scholarly journals Radio Galaxy Classification: #Tags, Not Boxes

Galaxies ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 85
Author(s):  
Lawrence Rudnick
Keyword(s):  
Radio Galaxy ◽  
Radio Galaxies ◽  
Physical Understanding ◽  
Galaxy Classification

After six decades of studying radio galaxies, we are now delightfully overwhelmed by their exponentially expanding numbers and the complexity of their structures. Similarly, the methods we use to classify radio galaxies have exploded, often resulting in conflicting terminology, ambiguous classifications, and historical schemes that may or may not match our current physical understanding. After discussions with more than 100 radio astronomers over the last several years and listening to their ideas and aspirations, I propose that we reconceptualize the classification of radio galaxies. Instead of trying to place them into “boxes”, we should assign them #tags, a system that is easy to understand and apply, that is flexible and evolving, and that can accommodate conflicting ideas with respect to what is relevant and important. Here, I outline the basis of such a #tag system; the rest is up to the community.

scholarly journals Attention-gating for improved radio galaxy classification

2020 ◽  
Author(s):  
Micah Bowles ◽  
Anna M M Scaife ◽  
Fiona Porter ◽  
Hongming Tang ◽  
David J Bastien
Keyword(s):  
Neural Networks ◽  
Radio Galaxy ◽  
State Of The Art ◽  
Radio Galaxies ◽  
Radio Sources ◽  
Effective Manner ◽  
Salient Regions ◽  
Galaxy Classification ◽  
Selection Of

Abstract In this work we introduce attention as a state of the art mechanism for classification of radio galaxies using convolutional neural networks. We present an attention-based model that performs on par with previous classifiers while using more than 50% fewer parameters than the next smallest classic CNN application in this field. We demonstrate quantitatively how the selection of normalisation and aggregation methods used in attention-gating can affect the output of individual models, and show that the resulting attention maps can be used to interpret the classification choices made by the model. We observe that the salient regions identified by the our model align well with the regions an expert human classifier would attend to make equivalent classifications. We show that while the selection of normalisation and aggregation may only minimally affect the performance of individual models, it can significantly affect the interpretability of the respective attention maps and by selecting a model which aligns well with how astronomers classify radio sources by eye, a user can employ the model in a more effective manner.

scholarly journals Fanaroff–Riley classification of radio galaxies using group-equivariant convolutional neural networks

2021 ◽  
Vol 503 (2) ◽  
pp. 2369-2379
Author(s):  
Anna M M Scaife ◽  
Fiona Porter
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Radio Galaxy ◽  
Epistemic Uncertainty ◽  
Parameter Tuning ◽  
Radio Galaxies ◽  
Input Image ◽  
Feature Maps ◽  
Galaxy Classification

ABSTRACT Weight sharing in convolutional neural networks (CNNs) ensures that their feature maps will be translation-equivariant. However, although conventional convolutions are equivariant to translation, they are not equivariant to other isometries of the input image data, such as rotation and reflection. For the classification of astronomical objects such as radio galaxies, which are expected statistically to be globally orientation invariant, this lack of dihedral equivariance means that a conventional CNN must learn explicitly to classify all rotated versions of a particular type of object individually. In this work we present the first application of group-equivariant convolutional neural networks to radio galaxy classification and explore their potential for reducing intra-class variability by preserving equivariance for the Euclidean group E(2), containing translations, rotations, and reflections. For the radio galaxy classification problem considered here, we find that classification performance is modestly improved by the use of both cyclic and dihedral models without additional hyper-parameter tuning, and that a D16 equivariant model provides the best test performance. We use the Monte Carlo Dropout method as a Bayesian approximation to recover epistemic uncertainty as a function of image orientation and show that E(2)-equivariant models are able to reduce variations in model confidence as a function of rotation.

scholarly journals The morphological classification of distant radio galaxies explored with three-dimensional simulations

2019 ◽  
Vol 490 (1) ◽  
pp. 1363-1382 ◽  
Author(s):  
Michael D Smith ◽  
Justin Donohoe
Keyword(s):  
Radio Galaxy ◽  
Three Dimensional ◽  
Radio Galaxies ◽  
Morphological Classification ◽  
Helical Structures ◽  
Radio Jets ◽  
Source Type ◽  
Radio Lobe ◽  
Three Dimensional Simulations

ABSTRACT We explore the observational implications of a large systematic study of high-resolution three-dimensional simulations of radio galaxies driven by supersonic jets. For this fiducial study, we employ non-relativistic hydrodynamic adiabatic flows from nozzles into a constant pressure-matched environment. Synchrotron emissivity is approximated via the thermal pressure of injected material. We find that the morphological classification of a simulated radio galaxy depends significantly on several factors with increasing distance (i.e. decreasing observed resolution) and decreasing orientation often causing reclassification from FR II (limb-brightened) to FR I (limb-darkened) type. We introduce the Lobe or Limb Brightening Index (LBI) to measure the radio lobe type more precisely. The jet density also has an influence as expected with lower density leading to broader and bridged lobe morphologies as well as brighter radio jets. Hence, relating observed source type to the intrinsic jet dynamics is not straightforward. Precession of the jet direction may also be responsible for wide relaxed sources with lower LBI and FR class as well as for X-shaped and double–double structures. Helical structures are not generated because the precession is usually too slow. We conclude that distant radio galaxies could appear systematically more limb darkened due to merger-related redirection and precession as well as due to the resolution limitation.

scholarly journals The FIRST Classifier: compact and extended radio galaxy classification using deep Convolutional Neural Networks

2018 ◽  
Author(s):  
Wathela Alhassan
Keyword(s):  
Radio Galaxies ◽  
Radio Sources ◽  
Automated Classification ◽  
Imaging Data ◽  
Deep Convolutional Neural Networks ◽  
Line System ◽  
New Radio ◽  
Extended Radio ◽  
Galaxy Classification

Upcoming surveys with new radio observatories such as the Square Kilometer Array will generate a wealth of imaging data containing large numbers of radio galaxies. Different classes of radio galaxies can be used as tracers of the cosmic environment, including the dark matter density field, to address key cosmological questions. Classifying these galaxies based on morphology is thus an important step toward achieving the science goals of next generation radio surveys. Radio galaxies have been traditionally classified as Fanaroff-Riley (FR) I and II, although some exhibit more complex 'bent' morphologies arising from environmental factors or intrinsic properties. In this work we present the FIRST Classifier, an on-line system for automated classification of Compact and Extended radio sources. We developed the FIRST Classifier based on a trained Deep Convolutional Neural Network Model to automate the morphological classification of com- pact and extended radio sources observed in the FIRST radio survey. Our model achieved an overall accuracy of 97% and a recall of 98%, 100%, 98% and 93% for Compact, BENT, FRI and FRII galaxies respectively. The current version of the FIRST classifier is able to identify the morphological class for a single source or for a list of sources as Compact or Extended (FRI, FRII and BENT).

scholarly journals CNN architecture comparison for radio galaxy classification

2021 ◽  
Vol 503 (2) ◽  
pp. 1828-1846
Author(s):  
Burger Becker ◽  
Mattia Vaccari ◽  
Matthew Prescott ◽  
Trienko Grobler
Keyword(s):  
Comparative Study ◽  
Galaxy Evolution ◽  
Radio Galaxy ◽  
Recognition Performance ◽  
Model Complexity ◽  
Great Promise ◽  
Radio Sources ◽  
Morphological Classification ◽  
Computational Performance

ABSTRACT The morphological classification of radio sources is important to gain a full understanding of galaxy evolution processes and their relation with local environmental properties. Furthermore, the complex nature of the problem, its appeal for citizen scientists, and the large data rates generated by existing and upcoming radio telescopes combine to make the morphological classification of radio sources an ideal test case for the application of machine learning techniques. One approach that has shown great promise recently is convolutional neural networks (CNNs). Literature, however, lacks two major things when it comes to CNNs and radio galaxy morphological classification. First, a proper analysis of whether overfitting occurs when training CNNs to perform radio galaxy morphological classification using a small curated training set is needed. Secondly, a good comparative study regarding the practical applicability of the CNN architectures in literature is required. Both of these shortcomings are addressed in this paper. Multiple performance metrics are used for the latter comparative study, such as inference time, model complexity, computational complexity, and mean per class accuracy. As part of this study, we also investigate the effect that receptive field, stride length, and coverage have on recognition performance. For the sake of completeness, we also investigate the recognition performance gains that we can obtain by employing classification ensembles. A ranking system based upon recognition and computational performance is proposed. MCRGNet, Radio Galaxy Zoo, and ConvXpress (novel classifier) are the architectures that best balance computational requirements with recognition performance.

scholarly journals Radio Spectra and Particle Ages of the Head-Tail Radio Galaxy NGC1265

1996 ◽  
Vol 175 ◽  
pp. 347-348
Author(s):  
L. Feretti ◽  
G. Giovannini ◽  
U. Klein ◽  
K.-H. Mack ◽  
L.G. Sijbring
Keyword(s):  
Magnetic Field ◽  
Radio Galaxy ◽  
Low Frequency ◽  
Radio Galaxies ◽  
Field Structure ◽  
Magnetic Field Structure ◽  
Linearly Polarized ◽  
Faraday Effects ◽  
Perseus Cluster ◽  
Comprehensive Study

We have performed sensitive observations of three classical head-tail radio galaxies at λ11.1, 6.3, and 2.8 cm using the Effelsberg 100-m telescope (Zech, 1994). Complete maps of the sources 3C129, NGC1265, and 3C465 were obtained, including the distributions of the linearly polarized intensity. Together with the low-frequency interferometric maps these allow a comprehensive study of their radio spectra and, based on models of particle losses, the derivations of particle ages across these sources. The highest frequency involved allows an unambiguous derivation of the projected magnetic field structure, unimpeded by Faraday effects. Here we focus on NGC1265, which is located in the Perseus Cluster.

scholarly journals NGC 3894: a young radio galaxy seen by Fermi-LAT

2020 ◽  
Vol 635 ◽  
pp. A185 ◽  
Author(s):  
G. Principe ◽  
G. Migliori ◽  
T. J. Johnson ◽  
F. D’Ammando ◽  
M. Giroletti ◽  
...  
Keyword(s):  
Radio Galaxy ◽  
Radio Galaxies ◽  
High Energy ◽  
Apparent Velocity ◽  
Large Area ◽  
Long Baseline ◽  
Full Period ◽  
Very Long Baseline Array ◽  
High Energy Emission ◽  
First Time

Context. According to radiative models, radio galaxies may produce γ-ray emission from the first stages of their evolution. However, very few such galaxies have been detected by the Fermi Large Area Telescope (LAT) so far. Aims. NGC 3894 is a nearby (z = 0.0108) object that belongs to the class of compact symmetric objects (CSOs, i.e., the most compact and youngest radio galaxies), which is associated with a γ-ray counterpart in the Fourth Fermi-LAT source catalog. Here we present a study of the source in the γ-ray and radio bands aimed at investigating its high-energy emission and assess its young nature. Methods. We analyzed 10.8 years of Fermi-LAT data between 100 MeV and 300 GeV and determined the spectral and variability characteristics of the source. Multi-epoch very long baseline array (VLBA) observations between 5 and 15 GHz over a period of 35years were used to study the radio morphology of NGC 3894 and its evolution. Results. NGC 3894 is detected in γ-rays with a significance >9σ over the full period, and no significant variability has been observed in the γ-ray flux on a yearly time-scale. The spectrum is modeled with a flat power law (Γ = 2.0 ± 0.1) and a flux on the order of 2.2 × 10−9 ph cm−2 s−1. For the first time, the VLBA data allow us to constrain with high precision the apparent velocity of the jet and counter-jet side to be βapp, NW = 0.132 ± 0.004 and βapp, SE = 0.065 ± 0.003, respectively. Conclusions. Fermi-LAT and VLBA results favor the youth scenario for the inner structure of this object, with an estimated dynamical age of 59 ± 5 years. The estimated range of viewing angle (10° < θ <  21°) does not exclude a possible jet-like origin of the γ-ray emission.

scholarly journals Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging

2020 ◽  
Vol 493 (3) ◽  
pp. 4209-4228 ◽  
Author(s):  
Ting-Yun Cheng ◽  
Christopher J Conselice ◽  
Alfonso Aragón-Salamanca ◽  
Nan Li ◽  
Asa F L Bluck ◽  
...  
Keyword(s):  
Machine Learning ◽  
Imaging Data ◽  
Morphological Classification ◽  
Learning Methods ◽  
Visual Classification ◽  
Machine Learning Methods ◽  
Dark Energy Survey ◽  
Galaxy Classification ◽  
Energy Survey

ABSTRACT There are several supervised machine learning methods used for the application of automated morphological classification of galaxies; however, there has not yet been a clear comparison of these different methods using imaging data, or an investigation for maximizing their effectiveness. We carry out a comparison between several common machine learning methods for galaxy classification [Convolutional Neural Network (CNN), K-nearest neighbour, logistic regression, Support Vector Machine, Random Forest, and Neural Networks] by using Dark Energy Survey (DES) data combined with visual classifications from the Galaxy Zoo 1 project (GZ1). Our goal is to determine the optimal machine learning methods when using imaging data for galaxy classification. We show that CNN is the most successful method of these ten methods in our study. Using a sample of ∼2800 galaxies with visual classification from GZ1, we reach an accuracy of ∼0.99 for the morphological classification of ellipticals and spirals. The further investigation of the galaxies that have a different ML and visual classification but with high predicted probabilities in our CNN usually reveals the incorrect classification provided by GZ1. We further find the galaxies having a low probability of being either spirals or ellipticals are visually lenticulars (S0), demonstrating that supervised learning is able to rediscover that this class of galaxy is distinct from both ellipticals and spirals. We confirm that ∼2.5 per cent galaxies are misclassified by GZ1 in our study. After correcting these galaxies’ labels, we improve our CNN performance to an average accuracy of over 0.99 (accuracy of 0.994 is our best result).

Sign in / Sign up

Export Citation Format

Share Document