DSC (Discrete Source Classifier)
The Discrete Source Classifier (DSC) is the two top-level classification modules in CU8. DSC is responsible for classifying sources using supervised machine learning techniques. The output is probabilistic and divides the sources into broad astrophysical classes (single stars, white dwarfs, binaries, galaxies and quasars).
DSC comprises two classification modules. The first, Specmod, uses the Gaia BP/RP spectra and is based on ExtraTrees. The second, Allosmod, uses several features defined from the Gaia photometry and astrometry and uses Gaussian Mixture Modules. The results from these are also combined probabilistically into an overall classification probability (Combmod).