Paper contribution

Early Warning of Ground Settlement and Sensitivity Analysis for Super-large Earth Pressure Balance Shield

Jie Wang; Yadong Xue; Wei Luo; Wei Wang; Shouzeng Jiao; Jie Tang

Proceedings
EUROCK 2026
Pages
1329-1334
Submitted
28 January 2026
Accepted
15 June 2026
Published
12 August 2026

Summary

Abstract

Ground settlement induced by shield tunneling poses a potential risk to adjacent structures and the surface environment, making early warning systems and analysis of influencing factors for settlement essential for effective risk management. This study develops a dynamic early warning method for surface settlement during shield tunneling, based on the Temporal Fusion Transformer (TFT) model, which integrates multiple factors through spatiotemporal fusion. The method places particular emphasis on the effects of surface reinforcement and tunneling-induced ground disturbances, providing a high-precision prediction of surface settlement trends over three time steps. Additionally, by incorporating the attention mechanism into the TFT model, an importance analysis of the key influencing factors on surface settlement is conducted, identifying the most significant contributors to settlement dynamics. The case study results demonstrate that the TFT model effectively integrates various construction factors, achieving an average prediction accuracy of 0.892 over three time steps, surpassing conventional time-series models such as LSTM and Transformer in performance. The sensitivity analysis results indicate that key factors such as stratum loss and total grouting volume are critical in influencing surface settlement, with their impact varying at different construction stages. This approach provides a science-based strategy for preventive risk mitigation in urban infrastructure development.

Contributors

Authors

  1. Jie Wang Department of Geotechnical Engineering, Tongji University, Shanghai, China; Key Laboratory of Geotechnical and Underground Engineering of Minister of Education and Department of Geotechnical Engineering, Tongji University, Shanghai, China
  2. Yadong Xue Department of Geotechnical Engineering, Tongji University, Shanghai, China; Key Laboratory of Geotechnical and Underground Engineering of Minister of Education and Department of Geotechnical Engineering, Tongji University, Shanghai, China ORCID 0009-0001-7587-5763
  3. Wei Luo Department of Geotechnical Engineering, Tongji University, Shanghai, China; Key Laboratory of Geotechnical and Underground Engineering of Minister of Education and Department of Geotechnical Engineering, Tongji University, Shanghai, China
  4. Wei Wang China Railway Shanghai Engineering Group Co., Ltd., Shanghai, China
  5. Shouzeng Jiao China Railway Shanghai Engineering Group Co., Ltd., Shanghai, China
  6. Jie Tang China Railway Shanghai Engineering Group Co., Ltd., Shanghai, China

Index terms

Keywords

Full text

Attachments

Works cited

References

  1. Hong C Y, Guo Y, Chen W B, et al. (2025) Calculation method for surface settlement induced by large-diameter shield tunneling considering multiple parameters. China Journal of Highway and Transport 38(9): 180-190.
  2. Kim D, Pham K, Oh J Y, Lee S J, Choi H (2022) Classification of surface settlement levels induced by TBM driving in urban areas using random forest with data-driven feature selection. Automation in Construction 135: 104109.
  3. Lim B, Arık S Ö, Loeff N, Pfister T (2021) Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting 37(4): 1748-1764.
  4. Lu D C, Ma Y D, Kong F C, Guo C X, Miao J B, Du X L (2023) Support vector regression with heuristic optimization algorithms for predicting the ground surface displacement induced by EPB shield tunneling. Gondwana Research 123: 3-15.
  5. Su J, Wang Y Z, Niu X K, Sha S, Yu J Y (2022) Prediction of ground surface settlement by shield tunneling using XGBoost and Bayesian optimization. Engineering Applications of Artificial Intelligence 114: 105020.
  6. Suwansawat S, Einstein H H (2006) Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling. Tunnelling and Underground Space Technology 21(2): 133-150.
  7. Xue Y D, Zhang W, Wang Y L, Luo W, Jia F, Li S T, Pang H J (2023) Serviceability evaluation of highway tunnels based on data mining and machine learning: a case study of continental United States. Tunnelling and Underground Space Technology 142: 105418.
  8. Zhao S S, Feng X D, et al. (2025) Prediction and parameter optimization of surface settlement induced by shield tunneling using improved Informer algorithm. Applied Sciences 15(12): 6766.
  9. Zhu D, Jiang G L, Liu X F, Yuan S, Yu T, Shen Y, Luo J (2025) Efficient Bayesian updating based on surrogate model and monitoring data for dynamic subgrade settlement prediction. International Journal of Rail Transportation: 1-29.