Radio Galaxy Classification with wGAN-Supported Augmentation

TL;DR

This paper introduces a method using Wasserstein GANs to generate synthetic radio galaxy images, augmenting training data and significantly improving the accuracy of a simple neural network classifier.

Contribution

The novel application of wGANs for generating artificial radio galaxy images to enhance classification performance.

Findings

Augmented training data improves classifier accuracy

wGAN-generated images effectively supplement real data

Simple neural network benefits from data augmentation

Abstract

Novel techniques are indispensable to process the flood of data from the new generation of radio telescopes. In particular, the classification of astronomical sources in images is challenging. Morphological classification of radio galaxies could be automated with deep learning models that require large sets of labelled training data. Here, we demonstrate the use of generative models, specifically Wasserstein GANs (wGAN), to generate artificial data for different classes of radio galaxies. Subsequently, we augment the training data with images from our wGAN. We find that a simple fully-connected neural network for classification can be improved significantly by including generated images into the training set.