Deep learning-based modeling and prediction of GNSS time series: A comparative analysis of adaptive optimization algorithms

•For the first time in the literature, adaptive learning rate optimization methods are compared on GNSS time series data.•Deep learning methods are proposed for the prediction of GNSS time series data.•10 different deep learning methods and 4 different optimization algorithms were studied.•The best...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Advances in space research Jg. 76; H. 4; S. 2086 - 2103
Hauptverfasser: Tabar, Mehmet Emin, Sisman, Yasemin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 15.08.2025
Schlagworte:
Adaptive learning optimization
Deep learning
GNSS
Time series
Deep learning
Adaptive learning optimization
GNSS
Time series
ISSN:0273-1177
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•For the first time in the literature, adaptive learning rate optimization methods are compared on GNSS time series data.•Deep learning methods are proposed for the prediction of GNSS time series data.•10 different deep learning methods and 4 different optimization algorithms were studied.•The best optimization method-deep learning model combination in the study was found to be GRU with Adam optimization. In this research, optimization algorithms with adaptive learning rates on Global Navigation Satellite System (GNSS) time series data are comparatively investigated. For this purpose, five years of GNSS measurement data obtained from the AGRD station located in the Ağrı province of Türkiye were used and incorrect or missing records were detected for a total of 251 days in the dataset. After the missing data were completed using the linear interpolation method, a total of ten different deep learning methods and four different adaptive optimization algorithms (Adam, Adagrad, RMSprop and AdamW) were used to develop separate prediction models and performance evaluations were performed. When the performance of the best combination, the Adam optimized-GRU model, was evaluated based on Root Mean Square Error (RMSE) values, it was found to be 1.58 mm, 1.36 mm and 3.07 mm for the north, east and up components, respectively. When evaluated according to the Mean Absolute Error (MAE) value, it was found to be 1.20 mm, 1.05 mm, 2.33 mm, respectively. As a result of the comprehensive analyses, it has been revealed that Adam and AdamW algorithms are more effective than the others among the adaptive optimization algorithms examined and the deep learning models optimized with these algorithms exhibit superior prediction performance on GNSS time series data. It is thought that the results obtained from this study will be an important reference on adaptive learning optimization algorithms for future studies in the field of GNSS time series and deep learning and will guide the research on the subject.
ISSN:0273-1177
DOI:10.1016/j.asr.2025.06.018