The feasibility and flexibility of selecting quasars by variability using ensemble machine learning algorithms

作     者：Da-Ming Yang Zhang-Liang Xie Jun-Xian Wang 羊达明;谢彰亮;王俊贤

作者机构：CAS Key Laboratory for Researches in Galaxies and CosmologyUniversity of Science and Technology of ChinaChinese Academy of SciencesHefei 230026China 

出 版 物：《Research in Astronomy and Astrophysics》 (天文和天体物理学研究（英文版）)

年 卷 期：2021年第21卷第4期

页      面：271-281页

核心收录：

学科分类：07[理学] 070401[理学-天体物理] 0704[理学-天文学] 

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.11421303,11890693) the National Basic Research Program of China(973 program,Grant No.2015CB857005) CAS Frontier Science Key Research Program(QYZDJ-SSW-SLH006) 

主　　题：quasars:general catalogs methods:data analysis 

摘      要：In this work,we train three decision-tree based ensemble machine learning algorithms(Random Forest Classifier,Adaptive Boosting and Gradient Boosting Decision Tree respectively)to study quasar selection in the variable source catalog in SDSS Stripe *** build training and test samples(both containing 1:1 of quasars and stars)using the spectroscopic confirmed sources in SDSS DR14(including8330 quasars and 3966 stars).We find that when trained with variation parameters alone,all three models can select quasars with similarly and remarkably high precision and completeness(~98.5%and 97.5%),even better than trained with SDSS colors alone(~97.2%and 96.5%),consistent with previous *** applying the trained models on the variable sources without spectroscopic identifications,we estimate the spectroscopically confirmed quasar sample in Stripe 82 variable source catalog is~93%complete(95%for mi19.0).Using the Random Forest Classifier we derive the relative importance of the observational features utilized for *** further show that even using one-or two-year time domain observations,variability-based quasar selection could still be highly efficient.