MiraBest: A Dataset of Morphologically Classified Radio Galaxies for Machine Learning

TL;DR

The paper introduces MiraBest, a standardized, labeled dataset of 1256 radio galaxies designed for machine learning, with an extended version of 2100 sources, to facilitate performance assessment of algorithms in radio galaxy classification.

Contribution

It provides a detailed description of the MiraBest dataset, including its construction, structure, and comparison to other datasets, supporting machine learning research in radio galaxy classification.

Findings

MiraBest dataset contains 1256 radio-loud AGN with Fanaroff-Riley classifications.

An extended dataset of 2100 sources was created by cross-matching with other catalogs.

The dataset is compatible with standard deep learning libraries for research use.

Abstract

The volume of data from current and future observatories has motivated the increased development and application of automated machine learning methodologies for astronomy. However, less attention has been given to the production of standardised datasets for assessing the performance of different machine learning algorithms within astronomy and astrophysics. Here we describe in detail the MiraBest dataset, a publicly available batched dataset of 1256 radio-loud AGN from NVSS and FIRST, filtered to $0.03 < z < 0.1$, manually labelled by Miraghaei and Best (2017) according to the Fanaroff-Riley morphological classification, created for machine learning applications and compatible for use with standard deep learning libraries. We outline the principles underlying the construction of the dataset, the sample selection and pre-processing methodology, dataset structure and composition, as well as a comparison of MiraBest to other datasets used in the literature. Existing applications that utilise the MiraBest dataset are reviewed, and an extended dataset of 2100 sources is created by cross-matching MiraBest with other catalogues of radio-loud AGN that have been used more widely in the literature for machine learning applications.