Improved Orbit Prediction Method Based on Two-Line Elements with Dynamic Loss Function

EasyChair Preprint 15676

Abstract

Accurate orbit prediction is crucial for space situational awareness. However, Physics-based approaches can fail to achieve the required accuracy for collision avoidance of Resident Space Objects (RSOs). This paper presents a Machine Learning-based approach for RSOs orbit prediction leveraging Two-Line Elements (TLE). Taking the dynamic nature of orbital deviations into consideration, we integrate a dynamic loss function into the orbit prediction framework, allowing for a more adaptive and accurate prediction model. The experiments demonstrate the superior performance of our proposed method in predicting RSOs orbits over extended periods.

Keyphrases: Convolutional Neural Networks, Dynamic Loss Function, Long Short Term Memory., Orbit Prediction, space objects

@booklet{EasyChair:15676,
  author    = {Wenxin Li and Yanfang Tao and Hao Deng},
  title     = {Improved Orbit Prediction Method Based on Two-Line Elements with Dynamic Loss Function},
  howpublished = {EasyChair Preprint 15676},
  year      = {EasyChair, 2025}}