AI Unearths Milky Way's Birth Stars.
Astronomers have used machine learning to discover a trove of ancient stars that preceded the Milky Way, shedding light on the galaxy's formation and disk galaxies in general. The stars were found using data from the European Space Agency's Gaia space telescope, and the team used an off-the-shelf algorithm called XGBoost to extract the signals of heavier elements from the low-resolution spectra. The discovery confirms that the Milky Way was preceded by a proto-galaxy, and suggests that it didn't steal stars from other galaxies. The findings also confirm a recent theory about the timeline for the Milky Way's disk formation.