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

The current archives of LAMOST multi-object spectrograph contain millions offully reduced spectra, from which the automatic pipelines have producedcatalogues of many parameters of individual objects, including theirapproximate spectral classification. This is, however, mostly based on theglobal shape of the whole spectrum and on integral properties of spectra ingiven bandpasses, namely presence and equivalent width of prominent spectrallines, while for identification of some interesting object types (e.g. Be starsor quasars) the detailed shape of only a few lines is crucial. Here the machinelearning is bringing a new methodology capable of improving the reliability ofclassification of such objects even in boundary cases.  We present results of Spark-based semi-supervised machine learning of LAMOSTspectra attempting to automatically identify the single and double-peakemission of H alpha line typical for Be and B[e] stars. The labelled sample wasobtained from archive of 2m Perek telescope at Ond\v{r}ejov observatory. Asimple physical model of spectrograph resolution was used in domain adaptationto LAMOST training domain. The resulting list of candidates contains dozens ofBe stars (some are likely yet unknown), but also a bunch of interesting objectsresembling spectra of quasars and even blazars, as well as many instrumentalartefacts. The verification of a nature of interesting candidates benefitedconsiderably from cross-matching and visualisation in the Virtual Observatoryenvironment.

Identification of Interesting Objects in Large Spectral Surveys Using Highly Parallelized Machine Learning