PREDNASAJUCI / LECTURER :

Andrii Maliuk

(1) Astronomical Institute, Slovak Academy of Sciences,
059 60 Tatranská Lomnica

NAZOV / TITLE :

Estimation of contact binaries parameters with machine learning

ABSTRAKT / ABSTRACT :

In this study, we used various machine learning methods to predict
the parameters of binary stars using a training dataset containing
11,894 objects. The input data consists of 11 coefficients from the
synthetic light curves decomposition into sines, while the target
variables include the mass ratio q, the fill out factor f, the
inclination angle i (converted to sin⁡(i)), and the third light
contribution l_3.
Our results validate the choice of XGBoost method as an effective
tool for predicting the parameters of binary star systems.