Науковий вісник НГУ

Empirical comparison of five deep learning architectures for GNSS time-series data forecasting

• 
• 

User Rating:  / 0

PoorBest 

Details

Parent Category: 2025

Category: Content №5 2025

Created on 25 October 2025

Last Updated on 25 October 2025

Published on 30 November -0001

Written by Trong Gia Nguyen, Tinh Duc Le, Long Quoc Nguyen

Hits: 3042

Authors:

Trong Gia Nguyen, orcid.org/0009-0006-0765-245X, Hanoi University of Mining and Geology, Faculty of Geomatics and Land Administration, Hanoi, Socialist Republic of Vietnam; Hanoi University of Mining and Geology, Geodesy and Environment Research Group, Hanoi, Socialist Republic of Vietnam

Tinh Duc Le, orcid.org/0000-0002-0022-3453, Hanoi University of Mining and Geology, Faculty of Geomatics and Land Administration, Hanoi, Socialist Republic of Vietnam

Long Quoc Nguyen*, orcid.org/0000-0002-4792-3684, Hanoi University of Mining and Geology, Faculty of Geomatics and Land Administration, Hanoi, Socialist Republic of Vietnam; Hanoi University of Mining and Geology, Innovations for Sustainable and Responsible Mining (ISRM) Research Group, Hanoi, Socialist Republic of Vietnam, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

* Corresponding author e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

повний текст / full article

Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu. 2025, (5): 122 - 131

https://doi.org/10.33271/nvngu/2025-5/122

Abstract:

Purpose. This study aims to propose an effective deep learning model for analyzing time series of GNSS data.

Methodology. Five deep learning models were investigated using the Adam optimization algorithm and the MSE loss function: CNN (Conv1D), GRU, Transformer, Seq2seq, and SimpleRNN. The models’ predictive performance was evaluated with data from three CORS stations in Vietnam: HYEN, BTRI, and CTHO. The models were constructed using the Adam optimization function, MSE loss function, and a batch size of 16.

Findings. The prediction results across all models were generally low. Specifically, the Seq2seq model achieved the lowest RMSE value for the Up-component data from the HYEN station. The Transformer model was unsuitable for analyzing GNSS data over time, and the SimpleRNN model showed poor performance with the HYEN station data. However, the proposed CNN(Conv1D)-RF model, which integrates the RF model with the CNN(Conv1D) model, achieved high predictive performance, with RMSE = 0.4 mm, MAE= 0.07 mm, and R-squared = 99.8 % when the input data consisted solely of the Up-component. When the input data included all three components (N, E, and Up), the maximum RMSE value was 0.92 mm.

Originality. This study introduces the CNN(Conv1D)-RF model, a novel integration of the RF model with the CNN(Conv1D) model, for GNSS data analysis.

Practical value. The proposed model demonstrates promising predictive performance, indicating its potential application in accurately analyzing GNSS data for various practical purposes.

Keywords: deep learning, GNSS time series, machine learning, algorithm

References.

1. Gill, S. K., Weston, N. D., & Smith, D. A. (2015). NOAA guidance document for determination of vertical land motion at water level stations using GPS technology, 18. https://doi.org/10.25607/OBP-147

2. Hu, B., Chen, J., & Zhang, X. (2019). Monitoring the Land Subsidence Area in a Coastal Urban Area with InSAR and GNSS. Sensors, 19(14), 3181. https://doi.org/10.3390/s19143181

3. Pipitone, C., Maltese, A., Lo Brutto, M., & Dardanelli, G. (2023). A Review of Selected Applications of GNSS CORS and Related Experiences at the University of Palermo (Italy). Remote Sensing, 15(22), 5343. https://doi.org/10.3390/rs15225343

4. Jones, C. E., An, K., Blom, R. G., Kent, J. D., Ivins, E. R., & Bekaert, D. (2016). Anthropogenic and geologic influences on subsidence in the vicinity of New Orleans, Louisiana. Journal of Geophysical Research: Solid Earth, 121(5), 3867-3887. Portico. https://doi.org/10.1002/2015jb012636

5. Leveson, I. (2009). Socio-Economic Benefits Study: Scoping the Value of CORS and GRAV-D. Retrieved from https://repository.library.noaa.gov/view/noaa/55545

6. Ige, A. O., & Sibiya, M. (2024). State-of-the-Art in 1D Convolutional Neural Networks: A Survey. IEEE Access, 12, 144082-144105. https://doi.org/10.1109/access.2024.3433513

7. Rizvi, S. M. H. (2021). Time Series Deep learning for Robust Steady-State Load Parameter Estimation using 1D-CNN. Arabian Journal for Science and Engineering, 47(3), 2731-2744. https://doi.org/10.1007/s13369-021-05782-6

8. Weerakody, P. B., Wong, K. W., Wang, G., & Ela, W. (2021).
A review of irregular time series data handling with gated recurrent neural networks. Neurocomputing, 441, 161-178. https://doi.org/10.1016/j.neucom.2021.02.046

9. Bi, J., Zhu, Z., & Meng, Q. (2021). Transformer in Computer Vision. 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), 178-188. https://doi.org/10.1109/cei52496.2021.9574462

10.      Ahmed, S., Nielsen, I. E., Tripathi, A., Siddiqui, S., Ramachandran, R. P., & Rasool, G. (2023). Transformers in Time-Series Analysis: A Tutorial. Circuits, Systems, and Signal Processing, 42(12), 7433-7466. https://doi.org/10.1007/s00034-023-02454-8

11.      Chen, Z., Ma, M., Li, T., Wang, H., & Li, C. (2023). Long sequence time-series forecasting with deep learning: A survey. Information Fusion, 97, 101819. https://doi.org/10.1016/j.inffus.2023.101819

12.      Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning, 1(2). Retrieved from https://www.deeplearningbook.org/

13.      Chollet, F., & Chollet, F. (2021). Deep learning with Python. Simon and Schuster. Retrieved from https://www.pressreader.com/books/b/deep-learning-with-python-23518

14.      Siemuri, A., Kuusniemi, H., Elmusrati, M. S., Valisuo, P., & Shamsuzzoha, A. (2021). Machine Learning Utilization in GNSS – Use Cases, Challenges and Future Applications. 2021 International Conference on Localization and GNSS (ICL-GNSS), 1-6. https://doi.org/10.1109/icl-gnss51451.2021.9452295

15.      Loli Piccolomini, E., Gandolfi, S., Poluzzi, L., Tavasci, L., Cascarano, P., & Pascucci, A. (2019). Recurrent neural networks applied to GNSS time series for denoising and prediction. 26^th International Symposium on Temporal Representation and Reasoning, 10-1. https://doi.org/10.4230/LIPIcs.TIME.2019.10

16.      Kiani, M. (2020). A precise machine learning aided algorithm for land subsidence or upheave prediction from GNSS time series. preprint arXiv:2006. 03772. https://doi.org/10.48550/arXiv.2006.03772

17.      Kiani, M. (2020). On GNSS residual position time series prediction and analysis using radial basis function networks machine learning. Second international conference on Development of Materials engineering technology, mining, and geology. Retrieved from https://www.researchgate.net/publication/344853610

18.      Kiani, M. (2020). On the suitability of generalized regression neural networks for GNSS position time series prediction for geodetic applications in geodesy and geophysics. arXiv preprint arXiv:2005.11106. https://doi.org/10.48550/arXiv.2005.11106

19.      Wang, J., Jiang, W., Li, Z., & Lu, Y. (2021). A New Multi-Scale Sliding Window LSTM Framework (MSSW-LSTM): A Case Study for GNSS Time-Series Prediction. Remote Sensing, 13(16), 3328. https://doi.org/10.3390/rs13163328

20.      Wen, T., Ou, G., Tang, X., Zhang, P., & Wang, P. (2021). A Novel Long Short-Term Memory Predicted Algorithm for BDS Short-Term Satellite Clock Offsets. International Journal of Aerospace Engineering, 2021, 1-16. https://doi.org/10.1155/2021/4066275

21.      Crocetti, L., Schartner, M., & Soja, B. (2021). Discontinuity Detection in GNSS Station Coordinate Time Series Using Machine Learning. Remote Sensing, 13(19), 3906. https://doi.org/10.3390/rs13193906

22.      Ruttner, P., Hohensinn, R., D’Aronco, S., Wegner, J. D., & Soja, B. (2021). Modeling of Residual GNSS Station Motions through Meteorological Data in a Machine Learning Approach. Remote Sensing, 14(1), 17. https://doi.org/10.3390/rs14010017

23.      Chen, H., Lu, T., Huang, J., He, X., Yu, K., Sun, X., Ma, X., & Huang, Z. (2023). An Improved VMD-LSTM Model for Time-Varying GNSS Time Series Prediction with Temporally Correlated Noise. Remote Sensing, 15(14), 3694. https://doi.org/10.3390/rs15143694

24.      Li, Z., Lu, T., Yu, K., & Wang, J. (2023). Interpolation of GNSS Position Time Series Using GBDT, XGBoost, and RF Machine Learning Algorithms and Models Error Analysis. Remote Sensing, 15(18), 4374. https://doi.org/10.3390/rs15184374

25.      Xie, Y., Wang, J., Li, H., Dong, A., Kang, Y., Zhu, J., Wang, Y., & Yang, Y. (2024). Deep Learning CNN-GRU Method for GNSS Deformation Monitoring Prediction. Applied Sciences, 14(10), 4004. https://doi.org/10.3390/app14104004

26.      Khorrami, F., Ejigu, Y. G., Näränen, J., Raja-Halli, A., & Nordman, M. (2024). Exploring Non-tidal Atmospheric Loading Deformation Correction in GNSS Time Series Analysis Using GAMIT/GLOBK Software. International Association of Geodesy Symposia. https://doi.org/10.1007/1345_2024_272

27.      Jadon, A., Patil, A., & Jadon, S. (2024). A comprehensive survey of regression-based loss functions for time series forecasting. Lecture Notes in Networks and Systems, 998, 117-147. https://doi.org/10.1007/978-981-97-3245-6_9

28.      Wang, J., Nie, G., Gao, S., Wu, S., Li, H., & Ren, X. (2021). Landslide Deformation Prediction Based on a GNSS Time Series Analysis and Recurrent Neural Network Model. Remote Sensing, 13(6), 1055. https://doi.org/10.3390/rs13061055

29.      Gao, W., Li, Z., Chen, Q., Jiang, W., & Feng, Y. (2022). Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches. Journal of Geodesy, 96(10). https://doi.org/10.1007/s00190-022-01662-5

• < Prev
• Next >