Applications of Machine-Learning Algorithms for Infrared Colour Selection of Galactic Wolf-Rayet Stars

TL;DR

This paper explores machine-learning algorithms, specifically variants of k-Nearest Neighbours, to automatically identify Galactic Wolf-Rayet stars using infrared colour data, achieving successful candidate selection and confirming four new WR stars.

Contribution

It introduces an automated infrared colour selection tool for Wolf-Rayet stars and evaluates its efficiency, laying groundwork for estimating total WR star populations in the Galaxy.

Findings

Successfully identified and confirmed 4 new Wolf-Rayet stars.

Demonstrated the effectiveness of k-NN algorithms in classifying infrared stellar objects.

Provided a framework for estimating the total number of WR stars in the Galaxy.

Abstract

We have investigated and applied machine-learning algorithms for Infrared Colour Selection of Galactic Wolf-Rayet (WR) candidates. Objects taken from the GLIMPSE catalogue of the infrared objects in the Galactic plane can be classified into different stellar populations based on the colours inferred from their broadband photometric magnitudes ($J$, $H$ and $K_s$ from 2MASS, and the four \textit{Spitzer}/IRAC bands). The algorithms tested in this pilot study are variants of the $k$-Nearest Neighbours ($k$-NN) approach, which is ideal for exploratory studies of classification problems where interrelations between variables and classes are complicated. The aims of this study are (1) to provide an automated tool to select reliable WR candidates and potentially other classes of objects, (2) to measure the efficiency of infrared colour selection at performing these tasks and, (3) to lay the groundwork for statistically inferring the total number of WR stars in our Galaxy. We report the performance results obtained over a set of known objects and selected candidates for which we have carried out follow-up spectroscopic observations, and confirm the discovery of 4 new WR stars.