Detached eclipsing binary stars (dEBs) are a key source of data on fundamental stellar parameters. While there is a vast source of candidate systems in the light curve databases of survey missions such as Kepler and TESS, published catalogues of well-characterised systems fall short of reflecting this abundance. We seek to improve the efficiency of efforts to process these data with the development of a machine learning model to inspect dEB light curves and predict the input parameters for subsequent formal analysis by the jktebop code.
@article{arxiv.2502.11758,
title = {EBOP MAVEN: A machine learning model for predicting eclipsing binary light curve fitting parameters},
author = {Stephen Overall and John Southworth},
journal= {arXiv preprint arXiv:2502.11758},
year = {2025}
}
Comments
4 pages, 1 figure. Contribution to the conference "Binary and multiple stars in the era of big surveys," Litomysl, CZ, September 2024. Accepted for publication in Contributions of the Astronomical Observatory Skalnate Pleso