Deriving the stellar labels of LAMOST spectra with Stellar LAbel Machine (SLAM)

TL;DR

This paper introduces SLAM, a support vector regression-based method for deriving stellar labels from LAMOST spectra, demonstrating high accuracy across various spectral types and providing a large catalog of stellar parameters.

Contribution

SLAM is a novel data-driven approach using SVR that effectively models non-linear spectral features, enabling accurate stellar label extraction over a wide range of spectral types.

Findings

Achieves 50 K accuracy in Teff at high SNR

Provides stellar labels for 1 million LAMOST K giants

Performs comparably to state-of-the-art data-driven models

Abstract

The LAMOST survey has provided 9 million spectra in its Data Release 5 (DR5) at R$\sim$1800. Extracting precise stellar labels is crucial for such a large sample. In this paper, we report the implementation of the Stellar LAbel Machine (SLAM), which is a data-driven method based on Support Vector Regression (SVR), a robust non-linear regression technique. Thanks to the capability to model highly non-linear problems with SVR, SLAM generally can derive stellar labels over a wide range of spectral types. This gives it a unique capability compared to other popular data-driven methods. To illustrate this capability, we test the performance of SLAM on stars ranging from Teff$\sim$4000 to $\sim$8000 K trained on LAMOST spectra and stellar labels. At g-band signal-to-noise ratio (SNRg) higher than 100, the random uncertainties of Teff, logg and [Fe/H] are 50 K, 0.09 dex, and 0.07 dex, respectively. We then set up another SLAM model trained by APOGEE and LAMOST common stars to demonstrate its capability of dealing with high dimensional problems. The spectra are from LAMOST DR5 and the stellar labels of the training set are from APOGEE DR15, including Teff, logg, [M/H],[$\alpha$/M], [C/M], and [N/M]. The cross-validated scatters at SNRg$\sim$100 are 49 K, 0.10 dex, 0.037 dex,0.026 dex, 0.058 dex, and 0.106 dex for these parameters, respectively. This performance is at the same level as other up-to-date data-driven models. As a byproduct, we also provide the latest catalog of $\sim$1 million LAMOST DR5 K giant stars with SLAM-predicted stellar labels in this work.