Optimizing Automated Classification of Periodic Variable Stars in New Synoptic Surveys

TL;DR

This paper addresses the challenge of survey-dependent feature differences in classifying periodic variable stars and introduces noisification, a method to empirically match feature distributions, significantly improving classification accuracy across different surveys.

Contribution

The paper introduces noisification, a novel empirical method to align feature distributions from different surveys, enhancing automated classification of variable stars.

Findings

Noisification significantly reduces classifier error rates.

Feature distribution mismatch causes performance degradation.

Applying noisification improves accuracy from 27% to 7% in a three-class problem.

Abstract

Efficient and automated classification of periodic variable stars is becoming increasingly important as the scale of astronomical surveys grows. Several recent papers have used methods from machine learning and statistics to construct classifiers on databases of labeled, multi--epoch sources with the intention of using these classifiers to automatically infer the classes of unlabeled sources from new surveys. However, the same source observed with two different synoptic surveys will generally yield different derived metrics (features) from the light curve. Since such features are used in classifiers, this survey-dependent mismatch in feature space will typically lead to degraded classifier performance. In this paper we show how and why feature distributions change using OGLE and \textit{Hipparcos} light curves. To overcome survey systematics, we apply a method, \textit{noisification}, which attempts to empirically match distributions of features between the labeled sources used to construct the classifier and the unlabeled sources we wish to classify. Results from simulated and real--world light curves show that noisification can significantly improve classifier performance. In a three--class problem using light curves from \textit{Hipparcos} and OGLE, noisification reduces the classifier error rate from 27.0% to 7.0%. We recommend that noisification be used for upcoming surveys such as Gaia and LSST and describe some of the promises and challenges of applying noisification to these surveys.