Confidence-Based Fusion of AC-LSTM and Kalman Filter for Accurate Space Target Trajectory Prediction
The accurate prediction of space target trajectories is critical for aerospace defense and space situational awareness, yet it remains challenging due to complex nonlinear dynamics, measurement noise, and environmental uncertainties. This study proposes a confidence-based dual-model fusion framework...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/12/4/347 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850183748690116608 |
|---|---|
| author | Caiyun Wang Jirui Zhang Jianing Wang Yida Wu |
| author_facet | Caiyun Wang Jirui Zhang Jianing Wang Yida Wu |
| author_sort | Caiyun Wang |
| collection | DOAJ |
| description | The accurate prediction of space target trajectories is critical for aerospace defense and space situational awareness, yet it remains challenging due to complex nonlinear dynamics, measurement noise, and environmental uncertainties. This study proposes a confidence-based dual-model fusion framework that separately processes linear and nonlinear trajectory components to enhance prediction accuracy and robustness. The Attention-Based Convolutional Long Short-Term Memory (AC-LSTM) network is designed to capture nonlinear motion patterns by leveraging temporal attention mechanisms and convolutional layers while also estimating confidence levels via a signal-to-noise ratio (SNR)-based multitask learning approach. In parallel, the Kalman Filter (KF) efficiently models quasi-linear motion components, dynamically estimating its confidence through real-time residual monitoring. A confidence-weighted fusion mechanism adaptively integrates the predictions from both models, significantly improving overall prediction performance. Experimental results on simulated radar-based noisy trajectory data demonstrate that the proposed method outperforms conventional algorithms, offering superior precision and robustness. This approach holds great potential for applications in pace situational awareness, orbital object tracking, and space trajectory prediction. |
| format | Article |
| id | doaj-art-e6e916a3b68a4ecc8b8f0c583c085bd3 |
| institution | OA Journals |
| issn | 2226-4310 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj-art-e6e916a3b68a4ecc8b8f0c583c085bd32025-08-20T02:17:14ZengMDPI AGAerospace2226-43102025-04-0112434710.3390/aerospace12040347Confidence-Based Fusion of AC-LSTM and Kalman Filter for Accurate Space Target Trajectory PredictionCaiyun Wang0Jirui Zhang1Jianing Wang2Yida Wu3Department of Optoelectronic Information, School of Aerospace, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaDepartment of Optoelectronic Information, School of Aerospace, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaBeijing Institute of Electronic System Engineering, Beijing 100854, ChinaDepartment of Optoelectronic Information, School of Aerospace, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaThe accurate prediction of space target trajectories is critical for aerospace defense and space situational awareness, yet it remains challenging due to complex nonlinear dynamics, measurement noise, and environmental uncertainties. This study proposes a confidence-based dual-model fusion framework that separately processes linear and nonlinear trajectory components to enhance prediction accuracy and robustness. The Attention-Based Convolutional Long Short-Term Memory (AC-LSTM) network is designed to capture nonlinear motion patterns by leveraging temporal attention mechanisms and convolutional layers while also estimating confidence levels via a signal-to-noise ratio (SNR)-based multitask learning approach. In parallel, the Kalman Filter (KF) efficiently models quasi-linear motion components, dynamically estimating its confidence through real-time residual monitoring. A confidence-weighted fusion mechanism adaptively integrates the predictions from both models, significantly improving overall prediction performance. Experimental results on simulated radar-based noisy trajectory data demonstrate that the proposed method outperforms conventional algorithms, offering superior precision and robustness. This approach holds great potential for applications in pace situational awareness, orbital object tracking, and space trajectory prediction.https://www.mdpi.com/2226-4310/12/4/347neuralnetworksspace targettrajectory predictionKalman filtersradar dataconfidence |
| spellingShingle | Caiyun Wang Jirui Zhang Jianing Wang Yida Wu Confidence-Based Fusion of AC-LSTM and Kalman Filter for Accurate Space Target Trajectory Prediction Aerospace neuralnetworks space target trajectory prediction Kalman filters radar data confidence |
| title | Confidence-Based Fusion of AC-LSTM and Kalman Filter for Accurate Space Target Trajectory Prediction |
| title_full | Confidence-Based Fusion of AC-LSTM and Kalman Filter for Accurate Space Target Trajectory Prediction |
| title_fullStr | Confidence-Based Fusion of AC-LSTM and Kalman Filter for Accurate Space Target Trajectory Prediction |
| title_full_unstemmed | Confidence-Based Fusion of AC-LSTM and Kalman Filter for Accurate Space Target Trajectory Prediction |
| title_short | Confidence-Based Fusion of AC-LSTM and Kalman Filter for Accurate Space Target Trajectory Prediction |
| title_sort | confidence based fusion of ac lstm and kalman filter for accurate space target trajectory prediction |
| topic | neuralnetworks space target trajectory prediction Kalman filters radar data confidence |
| url | https://www.mdpi.com/2226-4310/12/4/347 |
| work_keys_str_mv | AT caiyunwang confidencebasedfusionofaclstmandkalmanfilterforaccuratespacetargettrajectoryprediction AT jiruizhang confidencebasedfusionofaclstmandkalmanfilterforaccuratespacetargettrajectoryprediction AT jianingwang confidencebasedfusionofaclstmandkalmanfilterforaccuratespacetargettrajectoryprediction AT yidawu confidencebasedfusionofaclstmandkalmanfilterforaccuratespacetargettrajectoryprediction |