摘要
Accurate measurements of statistical properties, such as the star formation rate and the lifetime of young stellar objects (YSOs) in different stages, are essential for constraining star formation theories. However, it is a difficult task to separate galaxies and YSOs based on spectral energy distributions (SEDs) alone, because they contain both thermal emission from stars and dust around them and no reliable theories can be applied to distinguish them. Here we compare different machine learning algorithms and develop the Spectrum Classifier of Astronomical Objects (SCAO), based on Fully Connected Neural Network (FCN), to classify regular stars, galaxies, and YSOs. Superior to previous classifiers, SCAO is solely trained by high quality data labeled in Molecular Cores to Planet-forming Disks (c2d) catalog without a priori theoretical knowledge, and provides excellent results with high precision (>96%) and recall (>98%) for YSOs when only eight bands are included. We systematically investigate the effects of observation errors and distance effects, and show that high accuracy performance is still maintained even when using fluxes of only three bands (IRAC 3, a=IRAC 4, and MIPS 1) in the long wavelengths regime, because the silicate absorption feature is automatically detected by SCAO. Finally, we applied SCAO to Spitzer Enhanced Imaging Products (SEIP), the most complete catalog of Spitzer observations, and found 129219 YSO candidates. The website from SCAO is available at http://scao.astr.nthu.edu.tw.