Geodesy of irregular small bodies via neural density fields

Abstract

Asteroids’ and comets’ geodesy is a challenging yet important task for planetary science and spacecraft operations, such as ESA’s Hera mission tasked to look at the aftermath of the recent NASA DART spacecraft’s impact on Dimorphos. Here we present a machine learning approach based on so-called geodesyNets which learns accurate density models of irregular bodies using minimal prior information. geodesyNets are a three-dimensional, differentiable function representing the density of a target irregular body. We investigate six different bodies, including the asteroids Bennu, Eros, and Itokawa and the comet Churyumov-Gerasimenko, and validate on heterogeneous and homogeneous ground-truth density distributions. Induced gravitational accelerations and inferred body shape are accurate, resulting in a relative acceleration error of less than 1%, also close to the surface. With a shape model, geodesyNets can even learn heterogeneous density fields and thus provide insight into the body’s internal structure. This adds a powerful tool to consolidated approaches like spherical harmonics, mascon models, and polyhedral gravity.

Efficient Polyhedral Gravity Modeling in Modern C++ and Python

“…Further, it has been used to study the effectiveness of so-called neural density fields (Izzo & Gómez, 2022), where it served as ground truth to (pre-)train neural networks representing the density distribution of an arbitrarily shaped body (Schuhmacher et al, 2023).…”

Small celestial body exploration with CubeSat Swarms

“…The swarm's objective is to capture gravity signal around the body to assess its mass distribution at a later stage following the procedure described in the geodesyNETs project. [4] The swarm CubeSats will have to orbit around the body without colliding with each other, staying within a spherical region defined by a minimum safety radius to the body's center of mass and a maximum radius of operations. These operations will have to be performed with minimum ΔV budget requirements.…”

“…The mascon models used for this study were developed in the geodesyNETs project. [4] The dynamics of the swarm around the spacecraft are simulated via cascade simulations making use of the heyoka high-performance Taylor integrator. The equations of motion are represented by a gravitational N-body problem where N is the number of mascons, plus the solar radiation pressure integrated in an inertial reference frame and consider a rotating celestial body.…”

Reinforcement Learning and Orbit-Discovery Enhanced by Small-Body Physics-Informed Neural Network Gravity Models

“…For GeodesyNets [29], SIRENs of 9 hidden layers with 100 nodes each are used (9*100 2 = 90,000). Four asteroids are studied: Bennu, Churyumov-Gerasimenko, Eros, and Itokawa.…”