Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV

¹ Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas (CIFASIS, CONICET–UNR), Rosario, Argentina
e-mail: cabral@cifasis-conicet.gov.ar
² Instituto De Astronomía Teórica y Experimental – Observatorio Astronómico Córdoba (IATE–OAC–UNC–CONICET), Córdoba, Argentina
³ Departamento de Física, Facultad de Ciencias Exactas, Universidad Andrés Bello, Av. Fernandez Concha 700, Las Condes, Santiago, Chile
⁴ Instituto Milenio de Astrofísica, Santiago 7500912, Chile
⁵ Vatican Observatory, 00120 Vatican City State, Italy

Received: 4 May 2021
Accepted: 25 May 2021

Abstract

Context. As most of the modern astronomical sky surveys produce data faster than humans can analyse it, machine learning (ML) has become a central tool in astronomy. Modern ML methods can be characterised as highly resistant to some experimental errors. However, small changes in the data over long angular distances or long periods of time, which cannot be easily detected by statistical methods, can be detrimental to these methods.

Aims. We develop a new strategy to cope with this problem, using ML methods in an innovative way to identify these potentially detrimental features.

Methods. We introduce and discuss the notion of drifting features, related with small changes in the properties as measured in the data features. We use the identification techniques of RR Lyrae variable objects (RRLs) in the VVV based on an earlier work and introduce a method for detecting drifting features. For the VVV, each sky observation zone is called a tile. Our method forces the classifier to learn from the sources (mostly stellar ‘point sources’) which tile the source originated from and to select the features that are most relevant to the task of finding candidate drifting features.

Results. We show that this method can efficiently identify a reduced set of features that contains useful information about the tile of origin of the sources. For our particular example of detecting RRLs in the VVV, we find that drifting features are mostly related to colour indices. On the other hand, we show that even if we have a clear set of drifting features in our problem, they are mostly insensitive to the identification of RRLs.

Conclusions. Drifting features can be efficiently identified using ML methods. However, in our example removing drifting features does not improve the identification of RRLs.