Beyond Gaia DR3: Tracing the [$\alpha$/M]-[M/H] bimodality from the inner to the outer Milky Way disc with Gaia-RVS and convolutional neural networks

TL;DR

This paper introduces a hybrid convolutional neural network that combines Gaia-RVS spectra with other Gaia data to accurately determine stellar parameters and chemical abundances, enabling the first characterization of the [$ ext{α}$/M]-[M/H] bimodality across the Milky Way.

Contribution

The study presents a novel CNN approach that integrates diverse Gaia datasets to derive stellar parameters with high precision, even at low S/N, and applies it to map chemical bimodality across the Galaxy.

Findings

Achieved precise stellar parameters for over 886,000 RVS stars.

Successfully characterized the [$ ext{α}$/M]-[M/H] bimodality from inner to outer Milky Way.

Demonstrated robustness of the CNN against noise in RVS data.

Abstract

In June 2022, Gaia DR3 has provided the astronomy community with about one million spectra from the Radial Velocity Spectrometer (RVS) covering the CaII triplet region. However, one-third of the published spectra have 15<S/N<25 per pixel such that they pose problems for classical spectral analysis pipelines, and therefore, alternative ways to tap into these large datasets need to be devised. We aim to leverage the versatility and capabilities of machine learning techniques for supercharged stellar parametrisation by combining Gaia-RVS spectra with the full set of Gaia products and high-resolution, high-quality ground-based spectroscopic reference datasets. We developed a hybrid convolutional neural network (CNN) that combines the Gaia DR3 RVS spectra, photometry (G, G_BP, G_RP), parallaxes, and XP coefficients to derive atmospheric parameters (Teff, log(g) as well as overall [M/H]) and chemical abundances ([Fe/H] and [{\alpha}/M]). We trained the CNN with a high-quality training sample based on APOGEE DR17 labels. With this CNN, we derived homogeneous atmospheric parameters and abundances for 886080 RVS stars that show remarkable precision and accuracy compared to external datasets (such as GALAH and asteroseismology). The CNN is robust against noise in the RVS data, and we derive very precise labels down to S/N=15. We managed to characterise the [{\alpha}/M]-[M/H] bimodality from the inner regions to the outer parts of the Milky Way, which has never been done using RVS spectra or similar datasets. This work is the first to combine machine learning with such diverse datasets and paves the way for large-scale machine learning analysis of Gaia-RVS spectra from future data releases. Large, high-quality datasets can be optimally combined thanks to the CNN, thereby realising the full power of spectroscopy, astrometry, and photometry.