EclipseNETs: Learning Irregular Small Celestial Body Silhouettes

2025-04-06

AI Summary

To address the need for high-precision, real-time prediction of solar eclipses and occultations near irregular small bodies (e.g., Bennu, Itokawa, 67P, Eros), this paper proposes an end-to-end, indirect learning framework integrating neural implicit representations with neural ordinary differential equations (Neural ODEs). The method requires no prior shape model and jointly optimizes both the geometric representation of the body and occultation timing predictions solely from sparse spacecraft trajectory data. It supports online continual learning and accelerated inference. Evaluated on four representative small bodies, it achieves prediction accuracy comparable to conventional ray-tracing methods while accelerating inference by two to three orders of magnitude. The core contribution is the first application of Neural ODEs to occultation modeling—enabling a differentiable, optimizable, and lightweight implicit representation that tightly couples geometry and dynamics.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Neuro-Symbolic Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurately predicting eclipse events around irregular small bodies is crucial for spacecraft navigation, orbit determination, and spacecraft systems management. This paper introduces a novel approach leveraging neural implicit representations to model eclipse conditions efficiently and reliably. We propose neural network architectures that capture the complex silhouettes of asteroids and comets with high precision. Tested on four well-characterized bodies - Bennu, Itokawa, 67P/Churyumov-Gerasimenko, and Eros - our method achieves accuracy comparable to traditional ray-tracing techniques while offering orders of magnitude faster performance. Additionally, we develop an indirect learning framework that trains these models directly from sparse trajectory data using Neural Ordinary Differential Equations, removing the requirement to have prior knowledge of an accurate shape model. This approach allows for the continuous refinement of eclipse predictions, progressively reducing errors and improving accuracy as new trajectory data is incorporated.

Problem

• Accurately predict eclipse events around irregular small celestial bodies
• Model eclipse conditions efficiently using neural implicit representations
• Train models from sparse trajectory data without prior shape knowledge

Innovation

• Neural implicit representations for eclipse modeling
• High-precision neural network asteroid silhouettes
• Indirect learning from sparse trajectory data