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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The periodic pulsations of stars teach us about their underlying physicalprocess. We present a convolutional autoencoder-based pipeline as an automaticapproach to search for out-of-distribution anomalous periodic variables withinThe Zwicky Transient Facility Catalog of Periodic Variable Stars (ZTF CPVS). Weuse an isolation forest to rank each periodic variable by its anomaly score.Our overall most anomalous events have a unique physical origin: they aremostly highly variable and irregular evolved stars. Multiwavelength datasuggest that they are most likely Red Giant or Asymptotic Giant Branch starsconcentrated in the Milky Way galactic disk. Furthermore, we show how thelearned latent features can be used for the classification of periodicvariables through a hierarchical random forest. This novel semi-supervisedapproach allows astronomers to identify the most anomalous events within agiven physical class, significantly increasing the potential for scientificdiscovery.

A Convolutional Autoencoder-Based Pipeline for Anomaly Detection and Classification of Periodic Variables