Predictions of exoplanet hosts & abundances

While the connection between a star's iron (Fe) abundance and the presence of giant exoplanets is established, the relationship with small planets remains unclear. The elements Mg, Si, and Fe are important in forming small planets.

Employing machine learning algorithms like XGBoost, trained on the abundances (e.g., the Hypatia Catalog) of known exoplanet-hosting stars (NASA Exoplanet Archive), allows us to determine significant "features" (abundances or molar ratios) that may indicate the presence of small planets. We test on three groups of exoplanets: (1) all small, R_P_<3.5R_{Earth}_; (2) sub-Neptunes, 2.0R_{Earth}_<R_P_<3.5R_{Earth}_; and (3) super-Earths, 1.0R_{Earth}_<R_P_<2.0R_{Earth}_ - each subdivided into seven ensembles to test different combinations of features.