Inferring stellar parameters and their uncertainties from high-resolution spectroscopy using invertible neural networks

Abstract

Context: New spectroscopic surveys will increase the number of astronomical objects requiring characterization by over tenfold.. Machine learning tools are required to address this data deluge in a fast and accurate fashion. Most machine learning algorithms can not estimate error directly, making them unsuitable for reliable science. Aims: We aim to train a supervised deep-learning algorithm tailored for high-resolution observational stellar spectra. This algorithm accurately infer precise estimates while providing coherent estimates of uncertainties by leveraging information from both the neural network and the spectra. Methods: We train a conditional Invertible Neural Network (cINN) on observational spectroscopic data obtained from the GIRAFFE spectrograph (HR10 and HR21 setups) within the Gaia-ESO survey. A key features of cINN is its ability to produce the Bayesian posterior distribution of parameters for each spectrum. By analyzing this distribution, we inferred parameters and their uncertainties. Several tests have been applied to study how parameters and errors are estimated. Results: We achieved an accuracy of 28K in $T_{\text{eff}}$, 0.06 dex in $\log g$, 0.03 dex in $[\text{Fe/H}]$, and between 0.05 dex and 0.17 dex for the other abundances for high quality spectra. Accuracy remains stable with low signal-to-noise ratio spectra. The uncertainties obtained are well within the same order of magnitude. The network accurately reproduces astrophysical relationships both on the scale of the Milky Way and within smaller star clusters. We created a table containing the new parameters generated by our cINN. Conclusion: This neural network represents a compelling proposition for future astronomical surveys. These coherent derived uncertainties make it possible to reuse these estimates in other works as Bayesian priors and thus present a solid basis for future work.

Accepted for publication in A&A

References in corpus (33)

• The Gaia mission
• The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package
• PARSEC: stellar tracks and isochrones with the PAdova and TRieste Stellar Evolution Code
• The Apache Point Observatory Galactic Evolution Experiment (APOGEE)
• The GALAH Survey: Scientific Motivation
• Improving PARSEC models for very low mass stars
• Painting a portrait of the Galactic disc with its stellar clusters
• The Payne: self-consistent ab initio fitting of stellar spectra
• The Gaia-ESO Public Spectroscopic Survey: Implementation, data products, open cluster survey, science, and legacy
• Atomic data for the Gaia-ESO Survey
• Gaia FGK benchmark stars: abundances of alpha and iron-peak elements
• The Gaia-ESO Survey. Mg-Al anti-correlation in iDR4 globular clusters
• The chemical homogeneity of open clusters
• The AMBRE project: A new synthetic grid of high-resolution FGKM stellar spectra
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• The Gaia-ESO Public Spectroscopic Survey: Motivation, implementation, GIRAFFE data processing, analysis, and final data products
• The AMBRE project: The thick thin disk and thin thick disk of the Milky Way
• Stellar parametrization from Gaia RVS spectra
• The Gaia-ESO survey: mapping the shape and evolution of the radial abundance gradients with open clusters
• The Gaia-ESO Survey: calibration strategy
• How Many Elements Matter?
• PySME -- Spectroscopy Made Easier
• The Gaia-ESO Survey: homogenisation of stellar parameters and elemental abundances
• ERGO-ML I: Inferring the assembly histories of IllustrisTNG galaxies from integral observable properties via invertible neural networks
• Open Cluster Chemical Homogeneity Throughout the Milky Way
• Cycle-StarNet: Bridging the gap between theory and data by leveraging large datasets
• Stellar Parameter Determination from Photometry using Invertible Neural Networks
• The RAdial Velocity Experiment (RAVE): Parameterisation of RAVE spectra based on convolutional neural networks
• Stellar Parameters and Chemical Abundances Estimated from LAMOST-II DR8 MRS based on Cycle-StarNet
• Emission-line diagnostics of HII regions using conditional Invertible Neural Networks
• The Gaia-ESO Survey: Chemical evolution of Mg and Al in the Milky Way with Machine-Learning
• Noise-Net: Determining physical properties of HII regions reflecting observational uncertainties
• Spectral classification of young stars using conditional invertible neural networks I. Introducing and validating the method

Cited by in corpus (6)

• The Galactic inner spiral arms revealed by the Gaia ESO Survey chemical abundances. Metallicity and [Mg/Fe] ratios
• Spectral classification of young stars using conditional invertible neural networks II. Application to Trumpler 14 in Carina
• A normalizing flow approach for the inference of star cluster properties from unresolved broadband photometry I: Comparison to spectral energy distribution fitting
• Applying Vision Transformers on Spectral Analysis of Astronomical Objects
• A method to derive self-consistent NLTE astrophysical parameters for 4 million high-resolution 4MOST stellar spectra in half a day with invertible neural networks
• Playing CHESS with stars. I. Search for similar stars in large spectroscopic data sets