Exoplanet characterization across the mass-radius space using machine learning

Characterizing the internal composition of exoplanets is an essential part in understanding the diversity of observed exoplanets and the processes that govern their formation and evolution. However, the interior of an exoplanet is inaccessible to observations, and can only be investigated via numerical structure models. Furthermore, interior models are inherently non-unique, because the large number of unknown parameters outweigh the limited amount of observables. One set of observable parameters can correspond to a multitude of possible planet interiors.

Probabilistic inference methods, such as Markov chain Monte Carlo sampling, are a common, but computationally intensive and time-consuming tool to solve this inverse problem and obtain a comprehensive picture of possible planetary interiors, while also taking into account observational uncertainties. This prohibits large-scale characterization of exoplanet populations.

We explore here an alternative approach to interior characterization utilizing ExoMDN, a stand-alone machine-learning model based on mixture density networks (MDNs) that is capable of providing a full probabilistic inference of exoplanet interiors in under a second, without the need for extensive modeling of each exoplanet's interior or even a dedicated interior model. ExoMDN is trained on a large database of 5.6 million precomputed, synthetic interior structures of low mass exoplanets. 

The fast prediction times allow investigations into planetary interiors which were not feasible before. We demonstrate how ExoMDN can be leveraged to perform large-scale interior characterizations across the entire population of low-mass exoplanets. We can show how ExoMDN can be used to comprehensively quantify the effect of measurement uncertainties on the ability to constrain the interior of a planet, and to which accuracy these parameters need to be measured to well characterize a planet’s interior.