Identifying symbiotic stars with machine learning

TL;DR

This paper employs machine learning algorithms to identify new symbiotic star candidates from large astronomical surveys, successfully confirming two new symbiotic stars and expanding the candidate list significantly.

Contribution

The study introduces a machine learning approach using XGBoost, LightGBM, and Decision Tree algorithms to efficiently identify symbiotic star candidates from survey data, addressing the population discrepancy.

Findings

Identified 11,709 potential symbiotic stars candidates.

Confirmed two candidates as symbiotic stars.

Classified 11 candidates as accreting-only symbiotic stars.

Abstract

Symbiotic stars are interacting binary systems, making them valuable for studying various astronomical phenomena, such as stellar evolution, mass transfer, and accretion processes. Despite recent progress in the discovery of symbiotic stars, a significant discrepancy between the observed population of symbiotic stars and the number predicted by theoretical models. To bridge this gap, this study utilized machine learning techniques to efficiently identify new symbiotic stars candidates. Three algorithms (XGBoost, LightGBM, and Decision Tree) were applied to a dataset of 198 confirmed symbiotic stars and the resulting model was then used to analyze data from the LAMOST survey, leading to the identification of 11,709 potential symbiotic stars candidates. Out of the these potential symbiotic stars candidates listed in the catalog, 15 have spectra available in the SDSS survey. Among these 15 candidates, two candidates, namely V* V603 Ori and V* GN Tau, have been confirmed as symbiotic stars. The remaining 11 candidates have been classified as accreting-only symbiotic star candidates. The other two candidates, one of which has been identified as a galaxy by both SDSS and LAMOST surveys, and the other identified as a quasar by SDSS survey and as a galaxy by LAMOST survey.