Classification of Eclipsing Binary Light Curves with Deep Learning Neural Network Algorithms

Home Page
About
Submit A Journal
Submit A Conference
Submit Paper/Book
- Submit a Preprint
- Submit a Book
Contact

Turkish Journal of Astronomy and Astrophysics
Cilt: 6 Sayı: 1
Classification of Eclipsing Binary Light Curves with Deep Learning Neural Network Algorithms

Classification of Eclipsing Binary Light Curves with Deep Learning Neural Network Algorithms

Pages : 18-27

View : 60 | Download : 33

Publication Date : 2025-06-30

Article Type : Research Paper

Abstract :We present an image classification algorithm utilising a deep learning convolutional neural network architecture, which categorises the morphologies of eclipsing binary systems based on their light curves. The algorithm trains the machine with light curve images generated from the observational data of eclipsing binary stars in contact, detached and semi-detached morphologies, whose light curves are provided by Kepler, ASAS and CALEB catalogues. The structure of the architecture is explained, the parameters of the network layers and the resulting metrics are discussed. Our results show that the algorithm, which is selected among 132 neural network architectures, estimates the morphological classes of an independent validation dataset, 705 true data, with an accuracy of 92%.
Keywords : (stars:) binaries: eclipsing, methods: data analysis, techniques: image processing

ORIGINAL ARTICLE URL

* There may have been changes in the journal, article,conference, book, preprint etc. informations. Therefore, it would be appropriate to follow the information on the official page of the source. The information here is shared for informational purposes. IAD is not responsible for incorrect or missing information.