Stellar Atmospheric Parameters From Gaia BP/RP Spectra using Uncertain Neural Networks

TL;DR

This paper introduces an Uncertain Neural Network model trained on APOGEE data to accurately predict stellar atmospheric parameters from Gaia BP/RP spectra, providing robust uncertainty estimates and validating against multiple surveys.

Contribution

The paper presents a novel application of Uncertain Neural Networks to Gaia spectra, achieving high-precision parameter predictions with uncertainty quantification and analyzing spectral feature importance.

Findings

Median formal uncertainties are 0.068 dex for [Fe/H] and 0.14 dex for $T_\mathrm{eff}$

Strong correlation between predicted parameters and external survey data

Produced a publicly available catalogue of stellar parameters

Abstract

With the plentiful information available in the Gaia BP/RP spectra, there is significant scope for applying discriminative models to extract stellar atmospheric parameters and abundances. We describe an approach to leverage an `Uncertain Neural Network' model trained on APOGEE data to provide high-quality predictions with robust estimates for per-prediction uncertainty. We report median formal uncertainties of 0.068 dex, 69.1K, 0.14 dex, 0.031 dex, 0.040 dex, and 0.029 dex for [Fe/H], $T_\mathrm{eff}$, $\log g$, [C/Fe], [N/Fe], and [$\alpha$/M] respectively. We validate these predictions against our APOGEE training data, LAMOST, and Gaia GSP-Phot stellar parameters, and see a strong correlation between our predicted parameters and those derived from these surveys. We investigate the information content of the spectra by considering the `attention' our model pays to different spectral features compared to expectations from synthetic spectra calculations. Our model's predictions are applied to the Gaia dataset, and we produce a publicly available catalogue of our model's predictions.