Forecasting Tunnel-Induced Ground Settlement: A Hybrid Deep Learning Approach and Traditional Statistical Techniques With Sensor Data

Accurately forecasting tunnel-induced ground settlement is crucial for mitigating risks to urban infrastructure and ensuring the safety of tunnelling operations. This study introduces advanced predictive frameworks that incorporate enhancements to both deep learning (DL) models and statistical techn...

Full description

Saved in:
Bibliographic Details
Main Authors: Syed Mujtaba Hussaine, Linlong Mu, Yimin Lu, Syed Sajid Hussain
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10949176/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850151091418693632
author Syed Mujtaba Hussaine
Linlong Mu
Yimin Lu
Syed Sajid Hussain
author_facet Syed Mujtaba Hussaine
Linlong Mu
Yimin Lu
Syed Sajid Hussain
author_sort Syed Mujtaba Hussaine
collection DOAJ
description Accurately forecasting tunnel-induced ground settlement is crucial for mitigating risks to urban infrastructure and ensuring the safety of tunnelling operations. This study introduces advanced predictive frameworks that incorporate enhancements to both deep learning (DL) models and statistical techniques to handle the intricate, nonlinear, and dynamic characteristics of settlement data. The proposed DL models, Convolutional Long Short-Term Memory (Conv-LSTM2D) and Convolutional Gated Recurrent Unit (Conv-GRU2D), extend traditional LSTM and GRU architectures with 2D convolutional mechanisms to capture complex spatiotemporal dependencies. Additionally, the statistical Autoregressive Integrated Moving Average (ARIMA)/Seasonal ARIMA (SARIMA) models were enhanced through seasonality removal, automated model selection using the auto_arima algorithm, and parameter fine-tuning via grid search to improve their predictive accuracy. Extensive evaluations using real-world sensor datasets from tunnelling projects demonstrated that the proposed Conv-GRU2D model achieved superior performance, with a R-squared of 0.94, an RMSE of 0.12, and MAPE of 0.32, surpassing both Conv-LSTM2D and optimized ARIMA/SARIMA models. These results highlight the effectiveness of convolutional mechanisms in deep learning and the advantage of optimized ARIMA/SARIMA models in capturing complex temporal patterns and improving forecasting precision for optimizing ground settlement. Notably, our findings demonstrate that the proposed models outperform existing methods, providing superior prediction accuracy and computational efficiency, even with limited training data. This underscores the potential of these innovative methods to significantly enhance the reliability of ground settlement forecasts in urban tunnel construction, offering valuable insights that can further advance geotechnical engineering practices and contribute to safer and more efficient tunnelling operations in urban environments.
format Article
id doaj-art-981e4ea09b2e442695593a2adaa84eee
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-981e4ea09b2e442695593a2adaa84eee2025-08-20T02:26:23ZengIEEEIEEE Access2169-35362025-01-0113626916270310.1109/ACCESS.2025.355781510949176Forecasting Tunnel-Induced Ground Settlement: A Hybrid Deep Learning Approach and Traditional Statistical Techniques With Sensor DataSyed Mujtaba Hussaine0https://orcid.org/0000-0002-1905-0054Linlong Mu1Yimin Lu2https://orcid.org/0000-0001-6022-2551Syed Sajid Hussain3https://orcid.org/0000-0003-3376-2290Department of Geotechnical Engineering, Tongji University, Shanghai, ChinaDepartment of Geotechnical Engineering, Tongji University, Shanghai, ChinaDepartment of Civil, Environmental, and Construction Engineering, Texas Tech University, Lubbock, TX, USASchool of Computer Science, University of Petroleum and Energy Studies (UPES), Dehradun, Uttarakhand, IndiaAccurately forecasting tunnel-induced ground settlement is crucial for mitigating risks to urban infrastructure and ensuring the safety of tunnelling operations. This study introduces advanced predictive frameworks that incorporate enhancements to both deep learning (DL) models and statistical techniques to handle the intricate, nonlinear, and dynamic characteristics of settlement data. The proposed DL models, Convolutional Long Short-Term Memory (Conv-LSTM2D) and Convolutional Gated Recurrent Unit (Conv-GRU2D), extend traditional LSTM and GRU architectures with 2D convolutional mechanisms to capture complex spatiotemporal dependencies. Additionally, the statistical Autoregressive Integrated Moving Average (ARIMA)/Seasonal ARIMA (SARIMA) models were enhanced through seasonality removal, automated model selection using the auto_arima algorithm, and parameter fine-tuning via grid search to improve their predictive accuracy. Extensive evaluations using real-world sensor datasets from tunnelling projects demonstrated that the proposed Conv-GRU2D model achieved superior performance, with a R-squared of 0.94, an RMSE of 0.12, and MAPE of 0.32, surpassing both Conv-LSTM2D and optimized ARIMA/SARIMA models. These results highlight the effectiveness of convolutional mechanisms in deep learning and the advantage of optimized ARIMA/SARIMA models in capturing complex temporal patterns and improving forecasting precision for optimizing ground settlement. Notably, our findings demonstrate that the proposed models outperform existing methods, providing superior prediction accuracy and computational efficiency, even with limited training data. This underscores the potential of these innovative methods to significantly enhance the reliability of ground settlement forecasts in urban tunnel construction, offering valuable insights that can further advance geotechnical engineering practices and contribute to safer and more efficient tunnelling operations in urban environments.https://ieeexplore.ieee.org/document/10949176/Time-series forecastingground settlementsensor datahybrid deep learning modelsARIMA/SARIMAconvolution mechanisms
spellingShingle Syed Mujtaba Hussaine
Linlong Mu
Yimin Lu
Syed Sajid Hussain
Forecasting Tunnel-Induced Ground Settlement: A Hybrid Deep Learning Approach and Traditional Statistical Techniques With Sensor Data
IEEE Access
Time-series forecasting
ground settlement
sensor data
hybrid deep learning models
ARIMA/SARIMA
convolution mechanisms
title Forecasting Tunnel-Induced Ground Settlement: A Hybrid Deep Learning Approach and Traditional Statistical Techniques With Sensor Data
title_full Forecasting Tunnel-Induced Ground Settlement: A Hybrid Deep Learning Approach and Traditional Statistical Techniques With Sensor Data
title_fullStr Forecasting Tunnel-Induced Ground Settlement: A Hybrid Deep Learning Approach and Traditional Statistical Techniques With Sensor Data
title_full_unstemmed Forecasting Tunnel-Induced Ground Settlement: A Hybrid Deep Learning Approach and Traditional Statistical Techniques With Sensor Data
title_short Forecasting Tunnel-Induced Ground Settlement: A Hybrid Deep Learning Approach and Traditional Statistical Techniques With Sensor Data
title_sort forecasting tunnel induced ground settlement a hybrid deep learning approach and traditional statistical techniques with sensor data
topic Time-series forecasting
ground settlement
sensor data
hybrid deep learning models
ARIMA/SARIMA
convolution mechanisms
url https://ieeexplore.ieee.org/document/10949176/
work_keys_str_mv AT syedmujtabahussaine forecastingtunnelinducedgroundsettlementahybriddeeplearningapproachandtraditionalstatisticaltechniqueswithsensordata
AT linlongmu forecastingtunnelinducedgroundsettlementahybriddeeplearningapproachandtraditionalstatisticaltechniqueswithsensordata
AT yiminlu forecastingtunnelinducedgroundsettlementahybriddeeplearningapproachandtraditionalstatisticaltechniqueswithsensordata
AT syedsajidhussain forecastingtunnelinducedgroundsettlementahybriddeeplearningapproachandtraditionalstatisticaltechniqueswithsensordata