Featureless classification of light curves

Abstract

In the era of rapidly increasing amounts of time series data, classification of variable objects has become the main objective of time-domain astronomy. Classification of irregularly sampled time series is particularly difficult because the data cannot be represented naturally as a vector which can be directly fed into a classifier. In the literature, various statistical features serve as vector representations.In this work, we represent time series by a density model. The density model captures all the information available, including measurement errors. Hence, we view this model as a generalisation to the static features which directly can be derived, e.g., as moments from the density. Similarity between each pair of time series is quantified by the distance between their respective models. Classification is performed on the obtained distance matrix.In the numerical experiments, we use data from the OGLE and ASAS surveys and demonstrate that the proposed representation performs up to par with the best currently used feature-based approaches. The density representation preserves all static information present in the observational data, in contrast to a less complete description by features. The density representation is an upper boundary in terms of information made available to the classifier. Consequently, the predictive power of the proposed classification depends on the choice of similarity measure and classifier, only. Due to its principled nature, we advocate that this new approach of representing time series has potential in tasks beyond classification, e.g., unsupervised learning.

K2 variable catalogue – II. Machine learning classification of variable stars and eclipsing binaries in K2 fields 0–4

“…However, there is a subjective element to selecting features, and it can be desirable to minimise this if possible (see e.g. Kügler et al 2015). We do so through the use of the SOM.…”

“…Richards et al 2011aRichards et al , 2012Masci et al 2014). Several improvements have been proposed, in areas such as parametrizing light curves with maximal information retention (Kügler, Gianniotis & Polsterer 2015), and adjusting for training set deficiencies (Richards et al 2011b). One method of unsupervised machine learning is a Kohonen Self-Organizing Map (SOM;Kohonen 1990) demonstrated by Brett, West & Wheatley (2004) in an astronomical context.…”

A case study of ACV variables discovered in the Zwicky Transient Facility survey

“…Although many excellent data sources on stellar variability are now available, the class of the ACV variables is only rarely considered in the algorithms employed for the automatic classification of variable stars into astrophysically meaningful classes (Blomme et al 2010;Kügler et al 2015;Bass & Borne 2016). In this paper we present a case study of new ACV variables discovered in data from the Zwicky Transient Facility (ZTF), and show that the accuracy and cadence of the ZTF allows us to detect previously unknown stars of this kind.…”

A case study of ACV variables discovered in the Zwicky Transient Facility survey

“…Although many excellent data sources on stellar variability are now available, the class of the ACV variables is only rarely considered in the algorithms employed for the automatic classification of variable stars into astrophysically meaningful classes (Blomme et al 2010;Kügler et al 2015;Bass & Borne 2016). In this paper, we present a case study of new ACV variables discovered in data from the Zwicky Transient Facility (ZTF) and show that the accuracy and cadence of the ZTF allows to detect previously unknown stars of this kind.…”