On the estimation of stellar parameters with uncertainty prediction from Generative Artificial Neural Networks: application to Gaia RVS simulated spectra

Abstract

Aims. We present an innovative artificial neural network (ANN) architecture, called Generative ANN (GANN), that computes the forward model, that is it learns the function that relates the unknown outputs (stellar atmospheric parameters, in this case) to the given inputs (spectra). Such a model can be integrated in a Bayesian framework to estimate the posterior distribution of the outputs. Methods. The architecture of the GANN follows the same scheme as a normal ANN, but with the inputs and outputs inverted. We train the network with the set of atmospheric parameters (Teff, logg, [Fe/H] and [alpha/Fe]), obtaining the stellar spectra for such inputs. The residuals between the spectra in the grid and the estimated spectra are minimized using a validation dataset to keep solutions as general as possible. Results. The performance of both conventional ANNs and GANNs to estimate the stellar parameters as a function of the star brightness is presented and compared for different Galactic populations. GANNs provide significantly improved parameterizations for early and intermediate spectral types with rich and intermediate metallicities. The behaviour of both algorithms is very similar for our sample of late-type stars, obtaining residuals in the derivation of [Fe/H] and [alpha/Fe] below 0.1dex for stars with Gaia magnitude Grvs<12, which accounts for a number in the order of four million stars to be observed by the Radial Velocity Spectrograph of the Gaia satellite. Conclusions. Uncertainty estimation of computed astrophysical parameters is crucial for the validation of the parameterization itself and for the subsequent exploitation by the astronomical community. GANNs produce not only the parameters for a given spectrum, but a goodness-of-fit between the observed spectrum and the predicted one for a given set of parameters. Moreover, they allow us to obtain the full posterior distribution...

References in corpus (6)

• Automated derivation of stellar atmospheric parameters and chemical abundances: the MATISSE algorithm
• The Gaia astrophysical parameters inference system (Apsis). Pre-launch description
• Stellar parametrization from Gaia RVS spectra
• Physical Parameterization of Stellar Spectra: The Neural Network Approach
• The expected performance of stellar parametrization with Gaia spectrophotometry
• Three-Dimensional Spectral Classification of Low-Metallicity Stars Using Artificial Neural Networks

Cited by in corpus (9)

• Gaia Data Release 3: Analysis of RVS spectra using the General Stellar Parametriser from spectroscopy
• The Payne: self-consistent ab initio fitting of stellar spectra
• Gaia Data Release 3: Astrophysical parameters inference system (Apsis) I -- methods and content overview
• WIYN Open Cluster Study, LXXVI. Li Evolution Among Stars of Low/Intermediate Mass: The Metal-Deficient Open Cluster, NGC 2506
• SETI with Gaia: The observational signatures of nearly complete Dyson spheres
• Analysis of Stellar Spectra from LAMOST DR5 with Generative Spectrum Networks
• The atmospheric parameters of FGK stars using wavelet analysis of CORALIE spectra
• Stellar Spectral Interpolation using Machine Learning
• Physical Parameters of Stars in NGC 6397 Using ANN-Based Interpolation and Full Spectrum Fitting