SAR-Nbeats-based temperature interpretation and prediction of InSAR time-series deformations for bridges

Abstract

Existing bridge monitoring methods face high monitoring costs, and the processing and forecasting of monitoring data often rely on machine learning which lacks interpretability in the prediction results. Based on the Neural Basis Expansion Analysis for Time Series Forecasting (N-Beats) model, this study proposes an SAR-Nbeats (S-N) model for extracting, decomposition, and predicting bridge deformation. The input of S-N model is the bridge deformation data, which are obtained by Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) technique. At first, using Sentinel-1A imagery from 2018 to 2023 as the data source, bridge deformation results are obtained through PS-InSAR technology. Then, extremum symmetric mode decomposition and seasonal-trend decomposition are employed to decompose bridge deformation into trend, seasonal, and random components effectively, conducting adaptive classification based on different periods. Finally, based on the periodic and trend characteristics of bridge deformation, improvements and parameter adjustments are made to conventional N-Beats algorithms. The time-series data after decomposed are used as input to train the improved N-Beats model and obtain prediction results. Compared with the original algorithm, the main improvements include transforming the input data into modal decomposed data and associating the parameters of the fitting function with the deformation composition of the bridge. The bridge deformation patterns were evaluated based on climatic rules and InSAR time-series prediction results, yielding the following findings: by comparing the prediction results, the performance of SAR-Nbeats model is better than Long Short-Term Memory (LSTM) and Autoregressive Integrated Moving Average Model (ARIMA), which has highest R² 0.8605. The SAR-Nbeats model improves the accuracy and interpretability of bridge deformation predictions by refining the input of the data-driven forecasting model. It can achieve the goal of monitoring and early warning for bridges without ground-based monitoring systems with lower computational effort and faster processing speeds.

Keywords

Bridge deformation InSAR time series signals N-Beats algorithm modal decomposition prediction method

Get full access to this article

View all access options for this article.

References

Zou

Nico

Alani

, et al. Strategy for vertical deformation of railway bridge monitoring using polarimetric ground-based real aperture radar system. Struct Health Monit 2024; 23: 3719–3730.

Farneti

Cavalagli

Costantini

, et al. A method for structural monitoring of multispan bridges using satellite InSAR data with uncertainty quantification and its pre-collapse application to the Albiano-Magra Bridge in Italy. Struct Health Monit 2023; 22(1): 353–371.

Wen

Yao

, et al. InSAR-based method for monitoring the long-time evolutions and spatial-temporal distributions of unstable slopes with the impact of water-level fluctuation: a case study in the Xiluodu reservoir. Remote Sens Environ 2023; 295: 113686.

Macchiarulo

Milillo

Blenkinsopp

, et al. Monitoring deformations of infrastructure networks: a fully automated GIS integration and analysis of InSAR time-series. Struct Health Monit 2022; 21(4): 1849–1878.

Lazecky

Hlavacova

Bakon

, et al. Bridge displacements monitoring using space-borne X-band SAR interferometry. IEEE J Selected Topics Appl Earth Observ Remote Sens 2016; 10(1): 205–210.

Crosetto

Monserrat

Cuevas-González

, et al. Measuring thermal expansion using X-band persistent scatterer interferometry. ISPRS J Photogramm Remote Sens 2015; 100: 84–91.

Poreh

Railways’ stability observed in Campania (Italy) by InSAR data. Eur J Remote Sens 2016; 49(1): 417–431.

Zhang

, et al. SAR-transformer-based decomposition and geophysical interpretation of InSAR time-series deformations for the Hong Kong-Zhuhai-Macao bridge. Remote Sens Environ 2024; 302: 113962.

Masini

Medeiros

Mendes

EF.

Machine learning advances for time series forecasting. J Economic Surv 2023; 37(1): 76–111.

10.

Han

Zhao

Leung

, et al. A review of deep learning models for time series prediction. IEEE Sens J 2019; 21(6): 7833–7848.

11.

Parmezan

ARS

Souza

VMA

Batista

GE.

Evaluation of statistical and machine learning models for time series prediction: identifying the state-of-the-art and the best conditions for the use of each model. Inform Sci 2019; 484: 302–337.

12.

Wan

H-P

Zhu

Y-K

Luo

, et al. Unsupervised deep learning approach for structural anomaly detection using probabilistic features. Struct Health Monit 2025; 24(1): 3–33.

13.

Dong

G-S

Wan

H-P

Luo

, et al. A fast sparsity-free compressive sensing approach for vibration data reconstruction using deep convolutional GAN. Mech Syst Signal Process 2023; 188: 109937.

14.

Shenzhen Planning and Natural Resources Bureau. Shenzhen’s 2022 geological disaster prevention plan. Shenzhen Planning and Natural Resources Bureau, Shenzhen, Guangdong, China, 2022.

15.

Raspisaniye Pogodi Ltd. Weather for 241 countries of the world dataset: Reliable Prognosis, 2004 to 2024. Distributed by Raspisaniye Pogodi Ltd. https://rp5.ru/Weather_in_the_world.

16.

Zhou

Cai

Chen

, et al. Meteorological data prediction for service environments of bridge using spatial interpolation method. In: Sensors and smart structures technologies for civil, mechanical, and aerospace systems 2021, 2021, vol. 11591B, pp. 475–481. SPIE.

17.

Hooper

Zebker

Segall

, et al. A new method for measuring deformation on volcanoes and other natural terrains using InSAR persistent scatterers. Geophys Res Lett 2004; 31(23) https://doi.org/10.1029/2004GL021737.

18.

Ferretti

Prati

Rocca

Permanent scatterers in SAR interferometry. IEEE Trans Geosci Remote Sens 2001; 39(1): 8–20.

19.

Bao

Machine learning paradigm for structural health monitoring. Struct Health Monit 2021; 20(4): 1353–1372.

20.

Wang

J-L

Z-J.

Extreme-point symmetric mode decomposition method for data analysis. Adv Adaptive Data Anal 2013; 5(3): 1350015.

21.

Sellinger

Stow

Lamon

, et al. Recent water level declines in the Lake Michigan-Huron system. Environ Sci Technol 2008; 42(2): 367–373.

22.

Silvestre

Rocha dos Santos

CPLF de Carvalho

. Seasonal-trend decomposition based on loess machine learning: hybrid forecasting for monthly univariate time series. In: 2021 international joint conference on neural networks (IJCNN), 2021. IEEE.

23.

Moschas

Stiros

Measurement of the dynamic displacements and of the modal frequencies of a short-span pedestrian bridge using GPS and an accelerometer. Eng Struct 2011; 33(1): 10–17.

24.

Chung

Gulcehre

Cho

, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv: 2014: 1412.3555.

25.

Oreshkin

Carpov

Chapados

, et al. N-BEATS: neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv: 2019: 1905.10437.

26.

Olivares

Challu

Marcjasz

, et al. Neural basis expansion analysis with exogenous variables: forecasting electricity prices with NBEATSx. Int J Forecasting 2023; 39: 884–900.

27.

Box

GEP

Pierce

. Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. J Am Statistical Assoc 1970; 65(332): 1509–1526.

28.

Hochreiter

Schmidhuber

Long short-term memory. Neural Comput 1997; 9(8): 1735–1780.

29.

Kulshrestha

Chang

Stein

Use of LSTM for sinkhole-related anomaly detection and classification of InSAR deformation time series. IEEE J Selected Topics Appl Earth Observ Remote Sens 2022; 15: 4559–4570.