Morphological classification of compact and extended radio galaxies using convolutional neural networks and data augmentation techniques

@article{MaslejKrekov2021MorphologicalCO,
  title={Morphological classification of compact and extended radio galaxies using convolutional neural networks and data augmentation techniques},
  author={Viera Maslej-Kre{\vs}ň{\'a}kov{\'a} and Khadija El Bouchefry and Peter Butka},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.00385}
}
Machine-learning techniques have been increasingly used in astronomical applications and have proven to successfully classify objects in image data with high accuracy. The current work uses archival data from the Faint Images of the Radio Sky at Twenty Centimeters (FIRST) to classify radio galaxies into four classes: Fanaroff–Riley Class I (FRI), Fanaroff–Riley Class II (FRII), Bent-Tailed (BENT), and Compact (COMPT). The model presented in this work is based on Convolutional Neural Networks… 
2 Citations

Automatic Detection and Classification of Radio Galaxy Images by Deep Learning

Surveys conducted by radio astronomy observatories, such as SKA, MeerKAT, Very Large Array, and ASKAP, have generated massive astronomical images containing radio galaxies (RGs). This generation of

Lightweight HI source finding for next generation radio surveys

References

SHOWING 1-10 OF 50 REFERENCES

Classifying Radio Galaxies with the Convolutional Neural Network

We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have

Radio Galaxy Zoo: compact and extended radio source classification with deep learning

TLDR
This work designs a convolutional neural network to differentiate between different morphology classes using sources from the Radio Galaxy Zoo (RGZ) citizen science project, and explores the factors that affect the performance of such neural networks, such as the amount of training data, number and nature of layers, and the hyperparameters.

A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected from the Best–Heckman Sample

TLDR
A four-layer dichotomous tree is designed to classify the radio AGNs, which leads to a significantly better performance than the direct six-type classification and could confirm with a sufficiently large sample that there could not exist an abrupt separation between FRIs and FRIIs as reported in some previous works.

Transfer learning for radio galaxy classification

TLDR
This work presents radio galaxy classification based on a 13-layer Deep Convolutional Neural Network (DCNN) using transfer learning methods between different radio surveys, and finds that machine learning models trained from a random initialization achieve accuracies comparable to those found elsewhere in the literature.

Star-galaxy Classification Using Deep Convolutional Neural Networks

TLDR
This work presents a star-galaxy classification framework that uses deep convolutional neural networks (ConvNets) directly on the reduced, calibrated pixel values, and demonstrates that ConvNets are able to produce accurate and well-calibrated probabilistic classifications that are competitive with conventional machine learning techniques.

Radio Galaxy Zoo:Claran– a deep learning classifier for radio morphologies

TLDR
CLARAN is a proof-of-concept radio source morphology classifier based upon the Faster Region-based Convolutional Neutral Networks method, capable of locating and associating discrete and extended components of radio sources in a fast and accurate fashion.

Using transfer learning to detect galaxy mergers

TLDR
This work investigates the use of deep convolutional neural networks (deep CNNs) for automatic visual detection of galaxy mergers, and finds that transfer learning can act as a regulariser in some cases, leading to better overall classification accuracy.

Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit

TLDR
The ability to better recover detailed features from low-signal-to-noise and low angular resolution imaging data significantly increases the ability to study existing data sets of astrophysical objects as well as future observations with observatories such as the Large Synoptic Sky Telescope and the Hubble and James Webb space telescopes.

LensFlow: A Convolutional Neural Network in Search of Strong Gravitational Lenses

TLDR
The developed machine learning algorithm is more computationally efficient and complimentary to classical lens identification algorithms and is ideal for discovering such events across wide areas from current and future surveys such as LSST and WFIRST.

Fast automated analysis of strong gravitational lenses with convolutional neural networks

TLDR
The use of deep convolutional neural networks are reported to be used to estimate lensing parameters in an extremely fast and automated way, circumventing the difficulties that are faced by maximum likelihood methods.