Metallicities of 20 Million Giant Stars Based on Gaia XP spectra

TL;DR

This paper introduces a neural network method that accurately estimates metallicities for 20 million giant stars using Gaia XP spectra, especially improving measurements for very metal-poor stars.

Contribution

The study presents a novel uncertainty-aware, cost-sensitive neural network that enhances metallicity estimation from Gaia spectra, including for extremely metal-poor stars, and provides a large, publicly available stellar catalog.

Findings

Achieved metallicity estimates down to [Fe/H] ~ -4.

Accurately identified 360,000 VMP and 50,000 EMP stars.

Demonstrated the method's robustness against carbon enhancement effects.

Abstract

We design an uncertainty-aware cost-sensitive neural network (UA-CSNet) to estimate metallicities from dereddened and corrected Gaia BP/RP (XP) spectra for giant stars. This method accounts for both stochastic errors in the input spectra and the imbalanced density distribution in [Fe/H] values. With a specialized architecture and training strategy, the UA-CSNet improves the precision of the predicted metallicities, especially for very metal-poor (VMP; $\rm [Fe/H] \leq -2.0$) stars. With the PASTEL catalog as the training sample, our model can estimate metallicities down to $\rm [Fe/H] \sim -4$. We compare our estimates with a number of external catalogs and conduct tests using star clusters, finding overall good agreement. We also confirm that our estimates for VMP stars are unaffected by carbon enhancement. Applying the UA-CSNet, we obtain reliable and precise metallicity estimates for approximately 20 million giant stars, including 360,000 VMP stars and 50,000 extremely metal-poor (EMP; $\rm [Fe/H] \leq -3.0$) stars. The resulting catalog is publicly available at https://doi.org/10.12149/101604. This work highlights the potential of low-resolution spectra for metallicity estimation and provides a valuable dataset for studying the formation and chemo-dynamical evolution of our Galaxy.