Comparison of Machine-learning and Bayesian Inferences for the Interior of Rocky Exoplanets with Large Compositional Diversity

Abstract

In previous work, we demonstrated that machine-learning techniques based on mixture density networks (MDNs) are successful in inferring the interior structure of rocky exoplanets with large compositional diversity. In this study, we compare the performance of a well-trained MDN model with the conventional Bayesian inversion method based on the Markov chain Monte Carlo (MCMC) method, under the same observable constraints. Considering that MCMC inversion is generally performed with the prior knowledge of planetary mass, radius, and bulk molar ratios of Fe/Mg and Si/Mg, we regenerate a substantial data set of interior structure data for rocky exoplanets and train a new MDN model with inputs of planetary mass, radius, Fe/Mg, and Si/Mg. It has been found that the well-trained MDN model has comparable performance to that of the MCMC method but requires significantly less computation time. The MDN model presents a practical alternative to the traditional MCMC method, surpassing the latter with minimal requirements for specialized knowledge, faster prediction, and greater adaptability. The developed MDN model is made publicly available on GitHub for the broader scientific community’s utilization. With the advent of the James Webb Space Telescope, we are ushering in a new epoch in exoplanetary explorations. In this evolving landscape, the MDN model stands out as a valuable asset, particularly for its ability to rapidly assimilate and interpret new data, thereby substantially advancing our understanding of the interior and habitability of exoplanetary systems.