Abstract This paper presents a machine learning (ML) approach that can improve orbit prediction precision and reduce uncertainties with a properly designed fusion strategy. The ML models are trained based on historical TLE sets and then ML-modifications are generated for the future states and uncertainty predictions. The ML-modification is first interpreted as a pseudo-measurement of the true orbit prediction error and then fused with the conventional orbital state and uncertainty propagation result. The regularized particle filter (PF) with progressive correction and systematic sampling is adopted for uncertainty propagation while using the Simplified General Perturbations #4 (SGP4) model. Comprehensive experiments are conducted and analyzed on over 100 resident space objects (RSOs) in different orbit types. The results demonstrate that the fusion strategy enables the ML approach to work with the advanced PF prediction method. The prediction precision can be significantly improved for the majority of the cases. The prediction accuracy is observed to be improved in some cases but without a clear pattern. The results and analysis also suggest that future studies of a monitoring system facilitating the fusion process would be helpful in practical applications.

Highlights • Machine learning (ML) learns from data to improve orbit prediction accuracy. • ML reduces prediction uncertainty of Resident Space Objects (RSOs) in TLE catalog. • A medium-scale ML study over 100 RSOs in the TLE catalog was carried out. • RSOs in SSO, LEO, MEO, GEO can all be improved. • RSOs classified as debris, rocket bodies, or normal satellites can all be improved.