Kushwahaa, Tanya, Matsuura, Mikako  ORCID: https://orcid.org/0000-0002-5529-5593, Wesson, Roger and Davis, Timothy ORCID: https://orcid.org/0000-0003-4932-9379
2026.
Hybrid machine learning classification of AGB stars in Gaia
DR3.
Proceedings of the International Astronomical Union
21
, pp. 97-101.
10.1017/S1743921325104419
|
Preview |
PDF
- Published Version
Available under License Creative Commons Attribution. Download (476kB) | Preview |
Abstract
Machine learning (ML) is revolutionising the analysis of large astronomical surveys such as Gaia DR3. We present a two-step ML pipeline to classify Asymptotic Giant Branch (AGB) stars: (i) cosine similarity identifies candidate AGB stars from 140 million sources, and (ii) an XGBoost classifier which separates carbon-rich (C-rich) and oxygen-rich (O-rich) stars. Our classifier achieves ROC-AUC > 99.9%, producing a catalogue of 307,191 O-rich and 4,227 C-rich stars. Feature importance analysis shows that the sixth RP coefficient (RP6) dominates classification, underlining the critical role of Gaia red spectral features. This work demonstrates how hybrid ML approaches can efficiently identify chemically distinct stellar populations in massive survey datasets, providing opportunities for new studies of Galactic structure and stellar evolution.
| Item Type: | Article |
|---|---|
| Date Type: | Published Online |
| Status: | Published |
| Schools: | Schools > Physics and Astronomy |
| Publisher: | Cambridge University Press |
| Funders: | EPSRC |
| Date of First Compliant Deposit: | 13 January 2026 |
| Date of Acceptance: | 19 December 2025 |
| Last Modified: | 13 Oct 2026 11:28 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/183851 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions