A machine learning approach to photometric metallicities of giant stars

TL;DR

This paper introduces a neural network method to estimate metallicities and distances of giant stars using multi-band photometry and Gaia parallaxes, enabling large-scale stellar characterization beyond spectroscopic limits.

Contribution

The study develops a two-stage neural network approach that combines photometry, parallaxes, and spectroscopic data to estimate stellar metallicities and distances with quantified uncertainties.

Findings

Achieved metallicity predictions with ±0.19 dex uncertainty.

Recovered known metallicity gradients in the Galactic bulge.

Validated the method by analyzing spatial and kinematic metallicity gradients.

Abstract

Despite the advances provided by large-scale photometric surveys, stellar features - such as metallicity - generally remain limited to spectroscopic observations often of bright, nearby low-extinction stars. To rectify this, we present a neural network approach for estimating the metallicities and distances of red giant stars with 8-band photometry and parallaxes from Gaia EDR3 and the 2MASS and WISE surveys. The algorithm accounts for uncertainties in the predictions arising from the range of possible outputs at each input and from the range of models compatible with the training set (through drop-out). A two-stage procedure is adopted where an initial network to estimate photo-astrometric parallaxes is trained using a large sample of noisy parallax data from Gaia EDR3 and then a secondary network is trained using spectroscopic metallicities from the APOGEE and LAMOST surveys and an augmented feature space utilising the first-stage parallax estimates. The algorithm produces metallicity predictions with an average uncertainty of $\pm0.19$ dex. The methodology is applied to stars within the Galactic bar/bulge with particular focus on a sample of 1.69 million objects with Gaia radial velocities. We demonstrate the use and validity of our approach by inspecting both spatial and kinematic gradients with metallicity in the Galactic bar/bulge recovering previous results on the vertical metallicity gradient ($-0.528 \pm 0.002$ dex/kpc) and the vertex deviation of the bar ($-21.29 \pm 2.74$ deg).