A comparative study on different machine learning approaches with periodic items for the forecasting of GPS satellites clock bias
Abstract Accurately predicting satellite clock deviation is crucial for improving real-time location accuracy in a GPS navigation system. Therefore, to ensure high levels of real-time positioning accuracy, it is essential to address the challenge of enhancing satellite clock deviation prediction whe...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87328-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585861826347008 |
|---|---|
| author | Longjiang Song Jiahao Liu Leilei Wang Ziyi Wang Yibo Yuan |
| author_facet | Longjiang Song Jiahao Liu Leilei Wang Ziyi Wang Yibo Yuan |
| author_sort | Longjiang Song |
| collection | DOAJ |
| description | Abstract Accurately predicting satellite clock deviation is crucial for improving real-time location accuracy in a GPS navigation system. Therefore, to ensure high levels of real-time positioning accuracy, it is essential to address the challenge of enhancing satellite clock deviation prediction when high-precision clock data is unavailable. Given the high frequency, sensitivity, and variability of space-borne GPS satellite atomic clocks, it is important to consider the periodic variations of satellite clock bias (SCB) in addition to the inherent properties of GPS satellite clocks such as frequency deviation, frequency drift, and frequency drift rate to improve SCB prediction accuracy and gain a better understanding of its characteristics. In recent applications, deep learning models have significantly improved handling time-series data. This paper presents four machine learning prediction models that take into consideration periodic variations. Specifically, we utilize precision satellite clock bias data from the International GNSS Service forecast experiments and assess the predictive effects of various models including backpropagation neural network (BPNN), wavelet neural network (WNN), long short-term memory (LSTM), and gated recurrent units (GRUs). The predicted sequences of the four machine learning models are compared with the quadratic polynomial(QP) model. The average prediction accuracy of forecasting has improved by approximately (39.45, 57.57, 27.28, 29.14)% during 1-day forecasting. The results indicate that the machine learning models incorporating periodic variations outperform the standard quadratic polynomial model in terms of predictive accuracy, and the WNN model is better than that of these three machine learning models. This highlights the promising potential of deep learning models in forecasting satellite clock bias. |
| format | Article |
| id | doaj-art-a42640d2a89b4cc687fda1e3ebf82ed9 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a42640d2a89b4cc687fda1e3ebf82ed92025-01-26T12:24:56ZengNature PortfolioScientific Reports2045-23222025-01-0115111310.1038/s41598-025-87328-6A comparative study on different machine learning approaches with periodic items for the forecasting of GPS satellites clock biasLongjiang Song0Jiahao Liu1Leilei Wang2Ziyi Wang3Yibo Yuan4College of Ocean Science and Engineering, Shandong University of Science and TechnologyCollege of Ocean Science and Engineering, Shandong University of Science and TechnologySpace Star Technology Co., LtdCollege of Ocean Science and Engineering, Shandong University of Science and TechnologyCollege of Ocean Science and Engineering, Shandong University of Science and TechnologyAbstract Accurately predicting satellite clock deviation is crucial for improving real-time location accuracy in a GPS navigation system. Therefore, to ensure high levels of real-time positioning accuracy, it is essential to address the challenge of enhancing satellite clock deviation prediction when high-precision clock data is unavailable. Given the high frequency, sensitivity, and variability of space-borne GPS satellite atomic clocks, it is important to consider the periodic variations of satellite clock bias (SCB) in addition to the inherent properties of GPS satellite clocks such as frequency deviation, frequency drift, and frequency drift rate to improve SCB prediction accuracy and gain a better understanding of its characteristics. In recent applications, deep learning models have significantly improved handling time-series data. This paper presents four machine learning prediction models that take into consideration periodic variations. Specifically, we utilize precision satellite clock bias data from the International GNSS Service forecast experiments and assess the predictive effects of various models including backpropagation neural network (BPNN), wavelet neural network (WNN), long short-term memory (LSTM), and gated recurrent units (GRUs). The predicted sequences of the four machine learning models are compared with the quadratic polynomial(QP) model. The average prediction accuracy of forecasting has improved by approximately (39.45, 57.57, 27.28, 29.14)% during 1-day forecasting. The results indicate that the machine learning models incorporating periodic variations outperform the standard quadratic polynomial model in terms of predictive accuracy, and the WNN model is better than that of these three machine learning models. This highlights the promising potential of deep learning models in forecasting satellite clock bias.https://doi.org/10.1038/s41598-025-87328-6Satellite navigationSatellite clock biasClock forecastMachine learning models |
| spellingShingle | Longjiang Song Jiahao Liu Leilei Wang Ziyi Wang Yibo Yuan A comparative study on different machine learning approaches with periodic items for the forecasting of GPS satellites clock bias Scientific Reports Satellite navigation Satellite clock bias Clock forecast Machine learning models |
| title | A comparative study on different machine learning approaches with periodic items for the forecasting of GPS satellites clock bias |
| title_full | A comparative study on different machine learning approaches with periodic items for the forecasting of GPS satellites clock bias |
| title_fullStr | A comparative study on different machine learning approaches with periodic items for the forecasting of GPS satellites clock bias |
| title_full_unstemmed | A comparative study on different machine learning approaches with periodic items for the forecasting of GPS satellites clock bias |
| title_short | A comparative study on different machine learning approaches with periodic items for the forecasting of GPS satellites clock bias |
| title_sort | comparative study on different machine learning approaches with periodic items for the forecasting of gps satellites clock bias |
| topic | Satellite navigation Satellite clock bias Clock forecast Machine learning models |
| url | https://doi.org/10.1038/s41598-025-87328-6 |
| work_keys_str_mv | AT longjiangsong acomparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias AT jiahaoliu acomparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias AT leileiwang acomparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias AT ziyiwang acomparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias AT yiboyuan acomparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias AT longjiangsong comparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias AT jiahaoliu comparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias AT leileiwang comparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias AT ziyiwang comparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias AT yiboyuan comparativestudyondifferentmachinelearningapproacheswithperiodicitemsfortheforecastingofgpssatellitesclockbias |