Machine learning search for variable stars
Abstract
Photometric variability detection is often considered as a hypothesis testing problem: an object is variable if the null hypothesis that its brightness is constant can be ruled out given the measurements and their uncertainties. The practical applicability of this approach is limited by uncorrected systematic errors. We propose a new variability detection technique sensitive to a wide range of variability types while being robust to outliers and underestimated measurement uncertainties. We consider variability detection as a classification problem that can be approached with machine learning. Logistic Regression (LR), Support Vector Machines (SVM), k Nearest Neighbours (kNN), Neural Nets (NN), Random Forests (RF), and Stochastic Gradient Boosting classifier (SGB) are applied to 18 features (variability indices) quantifying scatter and/or correlation between points in a light curve. We use a subset of Optical Gravitational Lensing Experiment phase two (OGLEII) Large Magellanic Cloud (LMC) photometry (30 265 light curves) that was searched for variability using traditional methods (168 known variable objects) as the training set and then apply the NN to a new test set of 31 798 OGLEII LMC light curves. Among 205 candidates selected in the test set, 178 are real variables, while 13 lowamplitude variables are new discoveries. The machine learning classifiers considered are found to be more efficient (select more variables and fewer false candidates) compared to traditional techniques using individual variability indices or their linear combination. The NN, SGB, SVM, and RF show a higher efficiency compared to LR and kNN.
 Publication:

Monthly Notices of the Royal Astronomical Society
 Pub Date:
 April 2018
 DOI:
 10.1093/mnras/stx3222
 arXiv:
 arXiv:1710.07290
 Bibcode:
 2018MNRAS.475.2326P
 Keywords:

 methods: data analysis;
 methods: statistical;
 stars: variables: general;
 Astrophysics  Instrumentation and Methods for Astrophysics;
 Astrophysics  Solar and Stellar Astrophysics
 EPrint:
 19 pages, 13 figures, 5 tables