A Hybrid Spatial–Temporal Deep Learning Method for Metro Tunnel Displacement Prediction Under “Dual Carbon” Background

The burgeoning urbanization and construction activities pose significant challenges to the structural integrity and safety of the existing metro tunnels. This study introduces a hybrid spatial–temporal deep learning model, integrating graph convolutional network (GCN) and long short-term memory (LST...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianyong Chai, Limin Jia, Jianfeng Liu, Enguang Hou, Zhe Chen
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/atr/7189559
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850157220794204160
author Jianyong Chai
Limin Jia
Jianfeng Liu
Enguang Hou
Zhe Chen
author_facet Jianyong Chai
Limin Jia
Jianfeng Liu
Enguang Hou
Zhe Chen
author_sort Jianyong Chai
collection DOAJ
description The burgeoning urbanization and construction activities pose significant challenges to the structural integrity and safety of the existing metro tunnels. This study introduces a hybrid spatial–temporal deep learning model, integrating graph convolutional network (GCN) and long short-term memory (LSTM) networks, to predict metro tunnel displacements under the imperatives of “dual carbon” goals. The model leverages the strengths of GCNs in capturing spatial correlations and LSTM networks in processing temporal dynamics, offering a robust framework for accurate displacement prediction. The methodology encompasses data preprocessing, including outlier removal and missing value imputation, followed by feature extraction and normalization. The proposed GCN-LSTM model is trained on historical displacement data, employing a robotic total station (RTS) for high-precision monitoring. The model’s performance is evaluated using metrics such as root mean square error (RMSE), mean absolute error (MAE), and weighted mean absolute percentage error (WMAPE) and is compared against other models including LSTM, recurrent neural network (RNN), gated recurrent unit (GRU), residual LSTM (ResLSTM), and a variant of GCN-LSTM. The results indicate that the GCN-LSTM model outperforms comparative models across various sliding window sizes, demonstrating lower error metrics and higher stability. The model’s efficacy is further corroborated through a case study on the Jinan Metro Line 2, where it provides reliable predictions crucial for proactive maintenance and sustainable urban development. The study contributes to the field of metro tunnel displacement prediction and supports the advancement of intelligent monitoring systems for urban infrastructure.
format Article
id doaj-art-df5ce88321e940339711a6a0133dcffc
institution OA Journals
issn 2042-3195
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Journal of Advanced Transportation
spelling doaj-art-df5ce88321e940339711a6a0133dcffc2025-08-20T02:24:14ZengWileyJournal of Advanced Transportation2042-31952025-01-01202510.1155/atr/7189559A Hybrid Spatial–Temporal Deep Learning Method for Metro Tunnel Displacement Prediction Under “Dual Carbon” BackgroundJianyong Chai0Limin Jia1Jianfeng Liu2Enguang Hou3Zhe Chen4School of Traffic and TransportationSchool of Traffic and TransportationDesign Research InstituteSchool of Rail TransportationSchool of Rail TransportationThe burgeoning urbanization and construction activities pose significant challenges to the structural integrity and safety of the existing metro tunnels. This study introduces a hybrid spatial–temporal deep learning model, integrating graph convolutional network (GCN) and long short-term memory (LSTM) networks, to predict metro tunnel displacements under the imperatives of “dual carbon” goals. The model leverages the strengths of GCNs in capturing spatial correlations and LSTM networks in processing temporal dynamics, offering a robust framework for accurate displacement prediction. The methodology encompasses data preprocessing, including outlier removal and missing value imputation, followed by feature extraction and normalization. The proposed GCN-LSTM model is trained on historical displacement data, employing a robotic total station (RTS) for high-precision monitoring. The model’s performance is evaluated using metrics such as root mean square error (RMSE), mean absolute error (MAE), and weighted mean absolute percentage error (WMAPE) and is compared against other models including LSTM, recurrent neural network (RNN), gated recurrent unit (GRU), residual LSTM (ResLSTM), and a variant of GCN-LSTM. The results indicate that the GCN-LSTM model outperforms comparative models across various sliding window sizes, demonstrating lower error metrics and higher stability. The model’s efficacy is further corroborated through a case study on the Jinan Metro Line 2, where it provides reliable predictions crucial for proactive maintenance and sustainable urban development. The study contributes to the field of metro tunnel displacement prediction and supports the advancement of intelligent monitoring systems for urban infrastructure.http://dx.doi.org/10.1155/atr/7189559
spellingShingle Jianyong Chai
Limin Jia
Jianfeng Liu
Enguang Hou
Zhe Chen
A Hybrid Spatial–Temporal Deep Learning Method for Metro Tunnel Displacement Prediction Under “Dual Carbon” Background
Journal of Advanced Transportation
title A Hybrid Spatial–Temporal Deep Learning Method for Metro Tunnel Displacement Prediction Under “Dual Carbon” Background
title_full A Hybrid Spatial–Temporal Deep Learning Method for Metro Tunnel Displacement Prediction Under “Dual Carbon” Background
title_fullStr A Hybrid Spatial–Temporal Deep Learning Method for Metro Tunnel Displacement Prediction Under “Dual Carbon” Background
title_full_unstemmed A Hybrid Spatial–Temporal Deep Learning Method for Metro Tunnel Displacement Prediction Under “Dual Carbon” Background
title_short A Hybrid Spatial–Temporal Deep Learning Method for Metro Tunnel Displacement Prediction Under “Dual Carbon” Background
title_sort hybrid spatial temporal deep learning method for metro tunnel displacement prediction under dual carbon background
url http://dx.doi.org/10.1155/atr/7189559
work_keys_str_mv AT jianyongchai ahybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground
AT liminjia ahybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground
AT jianfengliu ahybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground
AT enguanghou ahybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground
AT zhechen ahybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground
AT jianyongchai hybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground
AT liminjia hybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground
AT jianfengliu hybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground
AT enguanghou hybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground
AT zhechen hybridspatialtemporaldeeplearningmethodformetrotunneldisplacementpredictionunderdualcarbonbackground