Denoising spectroscopic data by means of the improved Least-Squares Deconvolution method
The MOST, CoRoT, and Kepler space missions led to the discovery of a large number of intriguing, and in some cases unique, objects among which are pulsating stars, stars hosting exoplanets, binaries, etc. Although the space missions deliver photometric data of unprecedented quality, these data are lacking any spectral information and we are still in need of ground-based spectroscopic and/or multicolour photometric follow-up observations for a solid interpretation. Both faintness of most of the observed stars and the required high S/N of spectroscopic data imply the need of using large telescopes, access to which is limited. In this paper, we look for an alternative, and aim for the development of a technique allowing to denoise the originally low S/N spectroscopic data, making observations of faint targets with small telescopes possible and effective. We present a generalization of the original Least-Squares Deconvolution (LSD) method by implementing a multicomponent average profile and a line strengths correction algorithm. The method was successfully tested on the high resolution spectra of Vega and a Kepler star, KIC04749989. Application to the two pulsating stars, 20 Cvn and HD189631, showed that the technique is also applicable to intrinsically variable stars: the results of frequency analysis and mode identification from the LSD model spectra for both objects are in good agreement with the findings from literature. Depending on S/N of the original data and spectral characteristics of a star, the gain in S/N in the LSD model spectrum typically ranges from 5 to 15 times. The restored LSD model spectra contain all the information on line profile variations present in the original spectra. The method is applicable to both high- (>30 000) and low- (<30 000) resolution spectra, though the information that can be extracted from the latter is limited by the resolving power itself.