English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

As most of the modern astronomical sky surveys produce data faster thanhumans can analyze it, Machine Learning (ML) has become a central tool inAstronomy. Modern ML methods can be characterized as highly resistant to someexperimental errors. However, small changes on the data over long distances orlong periods of time, which cannot be easily detected by statistical methods,can be harmful to these methods. We develop a new strategy to cope with thisproblem, also using ML methods in an innovative way, to identify thesepotentially harmful features. We introduce and discuss the notion of DriftingFeatures, related with small changes in the properties as measured in the datafeatures. We use the identification of RRLs in VVV based on an earlier work andintroduce a method for detecting Drifting Features. Our method forces aclassifier to learn the tile of origin of diverse sources (mostly stellar'point sources'), and select the features more relevant to the task of findingcandidates to Drifting Features. We show that this method can efficientlyidentify a reduced set of features that contains useful information about thetile of origin of the sources. For our particular example of detecting RRLs inVVV, we find that Drifting Features are mostly related to color indices. On theother hand, we show that, even if we have a clear set of Drifting Features inour problem, they are mostly insensitive to the identification of RRLs.Drifting Features can be efficiently identified using ML methods. However, inour example, removing Drifting Features does not improve the identification ofRRLs.

Drifting Features: Detection and evaluation in the context of automatic RRLs identification in VVV