Searching for Barium Stars from the LAMOST Spectra Using the Machine-learning Method: I

Barium stars are chemically peculiar that exhibit enhancement of s-process elements. Chemical abundance analysis barium can provide crucial clues for the study chemical evolution Galaxy. The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) has released more than 6 million low-resolution spectra FGK-type by Data Release 9 (DR9), which significantly increase sample size stars. In this paper, we used machine learning algorithms to search from LAMOST. We have applied Light Gradient Boosting Machine (LGBM) algorithm build classifiers based on different features, and predictors determining [Ba/Fe] [Sr/Fe] candidates. classification with features in whole spectrum performs best: strontium enhancement, Precision = 97.81%, Recall 96.05%; 96.03% 97.70%. prediction, estimated BaII line at 4554 \r{A} smaller dispersion 4934 \r{A}: MAE$_{4554 \r{A}}$ 0.07, $\sigma_{4554 0.12. SrII 4077 better 4215 MAE$_{4077 0.09, $\sigma_{4077 0.16. A comparison LGBM other popular shows is accurate efficient classifying This work demonstrated be as an effective means identify determine their elemental abundance.