The Gaia-ESO Survey: Chemical evolution of Mg and Al in the Milky Way with Machine-Learning

Abstract

We aim to prepare the machine-learning ground for the next generation of spectroscopic surveys, such as 4MOST and WEAVE. Our goal is to show that convolutional neural networks can predict accurate stellar labels from relevant spectral features in a physically meaningful way. We built a neural network and trained it on GIRAFFE spectra with associated stellar labels from the sixth internal Gaia-ESO data release. Our neural network predicts the atmospheric parameters Teff and log(g) as well as the chemical abundances [Mg/Fe], [Al/Fe], and [Fe/H] for 30115 stellar spectra. The scatter of predictions from eight slightly different network models shows a high internal precision of the network results: 24 K for Teff, 0.03 for log(g), 0.02 dex for [Mg/Fe], 0.03 dex for [Al/Fe], and 0.02 dex for [Fe/H]. The network gradients reveal that the network is inferring the labels in a physically meaningful way from spectral features. Validation with benchmark stars and several scientific applications confirm that our network predictions are accurate for individual stars and recover the properties of different stellar populations in the Milky Way galaxy. Such a study provides very good insights into the application of machine-learning for the spectral analysis of large-scale spectroscopic surveys, such as WEAVE and 4MIDABLE-LR and -HR (4MOST Milky Way disk and bulge low- and high-resolution). The community will have to put a substantial effort into building proactive training sets for machine-learning methods to minimize the possible systematics.

Submitted to A&A

References in corpus (18)

• The Gaia mission
• galpy: A Python Library for Galactic Dynamics
• The Gaia-ESO Survey: the Galactic Thick to Thin Disc transition
• The Principles of Deep Learning Theory
• Age dissection of the Milky Way discs: red giants in the Kepler field
• Atomic data for the Gaia-ESO Survey
• The Sixth Data Release of the Radial Velocity Experiment (RAVE) -- I: Survey Description, Spectra and Radial Velocities
• The Ages of the Thin Disk, Thick Disk, and the Halo from Nearby White Dwarfs
• The Gaia-ESO Survey: the chemical structure of the Galactic discs from the first internal data release
• The GALAH Survey: Non-LTE departure coefficients for large spectroscopic surveys
• The Galah Survey: Classification and diagnostics with t-SNE reduction of spectral information
• The Gaia-ESO Survey: calibration strategy
• A Unified tool to estimate Distances, Ages and Masses (UniDAM) from spectrophotometric data
• Non-LTE abundance corrections for late-type stars from 2000Å to 3μm: I. Na, Mg, and Al
• The RAdial Velocity Experiment (RAVE): Parameterisation of RAVE spectra based on convolutional neural networks
• The Gaia-ESO Survey: Preparing the ground for 4MOST & WEAVE galactic surveys. Chemical evolution of lithium with machine learning
• The CoRoT-GES Collaboration. Improving Red Giants spectroscopic surface gravity and abundances with asteroseismology
• Study of star clusters in the M83 galaxy with a convolutional neural network

Cited by in corpus (7)

• Transferring spectroscopic stellar labels to 217 million Gaia DR3 XP stars with SHBoost
• The Gaia-ESO Survey: Preparing the ground for 4MOST & WEAVE galactic surveys. Chemical evolution of lithium with machine learning
• Advanced Classification of Hot Subdwarf Binaries Using Artificial Intelligence Techniques and Gaia DR3 data
• Inferring stellar parameters and their uncertainties from high-resolution spectroscopy using invertible neural networks
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• The GALAH survey: Improving chemical abundances using star clusters
• Automated quasar continuum estimation using neural networks: a comparative study of deep-learning architectures