The Feasibility and Flexibility of Selecting Quasars by Variability Using Ensemble Machine Learning Algorithms

Abstract

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 82. We build training and test samples (both containing 1:1 of quasars and stars) using the spectroscopic confirmed sources in SDSS DR14 (including 8330 quasars and 3966 stars). We find that, trained with variation parameters alone, all three models can select quasars with similarly and remarkably high precision and completeness ($\sim$ 98.5% and 97.5%), even better than trained with SDSS colors alone ($\sim$ 97.2% and 96.5%), consistent with previous studies. Through 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 $\sim$ 93% complete (95% for $m_i<19.0$). Using the Random Forest Classifier we derive the relative importance of the observational features utilized for classifications. We further show that even using one- or two-year time domain observations, variability-based quasar selection could still be highly efficient.

arXiv comment20 pages, 13 figures, accepted to RAA

References in corpus (33)

• Spectroscopic Target Selection in the Sloan Digital Sky Survey: The Quasar Sample
• The Sloan Digital Sky Survey Quasar Catalog V. Seventh Data Release
• Mid-Infrared Selection of Active Galaxies
• Are the Variations in Quasar Optical Flux Driven by Thermal Fluctuations?
• Modeling the Time Variability of SDSS Stripe 82 Quasars as a Damped Random Walk
• Identifying Luminous AGN in Deep Surveys: Revised IRAC Selection Criteria
• Optical and Radio Properties of Extragalactic Sources Observed by the FIRST and SDSS Surveys
• The Sloan Digital Sky Survey Quasar Catalog: Fourteenth Data Release
• Quantifying Quasar Variability As Part of a General Approach To Classifying Continuously Varying Sources
• An Alternative Approach To Measuring Reverberation Lags in Active Galactic Nuclei
• Is Quasar Optical Variability a Damped Random Walk?
• SDSS Standard Star Catalog for Stripe 82: the Dawn of Industrial 1% Optical Photometry
• Flexible and Scalable Methods for Quantifying Stochastic Variability in the Era of Massive Time-Domain Astronomical Data Sets
• Kepler Observations of Rapid Optical Variability in Active Galactic Nuclei
• Optical spectroscopy and X-ray detections of a sample of quasars and AGN selected in the mid-infrared from two Spitzer wide-area surveys
• Selecting Quasars by their Intrinsic Variability
• Optimal Time-Series Selection of Quasars
• A Stochastic Model for the Luminosity Fluctuations of Accreting Black Holes
• Pan-STARRS1 variability of XMM-COSMOS AGN. II. Physical correlations and power spectrum analysis
• Quasar Selection Based on Photometric Variability
• QSO Selection Algorithm Using Time Variability and Machine Learning: Selection of 1,620 QSO Candidates from MACHO LMC Database
• An Empirical Calibration of the Completeness of the SDSS Quasar Survey
• A novel variability-based method for quasar selection: evidence for a rest frame ~54 day characteristic timescale
• Extracting Information from AGN Variability
• Finding, characterizing and classifying variable sources in multi-epoch sky surveys: QSOs and RR Lyrae in PS1 3$\pi$ data
• Assessment of stochastic and deterministic models of 6304 quasar lightcurves from SDSS Stripe 82
• The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) Quasar Survey: the 4th and 5th Data Release
• How far is quasar UV/optical variability from damped random walk at low frequency?
• Variability-based AGN selection using image subtraction in the SDSS and LSST era
• The QUEST-La Silla AGN Variability Survey: selection of AGN candidates through optical variability
• Modeling the Variability of Active Galactic Nuclei by Infinite Mixture of Ornstein-Uhlenbeck(OU) Processes
• Using Leaked Power to Measure Intrinsic AGN Power Spectra of Red-Noise Time Series
• Exploring the Variable Sky with the Sloan Digital Sky Survey

Cited by in corpus (2)

• Galaxy Spectra neural Networks (GaSNets). I. Searching for strong lens candidates in eBOSS spectra using Deep Learning
• Identifications of RR Lyrae stars and Quasars from the simulated data of Mephisto-W Survey