Discovering Extragalactic Supermassive Black Holes with Multiwavelength Data Analysis

Differentiating extragalactic and galactic sources of light allows for the identification of supermassive black holes for further study. Using the newest X-ray dataset from eROSITA, a machine learning approach helps classify extragalactic and galactic sources. It was found that a Gaussian Mixture Model was effective at this classification, achieving a silhouette score of 0.84. This result shows that a Gaussian Mixture Model is suitable for tasks like this, working toward discovering more supermassive black holes.