BDS-3 Satellite Orbit Prediction Method Based on Ensemble Learning and Neural Networks

To address uncertainties in satellite orbit error prediction, this study proposes a novel ensemble learning-based orbit prediction method specifically designed for the BeiDou navigation satellite system (BDS). Building on ephemeris data and perturbation corrections, two new models are proposed: attention-enhanced BPNN (AEBP) and Transformer-ResNet-BiLSTM (TR-BiLSTM). These models effectively capture both local and global dependencies in satellite orbit data. To further enhance prediction accuracy and stability, the outputs of these two models were integrated using the gradient boosting decision tree (GBDT) ensemble learning method, which was optimized through a grid search. The main contribution of this approach is the synergistic combination of deep learning models and GBDT, which significantly improves both the accuracy and robustness of satellite orbit predictions. This model was validated using broadcast ephemeris data from the BDS-3 MEO and inclined geosynchronous orbit (IGSO) satellites. The results show that the proposed method achieves an error correction rate of 65.4%. This ensemble learning-based approach offers a highly effective solution for high-precision and stable satellite orbit predictions.