Kinematic Evidence of an Embedded Protoplanet in HD 142666 Identified by Machine Learning

Abstract Observations of protoplanetary disks have shown that forming exoplanets leave characteristic imprints on the gas and dust disk. In gas, these cause deviations from Keplerian motion, which can be detected through molecular line observations. Our previous work has machine learning correctly determine if a planet is present in disks. Using our machine-learning models, we identify strong, localized non-Keplerian motion within disk HD 142666. Subsequent hydrodynamics simulations system with 5 M J at 75 au recreate kinematic structure. By currently established standards field, conclude 142666 hosts planet. This represents first step toward using to previously overlooked features