Using machine learning method for variable star classification using the TESS Sectors 1-57 data

ABSTRACT The Transiting Exoplanet Survey Satellite (TESS) is a wide-field all-sky survey mission designed to detect Earth-sized exoplanets. After over four years photometric surveys, data from sectors 1-57, including approximately 1,050,000 light curves with a 2-minute cadence, were collected. By cross-matching the data with Gaia's variable star catalogue, we obtained labeled datasets for further analysis. Using a random forest classifier, we performed classification of variable stars and designed distinct classification processes for each subclass, 6770 EA, 2971 EW, 980 CEP, 8347 DSCT, 457 RRab, 404 RRc and 12348 ROT were identified. Each variable star was visually inspected to ensure the reliability and accuracy of the compiled catalog. Subsequently, we ultimately obtained 6046 EA, 3859 EW, 2058 CEP, 8434 DSCT, 482 RRab, 416 RRc, and 9694 ROT, and a total of 14092 new variable stars were discovered. INTRODUCTION Variable stars refer to a type of celestial body that exhibits periodic changes in luminosity due to reasons such as occultation, pulsation, or rotation. Variable stars, characterized by their distinctive variability in luminosity, offer astronomers a valuable tool for understanding the internal structures of stars, their evolutionary processes, and fundamental stellar physics theories. Therefore, researchers aim to identify as many variables as possible to assist the study of stellar evolution, exploring galactic structure, and so on. As early as hundreds of years ago, people began to explore variables. In recent decades, advancements in CCD technology and large-scale sky surveys have led to a significant increase in the discovery of variable stars.