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

TL;DR

This paper develops and tests a convolutional neural network to classify radio sources into compact and extended morphologies, achieving over 94% accuracy, aiding astronomical image analysis.

Contribution

It introduces a CNN architecture optimized for radio source morphology classification and evaluates factors affecting its performance, including data size and hyperparameters.

Findings

Achieved 97.4% accuracy in binary classification of radio source morphology.

Extended to four classes with 93.5% accuracy, final test accuracy of 94.8%.

Sigma clipping offers limited benefit except with small training datasets.

Abstract

Machine learning techniques have been increasingly useful in astronomical applications over the last few years, for example in the morphological classification of galaxies. Convolutional neural networks have proven to be highly effective in classifying objects in image data. The current work aims to establish when multiple components are present, in the astronomical context of synthesis imaging observations of radio sources. To this effect, we design a convolutional neural network to differentiate between different morphology classes using sources from the Radio Galaxy Zoo (RGZ) citizen science project. In this first step, we focus on exploring 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. We begin with a simple experiment in which we only differentiate between two extreme morphologies, using compact and multiple component extended sources. We found that a three convolutional layer architecture yielded very good results, achieving a classification accuracy of 97.4% on a test data set. The same architecture was then tested on a four-class problem where we let the network classify sources into compact and three classes of extended sources, achieving a test achieving a test accuracy of 93.5%. The best-performing convolutional neural network setup has been verified against RGZ Data Release 1 where a final test accuracy of 94.8% was obtained, using both original and augmented images. The use of sigma clipping does not offer a significant benefit overall, except in cases with a small number of training images.