|
Description
In modern astronomy, machine learning has proved to be efficient and effective in mining big data from the newest telescopes. In this study, we construct a supervised machine-learning algorithm to classify the objects in the Javalambre Photometric Local Universe Survey first data release (J-PLUS DR1). The sample set is featured with 12-waveband photometry and labeled with spectrum-based catalogs, including Sloan Digital Sky Survey (SDSS) spectroscopic data, the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), and VERON- CAT - the Veron Catalog of Quasars & AGN (VV13. Cat. VII/258). The performance of the classifier is presented with the applications of blind test validations based on RAdial Velocity Extension (RAVE), the Kepler Input Catalog (KIC), the 2 MASS (the Two Micron All Sky Survey) Redshift Survey (2MRS), and the UV-bright Quasar Survey (UVQS). A new algorithm was applied to constrain the potential extrapolation that could decrease the performance of the machine-learning classifier. The accuracies of the classifier are 96.5% in the blind test and 97.0% in training cross-validation. The F1-scores for each class are presented to show the balance between the precision and the recall of the classifier. We also discuss different methods to constrain the potential extrapolation.
|
