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

Observed Young Stellar Objects (YSOs) are used to study star formation andcharacterize star forming regions. For this purpose, YSO candidate catalogs arecompiled from various surveys, especially in the infrared (IR), and simpleselection schemes in colour-magnitude diagrams (CMDs) are often used toidentify and classify YSOs. We propose a methodology for YSO classificationthrough Machine Learning (ML) using Spitzer IR data. We detail our approach inorder to ensure reproducibility and provide an in-depth example on how toefficiently apply ML to an astrophysical classification. We used feedforwardArtificial Neural Networks (ANNs) that use the four IRAC bands ($3.6, 4.5, 5.8$and $8 \mu m$) and the $24\ \mu m$ MIPS band from Spitzer to classify pointsource objects into CI and CII YSO candidates or as contaminants. We found thatANNs can efficiently be applied to YSO classification with a contained numberof neurons ($\sim$ 25). Knowledge gathered on one star-forming region has shownto be partly efficient for prediction in new regions. Best generalizationcapacity was achieved using a combination of several star-forming regions totrain the network. Carefully rebalancing the training proportions was necessaryto achieve good results. We achieved above 90% and 97% recovery rate for CI andCII YSOs, respectively, with precision above 80% and 90% for our most generalresult. We took advantage of the ANN great flexibility to define, for eachobject, an effective membership probability to each output class. Using athreshold in this probability was found to efficiently improve theclassification results at a reasonable cost of object exclusion. With thisselection, we reached 90% precision on CI YSOs, for more than half of them. Ourcatalog of YSO candidates in Orion (365 CI, 2381 CII) and NGC 2264 (101 CI, 469CII) predicted by our final ANN is publicly available at CDS.

A neural network-based methodology to select young stellar object candidates from IR surveys