Assessing the performance of LTE and NLTE synthetic stellar spectra in a machine learning framework

Abstract

In the current era of stellar spectroscopic surveys, synthetic spectral libraries are the basis for the derivation of stellar parameters and chemical abundances. In this paper, we compare the stellar parameters determined using five popular synthetic spectral grids (INTRIGOSS, FERRE, AMBRE, PHOENIX, and MPIA/1DNLTE) with our convolutional neural network (CNN, StarNet). The stellar parameters are determined for six physical properties (effective temperature, surface gravity, metallicity, [α/Fe], radial velocity, and rotational velocity) given the spectral resolution, signal-to-noise, and wavelength range of optical FLAMES-UVES spectra from the Gaia-ESO Survey. Both CNN modelling and epistemic uncertainties are incorporated through training an ensemble of networks. StarNet training was also adapted to mitigate differences between the synthetic grids and observed spectra by augmenting with realistic observational signatures (i.e. resolution matching, wavelength sampling, Gaussian noise, zeroing flux values, rotational and radial velocities, continuum removal, and masking telluric regions). Using the FLAMES-UVES spectra for FGK type dwarfs and giants as a test set, we quantify the accuracy and precision of the stellar label predictions from StarNet. We find excellent results over a wide range of parameters when StarNet is trained on the MPIA/1DNLTE synthetic grid, and acceptable results over smaller parameter ranges when trained on the 1DLTE grids. These tests also show that our CNN pipeline is highly adaptable to multiple simulation grids.

A Model RRNet for Spectral Information Exploitation and LAMOST Medium-resolution Spectrum Parameter Estimation

“…Some experiments are conducted on the reference data (section 2), RRNet shows good performance on them. In addition, RRNet has higher accuracy and better generalization capability compared to the typical models such as StarNet (Fabbro et al 2017;Bialek et al 2020).…”

“…This kind methods usually estimate parameters by approximating the mapping relationship from observed spectra to stellar parameters (e.g. Fabbro et al 2017;Bialek et al 2020;Leung & Bovy 2018;Wang et al 2020), or from stellar parameters to observed spectra (e.g. Ting et al 2019;Xiang et al 2019;Rui et al 2019) using neural networks.…”

Line-depth ratios as indicators of effective temperature and surface gravity

“…The previous works assumed that the approximations of LTE and hydrostatic equilibrium hold. These kinds of equilibrium have been questioned, and including the non-LTE effects has often modified and improved results of spectroscopic analysis (e.g., Asplund 2005;Bergemann et al 2019;Amarsi et al 2020;Bialek et al 2020). Moreover, it has been demonstrated that significant non-LTE effects appear in some Fe lines (Bergemann et al 2012) and Ca lines (Osorio et al 2019) that are located within the wavelength range of our interest.…”

A Model RRNet for Spectral Information Exploitation and LAMOST Medium-resolution Spectrum Parameter Estimation

“…With the arrival of artificial intelligence and the big data era, deep-learning methods have been attempted to deal with the estimation of stellar parameters. These kinds of methods usually estimate parameters by approximating the mapping relationship from observed spectra to stellar parameters (e.g., Fabbro et al 2017;Leung & Bovy 2018;Bialek et al 2020;Wang et al 2020), or from stellar parameters to observed spectra (e.g., Rui et al 2019;Ting et al 2019;Xiang et al 2019) using neural networks. However, most of the above models use simple fully connected neural networks or convolutional neural networks to establish mapping relationships.…”