Using Deep Learning neural networks to predict the interior composition of exoplanets

Abstract

One of the main goals in exoplanetary science is the interior characterization of observed exoplanets. A common approach to characterize the interior of a known exoplanet is the use of numerical models to compute an interior structure which complies with the measured mass and radius of the planet (Sotin et al. 2017, Seager et al. 2007). With only these two observables, possible solutions tend to be highly degenerate, with multiple, qualitatively different interior compositions that can match the observations equally well. Other potential observables include the Love number k2 (bearing information on the mass concentration in the interior of the planet), and the elemental abundances of the host star, which may be representative of those of the planet. We explore the application of a deep learning neural network to the interior characterization of exoplanets. We employ a simple 1D structure model to construct a large training set of sub-Neptunian exoplanets up to 20 Earth-masses. A model planet consists of five layers: an iron-rich core, a lower and upper silicate mantle, a water ice layer, and a gaseous H/He envelope. The size of each layer is constrained by prescribed mass fractions. Using a feedforward neural network trained on a large dataset of such modelled planets, we show that we can reasonably well predict the original model input parameters (core, mantle, ice layer and atmosphere mass fractions) from just mass, radius and the fluid Love number k2.