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

In the coming years, next-generation space-based infrared observatories willsignificantly increase our samples of rare massive stars, representing atremendous opportunity to leverage modern statistical tools and methods to testmassive stellar evolution in entirely new environments. Such work is onlypossible if the observed objects can be reliably classified. Spectroscopicobservations are infeasible with more distant targets, and so we wish todetermine whether machine learning methods can classify massive stars usingbroadband infrared photometry. We find that a Support Vector Machine classifieris capable of coarsely classifying massive stars with labels corresponding tohot, cool, and emission line stars with high accuracy, while rejectingcontaminating low mass giants. Remarkably, 76\% of emission line stars can berecovered without the need for narrowband or spectroscopic observations. Weclassify a sample of ${\sim}2500$ objects with no existing labels, and identifyfourteen candidate emission line objects. Unfortunately, despite the highprecision of the photometry in our sample, the heterogeneous origins of thelabels for the stars in our sample severely inhibits our classifier fromdistinguishing classes of stars with more granularity. Ultimately, no large andhomogeneously labeled sample of massive stars currently exists. Withoutsignificant efforts to robustly classify evolved massive stars -- which isfeasible given existing data from large all-sky spectroscopic surveys --shortcomings in the labeling of existing data sets will hinder efforts toleverage the next-generation of space observatories.

Photometric Classifications of Evolved Massive Stars: Preparing for the Era of Webb and Roman with Machine Learning