Machine Learning Applied to Star–Galaxy–QSO Classification and Stellar Effective Temperature Regression

Abstract

In modern astrophysics, the machine learning has increasingly gained more popularity with its incredibly powerful ability to make predictions or calculated suggestions for large amounts of data. We describe an application of the supervised machine-learning algorithm, random forests (RF), to the star/galaxy/QSO classification and the stellar effective temperature regression based on the combination of LAMOST and SDSS spectroscopic data. This combination enable us to obtain reliable predictions with one of the largest training sample ever used. The training samples are built with nine-color data set of about three million objects for the classification and seven-color data set of over one million stars for the regression. The performance of the classification and regression is examined with the validation and the blind tests on the objects in the RAVE, 6dFGS, UVQS and APOGEE surveys. We demonstrate that the RF is an effective algorithm with the classification accuracies higher than 99% for the stars and the galaxies, and higher than 94% for the QSOs. These accuracies are higher than the machine-learning results in the former studies. The total standard deviations of the regression are smaller than 200 K that is similar to those of some spectrum-based methods. The machine-learning algorithm with the broad-band photometry provides us a more efficient approach to deal with massive amounts of astrophysical data than traditional color-cuts and SED fit.

KiDS-SQuaD

“…In this second paper of the KiDS-SQuaD project we present a new ML-based classifier to identify extragalactic objects in a search for lensed quasars within the KiDS DR4 data. The technique adopted in this paper has become relatively standard in the extragalactic community to classify objects in multi-band photometric surveys (Gieseke et al 2011;Kovács & Szapudi 2015;Brescia et al 2015;Carrasco et al 2015;Peters et al 2015;Krakowski et al 2016Krakowski et al , 2018Viquar et al 2018;Barrientos et al 2018;Nolte et al 2019;Bai et al 2019;Nakoneczny et al 2019), which provide a very large amount of data.…”

“…Machine learning (ML) methods have proven to be very effective in identifying and classifying extragalactic sources (e.g. Eyer & Blake 2005;Elting et al 2008;Kim et al 2011;Gieseke et al 2011;Kovács & Szapudi 2015;Brescia et al 2015;Peters et al 2015;Krakowski et al 2016Krakowski et al , 2018Viquar et al 2018;Nolte et al 2019;Bai et al 2019) with respect to any manual colour cut. A specific type of classifiers, the ensembles of decision trees, were shown to be advantageous in the identification of extragalactic sources, and in particular quasars (Ball et al 2006;Carrasco et al 2015;Hernitschek et al 2016;Schindler et al 2017Schindler et al , 2018Sergeyev et al 2018;Jin et al 2019;Nakoneczny et al 2019).…”

Identifying galaxies, quasars, and stars with machine learning: A new catalogue of classifications for 111 million SDSS sources without spectra

“…Consequently, photometry data have been demonstrated to be useful as machine learning features in source-type classification by a number of studies (e.g. Carrasco et al 2015;Schindler et al 2019;Kang et al 2019;Nakoneczny et al 2019;Bai et al 2019). Furthermore, testing whether a source is resolved or unresolved can help distinguish the extended profiles of galaxies from stars and quasars (Aguado et al 2019;Baldry et al 2010;Morice-Atkinson et al 2018) and serve as a useful machine learning feature.…”

J-PLUS: Support vector machine applied to STAR-GALAXY-QSO classification

“…New technologies help us accelerate information acquisition from the huge datasets. Several studies have focused on developing classifiers, and they have proved that spectral-based methods are more reliable than those only based on photometric data (Bai et al 2018;Ball et al 2006).…”