can identify the potentially resolved radio components that are associated with a single infrared host and (iii) introduce a "curliness" statistic to search for bent and disturbed radio morphologies, and (iv) extract a set of 17 giant radio galaxies between 700-1100 kpc. As we require no training labels, our method can be applied to any radio-continuum survey, provided a sufficiently representative SOM can be trained.

References in corpus (16)

• The NumPy array: a structure for efficient numerical computation
• scikit-image: Image processing in Python
• The Sloan Digital Sky Survey Quasar Catalog: twelfth data release
• Science with ASKAP - the Australian Square Kilometre Array Pathfinder
• The Last of FIRST: The Final Catalog and Source Identifications
• FIRST `Winged' and `X'-shaped Radio Source Candidates
• A multifrequency study of giant radio sources-II. Spectral ageing analysis of the lobes of selected sources
• On the relationship between a giant radio galaxy MSH 05-22 and the ambient large-scale galaxy structure
• Extragalactic Radio Continuum Surveys and the Transformation of Radio Astronomy
• Giant radio galaxies - II. Tracers of large-scale structure
• Discovering the Unexpected in Astronomical Survey Data
• Radio Galaxy Zoo: A Search for Hybrid Morphology Radio Galaxies
• MRC B0319-454: Probing the large-scale structure with a giant radio galaxy
• The Large Area Radio Galaxy Evolution Spectroscopic Survey (LARGESS): Survey design, data catalogue and GAMA/WiggleZ spectroscopy
• What Are "X-Shaped" Radio Sources Telling Us? II. Properties of a Sample of 87
• Uncovering High-z Clusters Using Wide-Angle Tailed Radio Sources

Cited by in corpus (18)

• The discovery of a radio galaxy of at least 5 Mpc
• Unveiling the rarest morphologies of the LOFAR Two-metre Sky Survey radio source population with self-organised maps
• A review of unsupervised learning in astronomy
• Discovery of Peculiar Radio Morphologies with ASKAP using Unsupervised Machine Learning
• Searching for pulsars associated with polarised point sources using LOFAR: Initial discoveries from the TULIPP project
• A machine learning classifier for LOFAR radio galaxy cross-matching techniques
• Radio source-component association for the LOFAR Two-metre Sky Survey with region-based convolutional neural networks
• A study on the Clustering Properties of Radio-Selected sources in the Lockman Hole Region at 325 MHz
• Optimal Probabilistic Catalogue Matching for Radio Sources
• Rotation and flipping invariant self-organizing maps with astronomical images: A cookbook and application to the VLA Sky Survey QuickLook images
• Feedback from low-to-moderate luminosity radio-AGN with MaNGA
• YOUNG Star detrending for Transiting Exoplanet Recovery (YOUNGSTER) II: Using Self-Organising Maps to explore young star variability in Sectors 1-13 of TESS data
• A catalogue of complex radio sources in the Rapid ASKAP Continuum Survey created using a Self-Organising Map
• EMU and the DRAGNs I: A Catalogue of DRAGNs
• Automatic morphological classification of galaxies: convolutional autoencoder and bagging-based multiclustering model
• Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift
• Quantifying Radio Source Morphology
• Radio Galaxy Zoo: Morphological classification by Fanaroff-Riley designation using self-supervised pre-training