Unveiling the rarest morphologies of the LOFAR Two-metre Sky Survey radio source population with self-organised maps

Abstract

The Low Frequency Array (LOFAR) Two-metre Sky Survey (LoTSS) is a low-frequency radio continuum survey of the Northern sky at an unparalleled resolution and sensitivity. In order to fully exploit this huge dataset and those produced by the Square Kilometre Array in the next decade, automated methods in machine learning and data-mining will be increasingly essential both for morphological classifications and for identifying optical counterparts to the radio sources. Using self-organising maps (SOMs), a form of unsupervised machine learning, we created a dimensionality reduction of the radio morphologies for the $\sim$25k extended radio continuum sources in the LoTSS first data release, which is only $\sim$2 percent of the final LoTSS survey. We made use of \textsc{PINK}, a code which extends the SOM algorithm with rotation and flipping invariance, increasing its suitability and effectiveness for training on astronomical sources. After training, the SOMs can be used for a wide range of science exploitation and we present an illustration of their potential by finding an arbitrary number of morphologically rare sources in our training data (424 square degrees) and subsequently in an area of the sky ($\sim$5300 square degrees) outside the training data. Objects found in this way span a wide range of morphological and physical categories: extended jets of radio active galactic nuclei, diffuse cluster haloes and relics, and nearby spiral galaxies. Finally, to enable accessible, interactive, and intuitive data exploration, we showcase the LOFAR-PyBDSF Visualisation Tool, which allows users to explore the LoTSS dataset through the trained SOMs.

26 pages; accepted for publication in A&A

References in corpus (13)

• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• The LOFAR Two-metre Sky Survey - I. Survey Description and Preliminary Data Release
• The Sloan Digital Sky Survey Quasar Catalog: twelfth data release
• The SDSS-IV MaNGA Sample: Design, Optimization, and Usage Considerations
• Revisiting the Fanaroff-Riley dichotomy and radio-galaxy morphology with the LOFAR Two-Metre Sky Survey (LoTSS)
• Classifying Radio Galaxies with Convolutional Neural Network
• An Optical Catalog of Galaxy Clusters Obtained from an Adaptive Matched Filter Finder Applied to SDSS DR6
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks
• NGC 326: X-shaped no more
• A Spectro-photometric Search for Galaxy Clusters in SDSS
• Cataloging the radio-sky with unsupervised machine learning: a new approach for the SKA era
• Revived Fossil Plasma Sources in Galaxy Clusters

Cited by in corpus (27)

• The LOFAR Two-metre Sky Survey -- V. Second data release
• The Planck clusters in the LOFAR sky. I. LoTSS-DR2: new detections and sample overview
• Measuring the giant radio galaxy length distribution with the LoTSS
• A review of unsupervised learning in astronomy
• A unique, ring-like radio source with quadrilateral structure detected with machine learning
• Insights on the origin of ORCs from cosmological simulations
• Searching for pulsars associated with polarised point sources using LOFAR: Initial discoveries from the TULIPP project
• Discovery of Peculiar Radio Morphologies with ASKAP using Unsupervised Machine Learning
• A machine learning classifier for LOFAR radio galaxy cross-matching techniques
• A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection
• Radio source-component association for the LOFAR Two-metre Sky Survey with region-based convolutional neural networks
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• Identifying anomalous radio sources in the EMU Pilot Survey using a complexity-based approach
• Yet another Odd Radio Circle?
• Finding AGN remnant candidates based on radio morphology with machine learning
• Rotation and flipping invariant self-organizing maps with astronomical images: A cookbook and application to the VLA Sky Survey QuickLook images
• Self-supervised contrastive learning of radio data for source detection, classification and peculiar object discovery
• Revealing new high redshift quasar populations through Gaussian mixture model selection
• Discovery of Odd Radio Circles and Other Peculiars in the First Year of the EMU Survey using Object Detection
• A catalogue of complex radio sources in the Rapid ASKAP Continuum Survey created using a Self-Organising Map
• 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
• EMU and the DRAGNs I: A Catalogue of DRAGNs
• Classification of Radio Sources Through Self-Supervised Learning
• Radio emission from a massive node of the cosmic web. A discovery powered by machine learning
• Convolutional Deep Denoising Autoencoders for Radio Astronomical Images
• Resurging from the ashes: A spectral study of seven candidate revived radio fossils in nearby low-mass galaxy clusters
• Galaxy clusters in the LoTSS-DR3: Catalogues and detection pipeline for diffuse radio emission