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

TL;DR

This study demonstrates that ensemble machine learning algorithms can effectively select quasars based on variability data, achieving high precision and completeness, and are feasible even with limited observational time frames.

Contribution

The paper introduces the use of decision-tree ensemble algorithms for quasar selection based solely on variability parameters, outperforming color-based methods and showing efficiency with short-term data.

Findings

All three models achieved ~98.5% precision and 97.5% completeness.

Variability-based selection outperforms color-based methods in accuracy.

Quasar sample completeness in Stripe 82 is estimated at ~93%.

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.