The study of Active Galactic Nuclei (AGN) is important to further our understanding of galaxy evolution, and thus, reliable and accurate methods for the identification of AGN are crucial. With the unprecedented sensitivity of the James Webb Space Telescope (JWST), and in particular, the Mid-Infrared Instrument (MIRI), more reliable and sensitive classification techniques are needed. Traditional methods for AGN classification include color selection techniques and model fitting, but the former suffers from minimal use of available information (≤ 4 passbands), and the latter is dependent on the accuracy of existing models. We propose to improve existing color selection techniques with an ensemble-based novelty detection network, using existing catalogs of JWST MIRI galaxies for training and testing. This work will result in a publicly-available library of code that will allow for more accurate AGN identification in JWST MIRI galaxies.
|Type of contribution||Oral contribution (20 minutes)|