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

When completed, the PHANGS-HST project will provide a census of roughly50,000 compact star clusters and associations, as well as human morphologicalclassifications for roughly 20,000 of those objects. These large numbersmotivated the development of a more objective and repeatable method to helpperform source classifications. In this paper we consider the results for fivePHANGS-HST galaxies (NGC 628, NGC 1433, NGC 1566, NGC 3351, NGC 3627) usingclassifications from two convolutional neural network architectures (RESNET andVGG) trained using deep transfer learning techniques. The results are comparedto classifications performed by humans. The primary result is that the neuralnetwork classifications are comparable in quality to the human classificationswith typical agreement around 70 to 80$\%$ for Class 1 clusters (symmetric,centrally concentrated) and 40 to 70$\%$ for Class 2 clusters (asymmetric,centrally concentrated). If Class 1 and 2 are considered together the agreementis 82 $\pm$ 3$\%$. Dependencies on magnitudes, crowding, and background surfacebrightness are examined. A detailed description of the criteria and methodologyused for the human classifications is included along with an examination ofsystematic differences between PHANGS-HST and LEGUS. The distribution of datapoints in a colour-colour diagram is used as a 'figure of merit' to furthertest the relative performances of the different methods. The effects on scienceresults (e.g., determinations of mass and age functions) of using differentcluster classification methods are examined and found to be minimal.

Star Cluster Classification in the PHANGS-HST Survey: Comparison between Human and Machine Learning Approaches