Machine-learning approaches for classifying star-forming galaxies and active galactic nuclei from MIGHTEE-detected radio sources in the COSMOS field

Simple item page
dc.contributor.authorSilima, Walter
dc.contributor.authorAn, Fangxia
dc.contributor.authorVaccari, Mattia
dc.contributor.authorHussein, Eslam
dc.date.accessioned2025-12-11T06:29:52Z
dc.date.available2025-12-11T06:29:52Z
dc.date.issued2025
dc.description.abstractRadio synchrotron emission originates from both massive star formation and black hole accretion, two processes that drive galaxy evolution. Efficient classification of sources dominated by either process is therefore essential for fully exploiting deep, wide-field extragalactic radio continuum surveys. In this study, we implement, optimize, and compare five widely used supervised machine-learning (ML) algorithms to classify radio sources detected in the MeerKAT International GHz Tiered Extragalactic Exploration (MIGHTEE)-COSMOS survey as star-forming galaxies (SFGs) and active galactic nuclei (AGNs). Training and test sets are constructed from conventionally classified MIGHTEE-COSMOS sources, and 18 physical parameters of the MIGHTEE-detected sources are evaluated as input features. As anticipated, our feature analyses rank the five parameters used in conventional classification as the most effective: the infrared–radio correlation parameter ($q_\mathrm{IR}$), the optical compactness morphology parameter (class_star), stellar mass, and two combined mid-infrared colours. By optimizing the ML models with these selected features and testing classifiers across various feature combinations, we find that model performance generally improves as additional features are incorporated. Overall, all five algorithms yield an F1-score (the harmonic mean of precision and recall) >90 per cent even when trained on only 20 per cent of the data set. Among them, the distance-based k-nearest neighbours classifier demonstrates the highest accuracy and stability, establishing it as a robust and effective method for classifying SFGs and AGNs in upcoming large radio continuum surveys.
dc.identifier.citationSilima, W., An, F., Vaccari, M., Hussein, E.A. and Randriamampandry, S., 2025. Machine-learning approaches for classifying star-forming galaxies and active galactic nuclei from MIGHTEE-detected radio sources in the COSMOS field. Monthly Notices of the Royal Astronomical Society, 544(1), pp.799-814.
dc.identifier.urihttps://doi.org/10.1093/mnras/staf1698
dc.identifier.urihttps://hdl.handle.net/10566/21567
dc.language.isoen
dc.publisherOxford University Press
dc.subjectgalaxies: evolution
dc.subjectgalaxies: formation
dc.subjectmethods: observational
dc.subjectradio continuum: galaxies
dc.subjectsoftware: machine learning
dc.titleMachine-learning approaches for classifying star-forming galaxies and active galactic nuclei from MIGHTEE-detected radio sources in the COSMOS field
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
silima_machine_learning_approaches_for_classifying_2025.pdf
Size:
3.15 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Research Articles (Physics)