I created a catalogue of star clusters in the Milky Way using multiple machine learning methods to analyse 729 million sources from Gaia DR3. Here's how!
Over a dozen papers have reported new discoveries of open clusters in Gaia data at the time of writing, in less than three years since the release of Gaia DR2. At the core of all papers in this field are clustering algorithms. But which is best at recovering them in Gaia data?