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

TL;DR

This paper introduces NeuralCMS, a deep neural network that efficiently models Jupiter's interior structure, significantly reducing computational costs while maintaining high accuracy in predicting gravity moments and interior features.

Contribution

NeuralCMS is a novel deep learning model that approximates the CMS method, enabling rapid exploration of Jupiter's interior models with high precision and interpretability.

Findings

NeuralCMS predicts gravity moments with errors comparable to measurement uncertainties.

The model reduces computation time by a factor of 10^5 compared to traditional methods.

It provides insights into parameter influences on interior structure predictions.

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.