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

CABRAL, J. B.; LARES, M.; GUROVICH, S.; MINNITI, D.; GRANITTO, P. M.

ASTRONOMY AND ASTROPHYSICS

EDP SCIENCES S A

Lugar: Paris; Año: 2021 vol. 652

0004-6361

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 statisticalmethods, 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 potentiallydetrimental features.Methods. We introduce and discuss the notion of drifting features, related with small changes in the properties as measured in thedata features. We use the identification techniques of RR Lyrae variable objects (RRLs) in the VVV based on an earlier work andintroduce a method for detecting drifting features. For the VVV, each sky observation zone is called a tile. Our method forces theclassifier to learn from the sources (mostly stellar ?point sources?) which tile the source originated from and to select the features thatare 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 tileof origin of the sources. For our particular example of detecting RRLs in the VVV, we find that drifting features are mostly relatedto colour indices. On the other hand, we show that even if we have a clear set of drifting features in our problem, they are mostlyinsensitive to the identification of RRLs.Conclusions. Drifting features can be efficiently identified using ML methods. However, in our example removing drifting featuresdoes not improve the identification of RRLs