{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T18:26:37Z","timestamp":1787336797694,"version":"build-2736575974"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Major Program of the National Natural Science Foundation of China","award":["Grant No. 62495022 and Project No. 62495020"],"award-info":[{"award-number":["Grant No. 62495022 and Project No. 62495020"]}]},{"name":"Jiangsu Provincial Industry Prospective Technology Research and Development Program","award":["BE2023043"],"award-info":[{"award-number":["BE2023043"]}]},{"name":"Jiangsu Provincial Key Laboratory Funding Project","award":["BM2014006"],"award-info":[{"award-number":["BM2014006"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>To address the strong dependence of space object orbit prediction on physical models and initial conditions, as well as the difficulty of completely eliminating prediction errors, this study proposes a satellite orbit prediction correction method that integrates an attention mechanism with a long short-term memory (LSTM) network. Taking the LAGEOS satellite as the research object, the proposed method uses position error, velocity, and acceleration features extracted from historical orbital data to train a deep learning model for predicting one-day-ahead orbital errors and correcting the SGP4 orbit prediction results. The experimental results show that the ATLSTM model outperforms the LSTM, support vector machine (SVM), back propagation neural network (BP), and bidirectional long short-term memory (BiLSTM) models in both orbital error prediction and correction. The residual ratios of ATLSTM in the X, Y, and Z axes are reduced to 3.68%, 4.77%, and 2.37%, respectively, effectively improving the accuracy of satellite orbital error prediction. Further analysis indicates that a reasonable setting of the number of neurons helps improve model performance, while the prediction difficulty increases with the extension of the prediction duration, suggesting that the ATLSTM model is more suitable for short-term orbital error prediction and correction. In addition, validation results for satellites at different orbital altitudes demonstrate that the proposed model has certain generalization capability. In summary, combining deep learning methods with physical orbital models can effectively improve the accuracy of space object orbit prediction and provides an effective approach for orbital error prediction, space situational awareness, and collision warning.<\/jats:p>","DOI":"10.1371\/journal.pone.0356376","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T17:31:04Z","timestamp":1787333464000},"page":"e0356376","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on LSTM-based spatial target trajectory forecasting enhanced by attention mechanisms"],"prefix":"10.1371","volume":"21","author":[{"given":"Qingshan","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6661-1420","authenticated-orcid":true,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yurui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunsheng","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"issue":"6","key":"pone.0356376.ref001","doi-asserted-by":"crossref","first-page":"4942","DOI":"10.1016\/j.asr.2024.12.058","article-title":"Mega-constellation satellite maneuver forecast via network with attention mechanism","volume":"75","author":"H Liu","year":"2025","journal-title":"Advances in Space Research"},{"issue":"6","key":"pone.0356376.ref002","first-page":"31","article-title":"Orbital lifetime distribution of debris from space object disintegration","volume":"21","author":"Y Jiang","year":"2024","journal-title":"Space Electronic Technology"},{"key":"pone.0356376.ref003","first-page":"51","article-title":"Design of the manned space station against space debris","volume":"33","author":"X Wang","year":"2024","journal-title":"Spacecraft Eng"},{"issue":"1","key":"pone.0356376.ref004","first-page":"3","article-title":"Research progress on trajectory optimization for space target collaborative detection","volume":"12","author":"Z Zhang","year":"2025","journal-title":"Journal of Deep Space Exploration"},{"issue":"4","key":"pone.0356376.ref005","first-page":"51","article-title":"Research progress in space environment situation awareness and technology","volume":"23","author":"PR Hou","year":"2023","journal-title":"Space Debris Research"},{"issue":"11","key":"pone.0356376.ref006","doi-asserted-by":"crossref","first-page":"1427","DOI":"10.1016\/j.asr.2010.08.023","article-title":"Analytical and numerical approaches of a solar array thermal analysis in a low-earth orbit satellite","volume":"46","author":"HK Kim","year":"2010","journal-title":"Advances in Space Research"},{"issue":"4","key":"pone.0356376.ref007","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1007\/s42401-022-00149-7","article-title":"Sun outage prediction modeling for Earth orbiting satellites","volume":"5","author":"VK Srivastava","year":"2022","journal-title":"AS"},{"issue":"1","key":"pone.0356376.ref008","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/j.asr.2022.09.005","article-title":"Advanced analytical model for orbital aerodynamic prediction in LEO","volume":"71","author":"T Liang","year":"2023","journal-title":"Advances in Space Research"},{"key":"pone.0356376.ref009","doi-asserted-by":"crossref","unstructured":"Elhag MA, Yassin AA, Babiker ME, Elmageed EAEA. The unscented Kalman filter applied to satellite orbit determination using only publically available two-line element sets. In: 2013 International conference on computing, electrical and electronic engineering (ICCEEE), 2013. 464\u20139. https:\/\/doi.org\/10.1109\/icceee.2013.6633983","DOI":"10.1109\/ICCEEE.2013.6633983"},{"issue":"4","key":"pone.0356376.ref010","first-page":"26","article-title":"Study on the evolution law of orbital prediction error for space targets based on historical TLE","volume":"60","author":"XL Xu","year":"2019","journal-title":"Acta Astronomica Sinica"},{"issue":"8","key":"pone.0356376.ref011","first-page":"66","article-title":"TLE two-line element orbital data parameter analysis","volume":"28","author":"XG Wu","year":"2020","journal-title":"Journal of Space Science and Technology"},{"issue":"2","key":"pone.0356376.ref012","first-page":"98","article-title":"Analysis of space station orbit accuracy based on the SGP4 model","volume":"49","author":"LL Xu","year":"2024","journal-title":"Global Positioning System"},{"issue":"1","key":"pone.0356376.ref013","doi-asserted-by":"crossref","DOI":"10.1007\/BF00049361","article-title":"Numerical integration methods for orbital motion","volume":"53","author":"O Montenbruck","year":"1992","journal-title":"Celestial Mech Dyn Astr"},{"issue":"4","key":"pone.0356376.ref014","first-page":"64","article-title":"Satellite orbit computation based on the SGP4 model","author":"NH Diao","year":"2012","journal-title":"Remote Sensing Information"},{"issue":"1","key":"pone.0356376.ref015","doi-asserted-by":"crossref","first-page":"11","DOI":"10.5140\/JASS.2003.20.1.011","article-title":"Estimation of the sgp4 drag term from two osculating orbit states","volume":"20","author":"B-S Lee","year":"2003","journal-title":"Journal of Astronomy and Space Sciences"},{"issue":"5","key":"pone.0356376.ref016","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.2514\/1.A34171","article-title":"Artificial Neural Network\u2013Based Machine Learning Approach to Improve Orbit Prediction Accuracy","volume":"55","author":"H Peng","year":"2018","journal-title":"Journal of Spacecraft and Rockets"},{"issue":"5","key":"pone.0356376.ref017","doi-asserted-by":"crossref","first-page":"746","DOI":"10.3390\/rs17050746","article-title":"A VMD-SVM Method for LEO Satellite Orbit Prediction with Space Weather Parameters","volume":"17","author":"H Xu","year":"2025","journal-title":"Remote Sensing"},{"issue":"10","key":"pone.0356376.ref018","first-page":"127","article-title":"Research on long short-term memory neural networks in satellite orbit prediction","volume":"38","author":"JP Zhu","year":"2017","journal-title":"Journal of Weapons and Equipment Engineering"},{"key":"pone.0356376.ref019","volume-title":"Research on Satellite Orbit Prediction Algorithms Based on Deep Learning","author":"XR Yang","year":"2019"},{"issue":"3","key":"pone.0356376.ref020","first-page":"939","article-title":"Short-term orbit prediction based on LSTM neural network","volume":"44","author":"XY Zhang","year":"2022","journal-title":"Systems Engineering and Electronics"},{"issue":"10","key":"pone.0356376.ref021","doi-asserted-by":"crossref","first-page":"890","DOI":"10.2514\/1.I011482","article-title":"Research on Space Object Orbital Prediction Using Long Short-Term Memory Neural Networks","volume":"22","author":"Q Luo","year":"2025","journal-title":"Journal of Aerospace Information Systems"},{"issue":"4","key":"pone.0356376.ref022","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/s42064-018-0055-4","article-title":"Comparative evaluation of three machine learning algorithms on improving orbit prediction accuracy","volume":"3","author":"H Peng","year":"2019","journal-title":"Astrodyn"},{"issue":"6","key":"pone.0356376.ref023","doi-asserted-by":"crossref","first-page":"366","DOI":"10.2514\/1.I010616","article-title":"Exploring Capability of Support Vector Machine for Improving Satellite Orbit Prediction Accuracy","volume":"15","author":"H Peng","year":"2018","journal-title":"Journal of Aerospace Information Systems"},{"key":"pone.0356376.ref024","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.actaastro.2021.04.017","article-title":"Fusion of a machine learning approach and classical orbit predictions","volume":"184","author":"H Peng","year":"2021","journal-title":"Acta Astronautica"},{"key":"pone.0356376.ref025","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.actaastro.2019.05.014","article-title":"Gaussian Processes for improving orbit prediction accuracy","volume":"161","author":"H Peng","year":"2019","journal-title":"Acta Astronautica"},{"issue":"10","key":"pone.0356376.ref026","doi-asserted-by":"crossref","first-page":"2628","DOI":"10.1016\/j.asr.2018.03.001","article-title":"Improving orbit prediction accuracy through supervised machine learning","volume":"61","author":"H Peng","year":"2018","journal-title":"Advances in Space Research"},{"key":"pone.0356376.ref027","doi-asserted-by":"crossref","unstructured":"Peng H, Bai XL. Limits of machine learning approach on improving orbit prediction accuracy using support vector machine. In: Proceedings of the Advanced Maui Optical and Space Surveillance (AMOS) Technologies Conference, 2017. 15.","DOI":"10.2514\/6.2018-1966"},{"key":"pone.0356376.ref028","doi-asserted-by":"crossref","unstructured":"Peng H, Bai X. Obtain confidence interval for the machine learning approach to improve orbit prediction accuracy. In: Proceedings of the AAS\/AIAA Astrodynamics Specialist Conference, 2018. 2131\u201347.","DOI":"10.2514\/6.2018-1966"},{"issue":"18","key":"pone.0356376.ref029","first-page":"25","article-title":"Analysis of observation accuracy of array-structured space debris photoelectric telescope","volume":"19","author":"YG Ding","year":"2019","journal-title":"Science Technology and Engineerin"},{"issue":"1","key":"pone.0356376.ref030","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.asr.2014.03.012","article-title":"Achievable debris orbit prediction accuracy using laser ranging data from a single station","volume":"54","author":"J Sang","year":"2014","journal-title":"Advances in Space Research"},{"issue":"6","key":"pone.0356376.ref031","doi-asserted-by":"crossref","first-page":"1868","DOI":"10.3390\/s18061868","article-title":"Optical Tracking Data Validation and Orbit Estimation for Sparse Observations of Satellites by the OWL-Net","volume":"18","author":"J Choi","year":"2018","journal-title":"Sensors (Basel)"},{"issue":"4","key":"pone.0356376.ref032","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1016\/j.chinastron.2019.11.007","article-title":"Study on the Orbit Prediction Errors of Space Objects Based on Historical TLE Data","volume":"43","author":"X Xiao-li","year":"2019","journal-title":"Chinese Astronomy and Astrophysics"},{"issue":"3","key":"pone.0356376.ref033","first-page":"31","article-title":"Study on orbital errors of the two-line element catalog system","volume":"59","author":"XL Xu","year":"2018","journal-title":"Acta Astronomica Sinica"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T17:31:12Z","timestamp":1787333472000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356376"}},"subtitle":[],"editor":[{"given":"Roberto","family":"Barrio","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":33,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0356376","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]}}}