Reddening-free Q indices to identify Be star candidates

TL;DR

This paper introduces reddening-free Q indices combined with neural networks to improve the automatic identification of Be star candidates from photometric data, overcoming reddening effects that hinder traditional methods.

Contribution

The study proposes and evaluates reddening-free Q indices for neural network-based classification of Be stars, enhancing generalization across different astronomical datasets.

Findings

Q indices significantly improve candidate identification accuracy.

Neural networks trained with Q indices outperform those using raw magnitudes.

High recall achieved at 99% precision on multiple datasets.

Abstract

Astronomical databases currently provide high-volume spectroscopic and photometric data. While spectroscopic data is better suited to the analysis of many astronomical objects, photometric data is relatively easier to obtain due to shorter telescope usage time. Therefore, there is a growing need to use photometric information to automatically identify objects for further detailed studies, specially H{\alpha} emission line stars such as Be stars. Photometric color-color diagrams (CCDs) are commonly used to identify this kind of objects. However, their identification in CCDs is further complicated by the reddening effect caused by both the circumstellar and interstellar gas. This effect prevents the generalization of candidate identification systems. Therefore, in this work we evaluate the use of neural networks to identify Be star candidates from a set of OB-type stars. The networks are trained using a labeled subset of the VPHAS+ and 2MASS databases, with filters u, g, r, H{\alpha}, i, J, H, and K. In order to avoid the reddening effect, we propose and evaluate the use of reddening-free Q indices to enhance the generalization of the model to other databases and objects. To test the validity of the approach, we manually labeled a subset of the database, and use it to evaluate candidate identification models. We also labeled an independent dataset for cross dataset evaluation. We evaluate the recall of the models at a 99% precision level on both test sets. Our results show that the proposed features provide a significant improvement over the original filter magnitudes.