Mass and Age determination of the LAMOST data with different Machine Learning methods

TL;DR

This paper develops machine learning models to accurately estimate stellar mass and age from LAMOST data, creating large catalogs with high precision, and compares various algorithms to identify the most effective methods.

Contribution

It introduces a new large-scale catalog of stellar masses and ages using multiple machine learning techniques, demonstrating the effectiveness of nonlinear models like GBDT and RF.

Findings

Median relative error for mass prediction is 3% for large samples.

Red clump star age uncertainty reaches 18%.

Nonlinear models outperform linear ones, with GBDT and RF being the best.

Abstract

We present a catalog of 948,216 stars with mass label and a catalog of 163,105 red clump (RC) stars with mass and age labels simultaneously. The training dataset is cross matched from the LAMOST (The Large Sky Area Multi-Object Fiber Spectroscopic Telescope) DR5 and high resolution asteroseismology data, mass and age are predicted by random forest method or convex hull algorithm. The stellar parameters with high correlation with mass and age are extracted and the test dataset shows that the median relative error of the prediction model for the mass of large sample is 3\% and meanwhile, the mass and age of red clump stars are 4\% and 7\%. We also compare the predicted age of red clump stars with the recent works and find that the final uncertainty of the RC sample could reach 18\% for age and 9\% for mass, in the meantime, final precision of the mass for large sample with different type of stars could reach 13\% without considering systematics, all these are implying that this method could be widely used in the future. Moreover, we explore the performance of different machine learning methods for our sample, including bayesian linear regression (BYS), gradient boosting decision Tree (GBDT), multilayer perceptron (MLP), multiple linear regression (MLR), random forest (RF) and support vector regression (SVR). Finally we find that the performance of nonlinear model is generally better than that of linear model, and the GBDT and RF methods are relatively better.