An autoencoder of stellar spectra and its application in automatically estimating atmospheric parameters

Abstract

This article investigates the problem of estimating stellar atmospheric parameters from spectra. Feature extraction is a key procedure in estimating stellar parameters automatically. We propose a scheme for spectral feature extraction and atmospheric parameter estimation using the following three procedures: firstly, learn a set of basic structure elements (BSE) from stellar spectra using an autoencoder; secondly, extract representative features from stellar spectra based on the learned BSEs through some procedures of convolution and pooling; thirdly, estimate stellar parameters ($T_{eff}$, log$g$, [Fe/H]) using a back-propagation (BP) network. The proposed scheme has been evaluated on both real spectra from Sloan Digital Sky Survey (SDSS)/Sloan Extension for Galactic Understanding and Exploration (SEGUE) and synthetic spectra calculated from Kurucz's new opacity distribution function (NEWODF) models. The best mean absolute errors (MAEs) are 0.0060 dex for log$T_{eff}$, 0.1978 dex for log$g$ and 0.1770 dex for [Fe/H] for the real spectra and 0.0004 dex for log$T_{eff}$, 0.0145 dex for log$g$ and 0.0070 dex for [Fe/H] for the synthetic spectra.

11 pages, 5 figures, 5 tables

References in corpus (5)

• The First Data Release (DR1) of the LAMOST general survey
• Automated derivation of stellar atmospheric parameters and chemical abundances: the MATISSE algorithm
• Estimation of stellar atmospheric parameters from SDSS/SEGUE spectra
• Principal Component Analysis of SDSS Stellar Spectra
• SDSS/SEGUE Spectral Feature Analysis For Stellar Atmospheric Parameter Estimation

Cited by in corpus (17)

• Abundance Estimates for 16 Elements in 6 Million Stars from LAMOST DR5 Low-Resolution Spectra
• Deep learning of multi-element abundances from high-resolution spectroscopic data
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Estimating stellar atmospheric parameters, absolute magnitudes and elemental abundances from the LAMOST spectra with Kernel-based Principal Component Analysis
• Dimensionality Reduction of SDSS Spectra with Variational Autoencoders
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Stellar classification from single-band imaging using machine learning
• Estimating Stellar Parameters from LAMOST Low-resolution Spectra
• Using autoencoders and deep transfer learning to determine the stellar parameters of 286 CARMENES M dwarfs
• The GALAH survey: Characterization of emission-line stars with spectral modelling using autoencoders
• Investigation of stellar magnetic activity using variational autoencoder based on low-resolution spectroscopic survey
• Classifying CMB time-ordered data through deep neural networks
• Stellar Karaoke: deep blind separation of terrestrial atmospheric effects out of stellar spectra by velocity whitening
• An Unsupervised Machine Learning Approach to Identify Spectral Energy Distribution Outliers: Application to the S-PLUS DR4 data
• Toward an auditory Virtual Observatory (preprint)
• Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources
• Towards model-free stellar chemical abundances. Potential applications in the search for chemically peculiar stars in large spectroscopic surveys