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

作者：Yang, Tan; Li, Xiangru^*

来源：Monthly Notices of the Royal Astronomical Society, 2015, 452(1): 158-168.

DOI：10.1093/mnras/stv1210

• methods: statistical
• techniques: spectroscopic
• stars: atmospheres
• stars: fundamental parameters

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 (BSEs) 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, logg, [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 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.

• 出版日期2015-9-1
• 单位华南师范大学