Investigation of the Robustness of Neural Density Fields

by   Jonas Schuhmacher, et al.

Recent advances in modeling density distributions, so-called neural density fields, can accurately describe the density distribution of celestial bodies without, e.g., requiring a shape model - properties of great advantage when designing trajectories close to these bodies. Previous work introduced this approach, but several open questions remained. This work investigates neural density fields and their relative errors in the context of robustness to external factors like noise or constraints during training, like the maximal available gravity signal strength due to a certain distance exemplified for 433 Eros and 67P/Churyumov-Gerasimenko. It is found that both models trained on a polyhedral and mascon ground truth perform similarly, indicating that the ground truth is not the accuracy bottleneck. The impact of solar radiation pressure on a typical probe affects training neglectable, with the relative error being of the same magnitude as without noise. However, limiting the precision of measurement data by applying Gaussian noise hurts the obtainable precision. Further, pretraining is shown as practical in order to speed up network training. Hence, this work demonstrates that training neural networks for the gravity inversion problem is appropriate as long as the gravity signal is distinguishable from noise. Code and results are available at


page 5

page 8

page 10

page 11

page 12


Optic Disc Segmentation using Disk-Centered Patch Augmentation

The optic disc is a crucial diagnostic feature in the eye since changes ...

Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images

Image noise modeling is a long-standing problem with many applications i...

DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation

Despite the recent advances in open-domain dialogue systems, building a ...

Neural Density-Distance Fields

The success of neural fields for 3D vision tasks is now indisputable. Fo...

Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps

We investigate the role of various demonstration components in the in-co...

Geodesy of irregular small bodies via neural density fields: geodesyNets

We present a novel approach based on artificial neural networks, so-call...

Randomness In Neural Network Training: Characterizing The Impact of Tooling

The quest for determinism in machine learning has disproportionately foc...

Please sign up or login with your details

Forgot password? Click here to reset