2026-10-14T14:39:35Z https://www.scidb.cn/oai

10.57760/sciencedb.space.03584 2026-05-21T11:25:23Z

2026-05-21 Research on Space Object Orbit Prediction Based on a BiLSTM Neural Network doi:10.57760/sciencedb.space.03584 en Accurate orbit prediction is crucial for ensuring the reliability and practical value of Space Situational Awareness (SSA). To reduce the high modeling cost and limited adaptability of traditional dynamics-based orbit prediction methods, this paper proposes a bidirectional Long Short-Term Memory (BiLSTM)-based Simplified General Perturbations 4 residual correction method. The model adopts an enhanced long short-term memory architecture with independent forget gates and input gates to improve the capture of long-term temporal dependencies. Axis-wise position residuals, velocity components, and the right ascension of the ascending node are selected as input features for orbit prediction. The proposed model was evaluated using HY-2B and WESTPAC as the main low Earth orbit test cases, with Beidou3m1 used as an additional satellite at a higher orbital altitude. Compared with the backpropagation model, the BiLSTM model generally achieved lower root mean square error and mean absolute error values, although the magnitude of improvement varied across satellites and coordinate axes. For example, for HY-2B, the root mean square error and mean absolute error along the Y-axis decreased from 72.120 m and 65.571 m to 17.019 m and 10.274 m, respectively. The additional Beidou3m1 experiment further indicates that the proposed framework can be applied to satellites with different orbital characteristics. These results suggest that BiLSTM-based temporal modeling is effective for Simplified General Perturbations 4 residual correction and can improve the accuracy of data-driven orbit prediction. Space Situational Awareness; Orbit Prediction; Bidirectional Long Short-Term Memory; low Earth orbit yang tao PUBLIC https://creativecommons.org/licenses/by-nc-nd/4.0/ dataset http://www.doi.org/10.1016/j.jsse.2026.06.002 Science Data Bank