Using Deep Neural Networks to compute the mass of forming planets

Abstract

Computing the mass of planetary envelopes and the critical mass beyond which planets accrete gas in a runaway fashion is important when studying planet formation, in particular for planets up to the Neptune mass range. This computation requires in principle solving a set of differential equations, the internal structure equations, for some boundary conditions (pressure, temperature in the protoplanetary disk where a planet forms, core mass and accretion rate of solids by the planet). Solving these equations in turn proves being time consuming and sometimes numerically unstable. We developed a method to approximate the result of integrating the internal structure equations for a variety of boundary conditions. We compute a set of planet internal structures for a very large number (millions) of boundary conditions, considering two opacities,(ISM and reduced). This database is then used to train Deep Neural Networks in order to predict the critical core mass as well as the mass of planetary envelopes as a function of the boundary conditions. We show that our neural networks provide a very good approximation (at the level of percents) of the result obtained by solving interior structure equations, but with a much smaller required computer time. The difference with the real solution is much smaller than the one obtained using some analytical formulas available in the literature which at best only provide the correct order of magnitude. We compare the results of the DNN with other popular machine learning methods (Random Forest, Gradient Boost, Support Vector Regression) and show that the DNN outperforms these methods by a factor of at least two. We show that some analytical formulas that can be found in various papers can severely overestimate the mass of planets, therefore predicting the formation of planets in the Jupiter-mass regime instead of the Neptune-mass regime.

accepted in A&A. Animations visible at http://nccr-planets.ch/research/phase2/domain2/project5/machine-learning-and-advanced-statistical-analysis/ and code available at https://github.com/yalibert/DNN_internal_structure

References in corpus (8)

• Formation of Jupiter using opacities based on detailed grain physics
• Planet formation with envelope enrichment: new insights on planetary diversity
• Searching for Exoplanets Using Artificial Intelligence
• Grain opacity and the bulk composition of extrasolar planets. II. An analytical model for the grain opacity in protoplanetary atmospheres
• Critical core mass for enriched envelopes: the role of H2O condensation
• A Machine Learns to Predict the Stability of Tightly Packed Planetary Systems
• The formation of mini-Neptunes
• A new metric to quantify the similarity between planetary systems - application to dimensionality reduction using T-SNE

Cited by in corpus (10)

• Six transiting planets and a chain of Laplace resonances in TOI-178
• A fading radius valley towards M-dwarfs, a persistent density valley across stellar types
• Machine learning inference of the interior structure of low-mass exoplanets
• ExoMDN: Rapid characterization of exoplanet interior structures with Mixture Density Networks
• Planetary Population Synthesis and the Emergence of Four Classes of Planetary System Architectures
• Unveiling the internal structure and formation history of the three planets transiting HIP 29442 (TOI-469) with CHEOPS
• Possible Atmospheric Diversity of Low Mass Exoplanets, some Central Aspects
• A Machine Learning model to infer planet masses from gaps observed in protoplanetary disks
• A proof-of-concept neural network for inferring parameters of a black hole from partial interferometric images of its shadow
• The PAIRS project: a global formation model for planets in binaries. I. Effect of disc truncation on the growth of S-type planets