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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |