Regression Prediction of Effective Temperature of Stellar Spectrum Based on Kernel Method

There are many factors that lead to the huge difference in stellar spectra, most important of which atmospheric physical parameters, namely, effective temperature, surface gravity and chemical abundance. This study is based on classified star data LAMOST DR6 with a temperature value 7500-9000K signal-to-noise ratio S/N greater than 50. The results two methods compared through regression verification nuclear least squares (KLSR) PCA (KPCR), scope application discussed, lick parameters affecting regressed. By regressing such stars, method for predicting measured spectral under large samples given, provides certain reference trend evolution studying law stars.