Estimating stellar atmospheric parameters based on Lasso features

• Published in: Research in astronomy and astrophysics 2014-04, Vol.14 (4), p.423-432
• Main Authors: Liu, Chuan-Xing, Zhang, Pei-Ai, Lu, Yu
• Format: Article
• Language: English
• Subjects: Algorithms; Atmospherics; Automation; Estimating; LAMOST; Mathematical models; SDSS; Sky surveys (astronomy); Spectra; Stellar spectra; 大气参数; 恒星光谱; 支持向量回归; 数字巡天; 模型估计; 特征选择
• ISSN: 1674-4527; 2397-6209
• DOI: 10.1088/1674-4527/14/4/005

With the rapid development of large scale sky surveys like the Sloan Digital Sky Survey （SDSS）, GAIA and LAMOST （Guoshoujing telescope）, stellar spectra can be obtained on an ever-increasing scale. Therefore, it is necessary to estimate stel- lar atmospheric parameters such as Teff, log g and [Fe/H] automatically to achieve the scientific goals and make full use of the potential value of these observations. Feature selection plays a key role in the automatic measurement of atmospheric parameters. We propose to use the least absolute shrinkage selection operator （Lasso） algorithm to select features from stellar spectra. Feature selection can reduce redundancy in spectra, alleviate the influence of noise, improve calculation speed and enhance the robustness of the estimation system. Based on the extracted features, stellar atmospheric param- eters are estimated by the support vector regression model. Three typical schemes are evaluated on spectral data from both the ELODIE library and SDSS. Experimental results show the potential performance to a certain degree. In addition, results show that our method is stable when applied to different spectra.