Finding AGN remnant candidates based on radio morphology with machine learning

Abstract

Remnant radio galaxies represent the dying phase of radio-loud active galactic nuclei (AGN). Large samples of remnant radio galaxies are important for quantifying the radio galaxy life cycle. The remnants of radio-loud AGN can be identified in radio sky surveys based on their spectral index, or, complementary, through visual inspection based on their radio morphology. However, this is extremely time-consuming when applied to the new large and sensitive radio surveys. Here we aim to reduce the amount of visual inspection required to find AGN remnants based on their morphology, through supervised machine learning trained on an existing sample of remnant candidates. For a dataset of 4107 radio sources, with angular sizes larger than 60 arcsec, from the LOw Frequency ARray (LOFAR) Two-Metre Sky Survey second data release (LoTSS-DR2), we started with 151 radio sources that were visually classified as 'AGN remnant candidate'. We derived a wide range of morphological features for all radio sources from their corresponding Stokes-I images: from simple source catalogue-derived properties, to clustered Haralick-features, and self-organising map (SOM) derived morphological features. We trained a random forest classifier to separate the 'AGN remnant candidates' from the not yet inspected sources. The SOM-derived features and the total to peak flux ratio of a source are shown to be most salient to the classifier. We estimate that $31\pm 5\%$ of sources with positive predictions from our classifier will be labelled 'AGN remnant candidates' upon visual inspection, while we estimate the upper bound of the $95\%$ confidence interval for 'AGN remnant candidates' in the negative predictions at $8\%$. Visual inspection of just the positive predictions reduces the number of radio sources requiring visual inspection by $73\%$.

arXiv comment23 pages; accepted for publication in A&A

References in corpus (45)

• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• LOFAR: The LOw-Frequency ARray
• 2MASS Extended Source Catalog: Overview and Algorithms
• The LOFAR Two-metre Sky Survey - I. Survey Description and Preliminary Data Release
• The LOFAR Two-metre Sky Survey - II. First data release
• The LOFAR Two-metre Sky Survey -- V. Second data release
• The Evolution of Galaxy Structure over Cosmic Time
• EMU: Evolutionary Map of the Universe
• Science with ASKAP - the Australian Square Kilometre Array Pathfinder
• Radio galaxies with a `double-double' morphology: I - Analysis of the radio properties and evidence for interrupted activity in active galactic nuclei
• Revisiting the Fanaroff-Riley dichotomy and radio-galaxy morphology with the LOFAR Two-Metre Sky Survey (LoTSS)
• ProFound: Source Extraction and Application to Modern Survey Data
• LOFAR/H-ATLAS: The low-frequency radio luminosity - star-formation rate relation
• The LOFAR Two-metre Sky Survey (LoTSS) III. First Data Release: optical/IR identifications and value-added catalogue
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Mahotas: Open source software for scriptable computer vision
• Classifying Radio Galaxies with Convolutional Neural Network
• In search of dying radio sources in the local universe
• The LOFAR Two-metre Sky Survey Deep fields: The star formation rate - radio luminosity relation at low frequencies
• The Lockman Hole project: LOFAR observations and spectral index properties of low-frequency radio sources
• Search and modelling of remnant radio galaxies in the LOFAR Lockman Hole field
• Search and analysis of giant radio galaxies with associated nuclei (SAGAN) -- I : New sample and multi-wavelength studies
• Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
• Remnant radio-loud AGN in the Herschel-ATLAS field
• ATLBS Extended Source Sample: The evolution in radio source morphology with flux density
• The life cycle of radio galaxies in the LOFAR Lockman Hole field
• A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected From The Best-Heckman Sample
• Cataloging the radio-sky with unsupervised machine learning: a new approach for the SKA era
• On the population of remnant FRII radio galaxies and implications for radio source dynamics
• Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images
• The FIRST Classifier: Compact and Extended Radio Galaxy Classification using Deep Convolutional Neural Networks
• Duty cycle of the radio galaxy B2 0258+35
• Unveiling the rarest morphologies of the LOFAR Two-metre Sky Survey radio source population with self-organised maps
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Attention-gating for improved radio galaxy classification
• The LOFAR LBA Sky Survey II. First data release
• Radio Source Extraction with ProFound
• A Selection of Giant Radio Sources from NVSS
• Remnant Radio Galaxies Discovered in a Multi-frequency Survey
• The best of both worlds: Combining LOFAR and Apertif to derive resolved radio spectral index images
• Radio Galaxy Zoo: Knowledge Transfer Using Rotationally Invariant Self-Organising Maps
• Rapid sorting of radio galaxy morphology using Haralick features
• A machine learning classifier for LOFAR radio galaxy cross-matching techniques
• Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy Classification
• Radio source-component association for the LOFAR Two-metre Sky Survey with region-based convolutional neural networks

Cited by in corpus (4)

• Constraining the giant radio galaxy population with machine learning and Bayesian inference
• Complex morphology and precession indicators of AGN jets in LoTSS DR2
• Galaxy clusters in the LoTSS-DR3: Catalogues and detection pipeline for diffuse radio emission
• J-HERTz: J-PLUS Heritage Exploration of Radio Targets at z $<$ 5