Prediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM-RF Hybrid Model

Accurate tunnel deformation prediction is critical for mitigating construction risks and ensuring tunnel stability. This study introduces a novel hybrid model integrating long short-term memory (LSTM) networks and random forest (RF) to enhance the precision of tunnel deformation predictions during c...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen Yintao, Shao Xin, Chang Xiangyu, Siti Norafida Bt. Jusoh, Lu Zhongxiang, Bao Hong Quan, Han Xinkai, Xu Jun
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Journal of Engineering
Online Access:http://dx.doi.org/10.1155/je/6652758
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850031815054589952
author Chen Yintao
Shao Xin
Chang Xiangyu
Siti Norafida Bt. Jusoh
Lu Zhongxiang
Bao Hong Quan
Han Xinkai
Xu Jun
author_facet Chen Yintao
Shao Xin
Chang Xiangyu
Siti Norafida Bt. Jusoh
Lu Zhongxiang
Bao Hong Quan
Han Xinkai
Xu Jun
author_sort Chen Yintao
collection DOAJ
description Accurate tunnel deformation prediction is critical for mitigating construction risks and ensuring tunnel stability. This study introduces a novel hybrid model integrating long short-term memory (LSTM) networks and random forest (RF) to enhance the precision of tunnel deformation predictions during construction. Bayesian optimization was utilized to fine-tune model parameters, ensuring optimal performance. Validated with multidepth data from the Yangjiashan highway tunnel in China, the hybrid model demonstrates remarkable adaptability to complex geological conditions. The results show that the LSTM-RF model achieves a mean square error (MSE) of 0.0025, a root-mean-square error (RMSE) of 0.0052, and a coefficient of determination (R2) of 0.9810, outperforming individual models and other hybrid frameworks in predicting deformation trends. By effectively capturing temporal dependencies and modeling nonlinear residuals, the hybrid model provides a robust and reliable solution for improving safety and efficiency in tunneling projects. These findings emphasize the potential of hybrid approaches for geotechnical engineering, particularly in predictive maintenance and infrastructure monitoring.
format Article
id doaj-art-4e9acdfd6b59467bb9daeacb03bfcd43
institution DOAJ
issn 2314-4912
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Journal of Engineering
spelling doaj-art-4e9acdfd6b59467bb9daeacb03bfcd432025-08-20T02:58:51ZengWileyJournal of Engineering2314-49122025-01-01202510.1155/je/6652758Prediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM-RF Hybrid ModelChen Yintao0Shao Xin1Chang Xiangyu2Siti Norafida Bt. Jusoh3Lu Zhongxiang4Bao Hong Quan5Han Xinkai6Xu Jun7School of Civil EngineeringTest and Inspection CenterSchool of Civil EngineeringSchool of Civil EngineeringSchool of Civil EngineeringTest and Inspection CenterSchool of Civil EngineeringEngineering Management DepartmentAccurate tunnel deformation prediction is critical for mitigating construction risks and ensuring tunnel stability. This study introduces a novel hybrid model integrating long short-term memory (LSTM) networks and random forest (RF) to enhance the precision of tunnel deformation predictions during construction. Bayesian optimization was utilized to fine-tune model parameters, ensuring optimal performance. Validated with multidepth data from the Yangjiashan highway tunnel in China, the hybrid model demonstrates remarkable adaptability to complex geological conditions. The results show that the LSTM-RF model achieves a mean square error (MSE) of 0.0025, a root-mean-square error (RMSE) of 0.0052, and a coefficient of determination (R2) of 0.9810, outperforming individual models and other hybrid frameworks in predicting deformation trends. By effectively capturing temporal dependencies and modeling nonlinear residuals, the hybrid model provides a robust and reliable solution for improving safety and efficiency in tunneling projects. These findings emphasize the potential of hybrid approaches for geotechnical engineering, particularly in predictive maintenance and infrastructure monitoring.http://dx.doi.org/10.1155/je/6652758
spellingShingle Chen Yintao
Shao Xin
Chang Xiangyu
Siti Norafida Bt. Jusoh
Lu Zhongxiang
Bao Hong Quan
Han Xinkai
Xu Jun
Prediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM-RF Hybrid Model
Journal of Engineering
title Prediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM-RF Hybrid Model
title_full Prediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM-RF Hybrid Model
title_fullStr Prediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM-RF Hybrid Model
title_full_unstemmed Prediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM-RF Hybrid Model
title_short Prediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM-RF Hybrid Model
title_sort prediction of surrounding rock deformation in a highway tunnel using an lstm rf hybrid model
url http://dx.doi.org/10.1155/je/6652758
work_keys_str_mv AT chenyintao predictionofsurroundingrockdeformationinahighwaytunnelusinganlstmrfhybridmodel
AT shaoxin predictionofsurroundingrockdeformationinahighwaytunnelusinganlstmrfhybridmodel
AT changxiangyu predictionofsurroundingrockdeformationinahighwaytunnelusinganlstmrfhybridmodel
AT sitinorafidabtjusoh predictionofsurroundingrockdeformationinahighwaytunnelusinganlstmrfhybridmodel
AT luzhongxiang predictionofsurroundingrockdeformationinahighwaytunnelusinganlstmrfhybridmodel
AT baohongquan predictionofsurroundingrockdeformationinahighwaytunnelusinganlstmrfhybridmodel
AT hanxinkai predictionofsurroundingrockdeformationinahighwaytunnelusinganlstmrfhybridmodel
AT xujun predictionofsurroundingrockdeformationinahighwaytunnelusinganlstmrfhybridmodel