Self-supervised deep learning for gnss time series imputation: a comparative study of neural network architectures
Transport and Communications Science Journal · 01.12.2025 · 77 (1) · 127-141
DOI: 10.47869/tcsj.77.1.10 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transport and Communications Science Journal, online erschienen am 01.12.2025. Verfasst von Giang Le Khanh und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Global Navigation Satellite System (GNSS) time series are widely used for structural health monitoring (SHM) and deformation analysis, but real-world recordings frequently contain short and long contiguous gaps that degrade downstream interpretation. This study addresses the challenge of accurate imputation for GNSS displacement series by proposing a self-supervised learning framework that trains models directly on real, unlabelled data using contiguous-span masking. We evaluate four neural architectures (ANN, CNN, GRU, LSTM) under a unified pipeline comprising signal denoising (moving-average, Kalman smoothing, Haar wavelet), sliding-window segmentation, Z-score normalization, and middle-region masking. Experiments use a year-long 10-minute-sampled dataset from the Can Tho cable-stayed bridge (sensor can519501, x/y/z components) and assess reconstruction quality via R², MAE, and MSE on withheld masked segments. Results indicate that recurrent architectures, particularly LSTM, produce the most faithful reconstructions: LSTM attains the highest validation R² (≈0.948) and the lowest MAE (≈0.137) and MSE (≈0.052) among tested models, while GRU offers competitive performance and CNN/ANN show substantially weaker recovery. These findings demonstrate that masking-based self-supervision is an effective strategy for GNSS gap recovery and that LSTM-like sequence models are well suited to capture the long-range temporal dependencies in bridge displacement data. The proposed approach enhances the reliability and continuity of GNSS-derived time series for structural monitoring and can inform future multi-sensor fusion and uncertainty quantification work
Zitieren
APA
Khanh, G. L., Duc, C. T., & Lan, H. H. T. (2025). Self-supervised deep learning for gnss time series imputation: a comparative study of neural network architectures. Transport and Communications Science Journal, 77(1), 127-141. https://doi.org/10.47869/tcsj.77.1.10
Vancouver
Khanh GL, Duc CT, Lan HHT. Self-supervised deep learning for gnss time series imputation: a comparative study of neural network architectures. Transport and Communications Science Journal. 2025;77(1):127-141. doi:10.47869/tcsj.77.1.10
BibTeX
@article{Khanh2025,
author = {Khanh, Giang Le and Duc, Cong Tran and Lan, Huong Ho Thi},
title = {Self-supervised deep learning for gnss time series imputation: a comparative study of neural network architectures},
journal = {Transport and Communications Science Journal},
year = {2025},
volume = {77},
number = {1},
pages = {127--141},
doi = {10.47869/tcsj.77.1.10}
}
EUVIMED