Machine Learning Classification of Gaia Data Release 2

Abstract

Machine learning has increasingly gained more popularity with its incredibly powerful ability to make predictions or calculated suggestions for large amounts of data. We apply the machine learning classification to 85,613,922 objects in the $Gaia$ data release 2, based on the combination of the Pan-STARRS 1 and AllWISE data. The classification results are cross-matched with Simbad database, and the total accuracy is 91.9%. Our sample is dominated by stars, $\sim$ 98%, and galaxies makes up 2%. For the objects with negative parallaxes, about 2.5\% are galaxies and QSOs, while about 99.9% are stars if the relative parallax uncertainties are smaller than 0.2. Our result implies that using the threshold of 0 $<{\sigma }_{\pi }/\pi <$ 0.2 could yield a very clean stellar sample.

References in corpus (4)

• The Gaia mission
• A robust morphological classification of high-redshift galaxies using support vector machines on seeing limited images. I Method description
• Machine learning search for variable stars
• Gaia Data Release 1. Cross-match with external catalogues - Algorithm and results

Cited by in corpus (10)

• Quasar and galaxy classification in Gaia Data Release 2
• Machine Learning Regression of stellar effective temperatures in the second $Gaia$ Data Release
• Machine learning Applied to Star-Galaxy-QSO Classification and Stellar Effective Temperature Regression
• Attention-gating for improved radio galaxy classification
• Evaluating the optical classification of Fermi BCUs using machine learning
• The EXTraS Project: Exploring the X-ray transient and variable sky
• The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves
• A Hybrid method of accurate classification for Blazars Of Uncertain Type in Fermi LAT Catalogs
• Machine Learning-Based Identification of Contaminated Images in Light Curves Data Preprocessing
• Gaia Calibrated UV Luminous Stars in LAMOST