CAOSP abstracts, Volume: 55, No.: 3, year: 2025

Author(s): Parimucha, Š.; Markus, Y.; Gajdoš, P.; Kudak, V.
Journal: Contributions of the Astronomical Observatory Skalnaté Pleso, vol. 55, no. 3, p. 374-376.
Date: 04/2025
Title: Classification of light curves of eclipsing binaries using deep-learning models
Keyword(s): stars: binaries: eclipsing, deep-learning
Pages: 374 -- 376
DOI: https://doi.org/10.31577/caosp.2025.55.3.374
NASA ADS Abstract Service: 2025CoSka..55c.374P
Citation:
License: This work is licensed under a Creative Commons Attribution 4.0 International License

Abstract: This paper introduces a hierarchical deep-learning classification model for eclipsing binaries, where the period is also considered. Our classifier provides a tool for categorizing their light curves into four groups: overcontact with/without spots and detached with/without spots. We applied our model to light curves of OGLE eclipsing binaries and showed that it is reliably classified, although the precision of classification depends on the light curve quality.