Machine Learning Techniques to Distinguish Giant Stars from Dwarf Stars Using Only Photometry—Pushing Redward
Open Access
- 14 November 2025
- journal article
- Published by American Astronomical Society in The Astronomical Journal
- Vol. 170 (6) , 327
Abstract
We present our photometric method, which combines Subaru/Hyper Suprime-Cam N B 515, g -band, and i- band filters to distinguish giant stars in Local Group galaxies from Milky Way dwarf contamination. The N B 515 filter is a narrowband filter that covers the MgI+MgH features at 5150 Å and is sensitive to stellar surface gravity. Using synthetic photometry derived from large empirical stellar spectral libraries, we model the N B 515 filter’s sensitivity to stellar atmospheric parameters and chemical abundances. Our results demonstrate that the N B 515 filter effectively separates dwarfs from giants, even for the reddest and coolest M-type stars. To further enhance this separation, we develop machine learning models that improve the classification on the two-color ( g − i , N B 515 − g ) diagram. We apply these models to photometric data from the Fornax dwarf spheroidal galaxy and two fields of M31, successfully identifying red giant branch stars in these galaxies.Keywords
Funding Information
- Schmidt Sciences (NA)
This publication has 66 references indexed in Scilit:
- SkyMapper Southern Survey: Data release 4Publications of the Astronomical Society of Australia, 2024
- Array programming with NumPyNature, 2020
- SciPy 1.0: fundamental algorithms for scientific computing in PythonNature Methods, 2020
- Fundamental M-dwarf parameters from high-resolution spectra using PHOENIX ACES modelsAstronomy & Astrophysics, 2016
- The Besançon Galaxy model renewedAstronomy & Astrophysics, 2014
- Astropy: A community Python package for astronomyAstronomy & Astrophysics, 2013
- The star formation and chemical evolution history of the Fornax dwarf spheroidal galaxyAstronomy & Astrophysics, 2012
- Stellar populations in the Milky Way bulge region: towards solving the Galactic bulge and bar shapes using 2MASS dataAstronomy & Astrophysics, 2012
- X-shooter, the new wide band intermediate resolution spectrograph at the ESO Very Large TelescopeAstronomy & Astrophysics, 2011
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989