NeuralCMS: A deep learning approach to study Jupiter's interior

Abstract

NASA's Juno mission provided exquisite measurements of Jupiter's gravity field that together with the Galileo entry probe atmospheric measurements constrains the interior structure of the giant planet. Inferring its interior structure range remains a challenging inverse problem requiring a computationally intensive search of combinations of various planetary properties, such as the cloud-level temperature, composition, and core features, requiring the computation of ~10^9 interior models. We propose an efficient deep neural network (DNN) model to generate high-precision wide-ranged interior models based on the very accurate but computationally demanding concentric MacLaurin spheroid (CMS) method. We trained a sharing-based DNN with a large set of CMS results for a four-layer interior model of Jupiter, including a dilute core, to accurately predict the gravity moments and mass, given a combination of interior features. We evaluated the performance of the trained DNN (NeuralCMS) to inspect its predictive limitations. NeuralCMS shows very good performance in predicting the gravity moments, with errors comparable with the uncertainty due to differential rotation, and a very accurate mass prediction. This allowed us to perform a broad parameter space search by computing only ~10^4 actual CMS interior models, resulting in a large sample of plausible interior structures, and reducing the computation time by a factor of 10^5. Moreover, we used a DNN explainability algorithm to analyze the impact of the parameters setting the interior model on the predicted observables, providing information on their nonlinear relation.

8 pages, 6 figures, 4 tables, accepted for publication in A&A

References in corpus (20)

• CODATA Recommended Values of the Fundamental Physical Constants: 2010
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• New models of Jupiter in the context of Juno and Galileo
• A new equation of state for dense hydrogen-helium mixtures
• The water abundance in Jupiter's equatorial zone
• Concentric Maclaurin spheroid models of rotating liquid planets
• Jupiter internal structure: the effect of different equations of state
• Jupiter's inhomogeneous envelope
• Determining the initial helium abundance of the Sun
• Revelations on Jupiter's Formation, Evolution and Interior: Challenges from Juno Results
• Models of Saturn's Interior Constructed with Accelerated Concentric Maclaurin Spheroid Method
• Jupiter's interior from Juno: Equation-of-state uncertainties and dilute core extent
• Low- and high-order gravitational harmonics of rigidly rotating Jupiter
• Machine learning inference of the interior structure of low-mass exoplanets
• ExoMDN: Rapid characterization of exoplanet interior structures with Mixture Density Networks
• Accounting for non-ideal mixing effects in the hydrogen-helium equation of state
• Saturn's Probable Interior: An Exploration of Saturn's Potential Interior Density Structures
• A complete study of the precision of the concentric MacLaurin spheroid method to calculate Jupiter's gravitational moments
• The Shape of Jupiter and Saturn Based on Atmospheric Dynamics, Radio Occultations and Gravity Measurements
• Study of Jupiter's Interior with Quadratic Monte Carlo Simulations

Cited by in corpus (3)

• Evolution of Semi-convective Staircases in Rotating Flows: Consequences for Fuzzy Cores in Giant Planets
• Characterizing Jupiter's interior using machine learning reveals four key structures
• Dynamical constraints on the vertical structure of Jupiter's polar cyclones