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.

arXiv commentaccepted 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 (24)

• Towards a Deterministic Model of Planetary Formation I: a Desert in the Mass and Semi Major Axis Distributions of Extra Solar Planets
• Using FU Orionis Outbursts to Constrain Self-Regulated Protostellar Disk Models
• Models of Giant Planet formation with migration and disc evolution
• The effect of gas drag on the growth of protoplanets -- Analytical expressions for the accretion of small bodies in laminar disks
• Extrasolar planet population synthesis I: Method, formation tracks and mass-distance distribution
• Gaseous Mean Opacities for Giant Planet and Ultracool Dwarf Atmospheres over a Range of Metallicities and Temperatures
• Models of Jupiter's Growth Incorporating Thermal and Hydrodynamic Constraints
• To Cool is to Accrete: Analytic Scalings for Nebular Accretion of Planetary Atmospheres
• Critical Protoplanetary Core Masses in Protoplanetary Disks and the Formation of Short-Period Giant Planets
• On the Minimum Core Mass for Giant Planet Formation at Wide Separations
• Formation of Jupiter using opacities based on detailed grain physics
• Theoretical models of planetary system formation: mass vs semi-major axis
• Planet formation with envelope enrichment: new insights on planetary diversity
• Planet formation models: the interplay with the planetesimal disc
• 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
• On the radius of habitable planets
• A Machine Learns to Predict the Stability of Tightly Packed Planetary Systems
• The formation of mini-Neptunes
• A machine learns to predict the stability of circumbinary planets
• Supervised detection of exoplanets in high-contrast imaging sequences
• Metallicity effect and planet mass function in pebble-based planet formation models
• A new metric to quantify the similarity between planetary systems - application to dimensionality reduction using T-SNE

Cited by in corpus (16)

• The Nature of the Radius Valley: Hints from Formation and Evolution Models
• Six transiting planets and a chain of Laplace resonances in TOI-178
• The New Generation Planetary Population Synthesis (NGPPS). I. Bern global model of planet formation and evolution, model tests, and emerging planetary systems
• The New Generation Planetary Population Synthesis (NGPPS). III. Warm super-Earths and cold Jupiters: A weak occurrence correlation, but with a strong architecture-composition link
• 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
• Exoplanet Characterization using Conditional Invertible Neural Networks
• 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
• PGNets: Planet mass prediction using convolutional neural networks for radio continuum observations of protoplanetary disks
• 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
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods