RGC: a radio AGN classifier based on deep learning. I. A semi-supervised multiclass model for VLA images
arXiv:2510.22190v2 Announce Type: replace-cross Abstract: Bent radio active galactic nuclei (RAGNs) -- wide-angle tails (WATs) and narrow-angle tails (NATs) -- trace dense environments in galaxy groups and clusters, yet no multiclass classifier simultaneously separates them from straight Fanaroff--Riley types (sFRI, sFRII) using visually inspected labels and unlabelled data. We release FIRST-2060, a four-class labelled dataset of 2060 RAGNs (sFRI, sFRII, WAT, NAT) constructed from three publicly available catalogues through multi-tier visual inspection, together with the semi-supervised RGC 1.
The continuous research and publication cycle in fields like AI and astrophysics leads to regular updates on specialized applications.
This item represents incremental academic progress within highly specific scientific domains rather than a broader strategic concern.
A new semi-supervised deep learning model and a labelled dataset have been developed for classifying radio AGN images, improving existing astronomical analysis tools.
- · Astrophysics researchers
- · Deep learning practitioners
- · Astronomical observation facilities
Improved accuracy in classifying active galactic nuclei from radio images.
Potential for new insights into galaxy cluster environments by more efficiently identifying RAGN types.
Accelerated discovery of rare or specific celestial phenomena through automated classification.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG