LEO satellite clock prediction using deep learning: a wavelet–LSTM method with autoformer and LSTM comparisons
Open Access
- 22 June 2026
- journal article
- research article
- Published by Springer Nature in GPS Solutions
- Vol. 30 (3) , 147
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (No. 12473078)
- National Natural Science Foundation of China (No. 42404033)
- International Partnership Program of the Chinese Academy of Sciences (Grant No. 021GJHZ2023010FN)
- Special Research Assistant Funding Project, Chinese Academy of Sciences (No. 110400T0XW)
This publication has 40 references indexed in Scilit:
- Characteristics analysis and prediction of Low Earth Orbit (LEO) satellite clock corrections by using least-squares harmonic estimationGPS Solutions, 2022
- LEO-constellation-augmented multi-GNSS real-time PPP for rapid re-convergence in harsh environmentsGPS Solutions, 2021
- Clock bias prediction algorithm for navigation satellites based on a supervised learning long short-term memory neural networkGPS Solutions, 2021
- LEO constellation-augmented multi-GNSS for rapid PPP convergenceJournal of Geodesy, 2018
- Broadband LEO Constellations for NavigationNAVIGATION: Journal of the Institute of Navigation, 2018
- Short‐term GNSS satellite clock stabilityRadio Science, 2015
- Real-time clock offset prediction with an improved modelGPS Solutions, 2013
- Relativistic Time Transformations in GPSGPS Solutions, 2002
- The Global Positioning System: Signals, measurements, and performanceInternational Journal of Wireless Information Networks, 1994
- Effects of antenna orientation on GPS carrier phasemanuscripta geodaetica, 1993