ABSTRACT
Although the collision of space objects not only incurs a high cost but also threatens human life, the risk of collision between satellites has increased, as the number of satellites has rapidly grown due to the significant interests in many space applications. However, it is not trivial to monitor the behavior of the satellite in real-time since the communication between the ground station and spacecraft is dynamic and sparse, and there is an increased latency due to the long distance. Accordingly, it is strongly required to predict the orbit of a satellite to prevent unexpected contingencies such as a collision. Therefore, the real-time monitoring and accurate orbit prediction are required. Furthermore, it is necessary to compress the prediction model, while achieving a high prediction performance in order to be deployable in the real systems. Although several machine learning and deep learning-based prediction approaches have been studied to address such issues, most of them have applied only basic machine learning models for orbit prediction without considering the size, running time, and complexity of the prediction model. In this research, we propose Selective Tensorized multi-layer LSTM (ST-LSTM) for orbit prediction, which not only improves the orbit prediction performance but also compresses the size of the model that can be applied in practical deployable scenarios. To evaluate our model, we use the real orbit dataset collected from the Korea Multi-Purpose Satellites (KOMPSAT-3 and KOMPSAT-3A) of the Korea Aerospace Research Institute (KARI) for 5 years. In addition, we compare our ST-LSTM to other machine learning-based regression models, LSTM, and basic tensorized LSTM models with regard to the prediction performance, model compression rate, and running time.
Supplemental Material
- Lars Buitinck, Gilles Louppe, Mathieu Blondel, Fabian Pedregosa, Andreas Mueller, Olivier Grisel, Vlad Niculae, Peter Prettenhofer, Alexandre Gramfort, Jaques Grobler, Robert Layton, Jake VanderPlas, Arnaud Joly, Brian Holt, and Gaël Varoquaux. 2013. API design for machine learning software: experiences from the scikit-learn project. In ECML PKDD Workshop: Languages for Data Mining and Machine Learning. 108--122.Google Scholar
- Shkelzen Cakaj and Kre?imir Malaric. 2007. Rigorous analysis on performance of LEO satellite ground station in urban environment. International Journal of Satellite Communications and Networking 25, 6 (2007), 619--643.Google ScholarDigital Library
- J Douglas Carroll and Jih-Jie Chang. 1970. Analysis of individual differences in multidimensional scaling via an N-way generalization of "Eckart-Young" decomposition. Psychometrika 35, 3 (1970), 283--319.Google ScholarCross Ref
- Tianqi Chen and Carlos Guestrin. 2016. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Francisco, California, USA) (KDD '16). ACM, New York, NY, USA, 785--794. https://doi.org/10.1145/2939672.2939785Google ScholarDigital Library
- Yuwei Chen and Kaizhi Wang. 2019. Prediction of satellite time series data based on long short term memory-autoregressive integrated moving average model (LSTM-ARIMA). In 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP). IEEE, 308--312.Google ScholarCross Ref
- Lin Cheng, Zhenbo Wang, Fanghua Jiang, and Chengyang Zhou. 2018. Real-time optimal control for spacecraft orbit transfer via multiscale deep neural networks. IEEE Trans. Aerospace Electron. Systems 55, 5 (2018), 2436--2450.Google ScholarCross Ref
- Earthsky. 2020. Who owns all the satellites? https://earthsky.org/space/who-owns-satellites-company-country/Google Scholar
- Albert Garcia, Mohamed Adel Musallam, Vincent Gaudilliere, Enjie Ghorbel, Kassem Al Ismaeil, Marcos Perez, and Djamila Aouada. 2021. Lspnet: A 2d localization-oriented spacecraft pose estimation neural network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2048--2056.Google ScholarCross Ref
- Timur Garipov, Dmitry Podoprikhin, Alexander Novikov, and Dmitry Vetrov. 2016. Ultimate tensorization: compressing convolutional and fc layers alike. arXiv preprint arXiv:1611.03214 (2016).Google Scholar
- KARI. 1989--2022. Korea Aerospace Research Institute. https://www.kari.re.krGoogle Scholar
- Henk AL Kiers. 2000. Towards a standardized notation and terminology in multiway analysis. Journal of Chemometrics: A Journal of the Chemometrics Society 14, 3 (2000), 105--122.Google ScholarCross Ref
- J. B. Kruskal. 1977. Three-way arrays: rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics. Linear Algebra and Its Applications 18, 2 (1977), 95--138.Google ScholarCross Ref
- Rocket Lab. 2006--2022. Rocket Lab USA, Inc. https://www.rocketlabusa.com/Google Scholar
- Byoung-sun Lee, Won-Gil Kim, Junho Lee, and Yoola Hwang. 2018. Machine learning approach to initial orbit determination of unknown LEO satellites. In 2018 SpaceOps Conference. 2566.Google Scholar
- Creon Levit and William Marshall. 2011. Improved orbit predictions using two-line elements. Advances in Space Research 47, 7 (2011), 1107--1115.Google ScholarCross Ref
- Alexander Novikov, Dmitrii Podoprikhin, Anton Osokin, and Dmitry P Vetrov. 2015. Tensorizing neural networks. Advances in neural information processing systems 28 (2015).Google Scholar
- Charles C Onu, Jacob E Miller, and Doina Precup. 2020. A fully tensorized recurrent neural network. arXiv preprint arXiv:2010.04196 (2020).Google Scholar
- Virgin Orbit. 2017--2022. Virgin Orbit. https://virginorbit.com/Google Scholar
- Blue Origin. 2007--2022. Blue Origin, LLC. https://www.blueorigin.com/Google Scholar
- Alaa Osama, Mourad Raafat, Ashraf Darwish, Sara Abdelghafar, and Aboul Ella Hassanien. 2022. Satellite Orbit Prediction Based on Recurrent Neural Network using Two Line Elements. In 2022 5th International Conference on Computing and Informatics (ICCI). IEEE, 298--302.Google ScholarCross Ref
- Ivan V Oseledets. 2011. Tensor-train decomposition. SIAM Journal on Scientific Computing 33, 5 (2011), 2295--2317.Google ScholarDigital Library
- Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, Inc., 8024--8035. http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdfGoogle ScholarDigital Library
- Hao Peng and Xiaoli Bai. 2018. Exploring capability of support vector machine for improving satellite orbit prediction accuracy. Journal of Aerospace Information Systems 15, 6 (2018), 366--381.Google ScholarCross Ref
- Hao Peng and Xiaoli Bai. 2018. Improving orbit prediction accuracy through supervised machine learning. Advances in Space Research 61, 10 (2018), 2628--2646.Google ScholarCross Ref
- Hao Peng and Xiaoli Bai. 2019. Comparative evaluation of three machine learning algorithms on improving orbit prediction accuracy. Astrodynamics 3, 4 (2019), 325--343.Google ScholarCross Ref
- Hao Peng and Xiaoli Bai. 2020. Machine learning approach to improve satellite orbit prediction accuracy using publicly available data. The Journal of the astronautical sciences 67, 2 (2020), 762--793.Google ScholarCross Ref
- Haoli Ren, Xiaolin Chen, Bei Guan, Yongji Wang, Tiantian Liu, and Kongyang Peng. 2019. Research on Satellite Orbit Prediction Based on Neural Network Algorithm. In Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference. 267--273.Google ScholarDigital Library
- Ali Shehadeh, Odey Alshboul, Rabia Emhamed Al Mamlook, and Ola Hamedat. 2021. Machine learning models for predicting the residual value of heavy construction equipment: An evaluation of modified decision tree, LightGBM, and XGBoost regression. Automation in Construction 129 (2021), 103827.Google ScholarCross Ref
- Paul F Smith, Siva Ganesh, and Ping Liu. 2013. A comparison of random forest regression and multiple linear regression for prediction in neuroscience. Journal of neuroscience methods 220, 1 (2013), 85--91.Google ScholarCross Ref
- SpaceX. 2002--2022. Space Exploration Technologies Corp. https://www.spacex.com/Google Scholar
- Ledyard R Tucker. 1963. Implications of factor analysis of three-way matrices for measurement of change. Problems in measuring change 15 (1963), 122--137.Google Scholar
- Ledyard R Tucker. 1964. The extension of factor analysis to three-dimensional matrices. Contributions to mathematical psychology 110119 (1964).Google Scholar
- Ledyard R Tucker. 1966. Some mathematical notes on three-mode factor analysis. Psychometrika 31, 3 (1966), 279--311.Google ScholarCross Ref
- David A Vallado, Paul Crawford, Richard Hujsak, and TS Kelso. 2006. Revisiting spacetrack report# 3. AIAA 6753, 2006 (2006), 446.Google Scholar
- Paul Vergez, Luke Sauter, and Scott Dahlke. 2004. An improved Kaiman filter for satellite orbit predictions. The Journal of the Astronautical Sciences 52, 3 (2004), 359--380.Google ScholarCross Ref
- Zeyi Wen, Jiashuai Shi, Qinbin Li, Bingsheng He, and Jian Chen. 2018. ThunderSVM: A Fast SVM Library on GPUs and CPUs. Journal of Machine Learning Research 19 (2018), 797--801.Google ScholarDigital Library
- Wikipedia. 1989--2022. "Korea Aerospace Research Institute". https://en.wikipedia.org/wiki/Korea_Aerospace_Research_Institute#cite_note-4Google Scholar
- Wikipedia. 2022. "Two-line element set". https://en.wikipedia.org/wiki/Two-line_element_setGoogle Scholar
- Wikipedia. Accessed: 2022-05-01. "Tensor". https://en.wikipedia.org/wiki/Tensor#As_multidimensional_arraysGoogle Scholar
- Yinchong Yang, Denis Krompass, and Volker Tresp. 2017. Tensor-train recurrent neural networks for video classification. In International Conference on Machine Learning. PMLR, 3891--3900.Google Scholar
Index Terms
- Selective Tensorized Multi-layer LSTM for Orbit Prediction
Recommendations
Prediction versus real-time orbit determination for GNSS satellites
To serve real-time users, the IGS (International GNSS Service) provides GPS and GLONASS Ultra-rapid (IGU) orbits with an update of every 6 h. Following similar procedures, we produce Galileo and BeiDou predicted orbits. Comparison with precise orbits ...
Evaluation of GPS orbit prediction strategies for the IGS Ultra-rapid products
The International GNSS Service (IGS) provides Ultra-rapid GPS & GLONASS orbits every 6 h. Each product is composed of 24 h of observed orbits with predicted orbits for the next 24 h. We have studied how the orbit prediction performance varies as a ...
An impact analysis of arc length on orbit prediction and clock estimation for PPP ambiguity resolution
Real-time precise orbit and clock products are crucial for real-time high-precision precise point positioning (PPP). The key for precise orbit prediction is to precisely determine the initial conditions (satellite position, velocity at the initial epoch)...
Comments