Deriving the Stellar Labels of LAMOST Spectra with the Stellar LAbel Machine (SLAM)

The LAMOST survey has provided 9 million spectra in its Data Release 5 (DR5) at R similar to 1800. Extracting precise stellar labels is crucial for such a large sample. In this paper, we report the implementation of the Stellar LAbel Machine (SLAM), which is a data-driven method based on support vector regression (SVR), a robust nonlinear regression technique. Thanks to the capability to model highly nonlinear problems with SVR, SLAM can generally derive stellar labels over a wide range of spectral types. This gives it a unique capability compared to other popular data-driven methods. To illustrate this capability, we test the performance of SLAM on stars ranging from T-eff similar to 4000 to similar to 8000 K trained on LAMOST spectra and stellar labels. At g-band signal-to-noise ratio (S/N-g) higher than 100, the random uncertainties of T-eff, log g, and [Fe/H] are 50 K, 0.09 dex, and 0.07 dex, respectively. We then set up another SLAM model trained by APOGEE and LAMOST common stars to demonstrate its capability of dealing with high dimensional problems. The spectra are from LAMOST DR5 and the stellar labels of the training set are from APOGEE DR15, including T-eff, log g, [M/H], [alpha/M], [C/M], and [N/M]. The cross-validated scatters at