Model-Agnostic Meta-Learning in Predicting Tunneling-Induced Surface Ground Deformation
Abstract
1. Introduction
2. Measurement
2.1. Site Conditions and Geological Conditions
2.2. Surface Ground Settlement
3. Methodology
3.1. Predictive Model Architectures Based on Model-Agnostic Meta-Learning
3.2. Models Setting and Evaluation Metrics
4. Results and Discussion
4.1. Overall Performance of MAML-BPNN
4.2. Overall Performance of MAML-LSTM
4.3. Parameter Analysis
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- He, W.; Kong, X.; Tang, L.; Chen, W.; Hu, W.; Chen, G. A Preliminary Study on Mitigation Techniques for 3D Deformation of Adjacent Buildings Induced by Tunnelling in Water-Rich Strata: A Case. Symmetry 2024, 16, 1339. [Google Scholar] [CrossRef]
- Tang, S.; Zhang, X.; Liu, Q.; Xie, W.; Wu, X.; Chen, P.; Qian, Y. Control and prevention of gas explosion in soft ground tunneling using slurry shield TBM. Tunn. Undergr. Space Technol. 2021, 113, 103963. [Google Scholar] [CrossRef]
- Liu, Z.; Xue, J.; Ye, J.; Qian, J. A simplified two-stage method to estimate the settlement and bending moment of upper tunnel considering the interaction of undercrossing twin tunnels. Transp. Geotech. 2021, 29, 100558. [Google Scholar] [CrossRef]
- Chen, R.P.; Song, X.; Meng, F.Y.; Wu, H.N.; Lin, X.T. Analytical approach to predict tunneling-induced subsurface settlement in sand considering soil arching effect. Comput. Geotech. 2022, 141, 104492. [Google Scholar] [CrossRef]
- Farrell, R.; Mair, R.; Sciotti, A.; Pigorini, A. Building response to tunnelling. Soils Found. 2014, 54, 269–279. [Google Scholar] [CrossRef]
- Park, K.H. Analytical solution for tunnelling-induced ground movement in clays. Tunn. Undergr. Space Technol. 2005, 20, 249–261. [Google Scholar] [CrossRef]
- Cao, L.; Zhang, D.; Fang, Q.; Yu, L. Movements of ground and existing structures induced by slurry pressure-balance tunnel boring machine (SPB TBM) tunnelling in clay. Tunn. Undergr. Space Technol. 2020, 97, 103278. [Google Scholar] [CrossRef]
- Liang, J.; Liu, W.; Yin, X.; Li, W.; Yang, Z.; Yang, J. Experimental study on the performance of shield tunnel tail grout in ground. Undergr. Space 2025, 20, 277–292. [Google Scholar] [CrossRef]
- Bayen, A.; Samanta, M. Assessment of Building Response Supported on Shallow Foundation Due to Tunnelling in Cohesionless Soil. IOP Conf. Ser. Earth Environ. Sci. 2024, 1333, 012044. [Google Scholar] [CrossRef]
- Franza, A.; Ritter, S.; Dejong, M.J. Continuum solutions for tunnel–building interaction and a modified framework for deformation prediction. Géotechnique 2020, 70, 108–122. [Google Scholar] [CrossRef]
- Liang, R.; Zhang, Z.; Wu, J.; Li, Z.; Cao, S.; Wu, W. Probabilistic assessment of existing shield tunnel longitudinal responses to tunnelling. Int. J. Numer. Anal. Methods Géoméch. 2024, 48, 2493–2520. [Google Scholar] [CrossRef]
- Liu, W.; Liang, J.; Xu, T. Tunnelling-induced ground deformation subjected to the behavior of tail grouting materials. Tunn. Undergr. Space Technol. 2023, 140, 105253. [Google Scholar] [CrossRef]
- Liu, Y.; Liao, S.; Chen, L.; Liu, M. Structural responses of DOT tunnel induced by shield under-crossing in close proximity in soft ground. Part I: Field measurement. Tunn. Undergr. Space Technol. 2022, 128, 104623. [Google Scholar]
- Bilotta, E.; Stallebrass, S.E. Prediction of stresses and strains around model tunnels with adjacent embedded walls in overconsolidated clay. Comput. Geotech. 2009, 36, 1049–1057. [Google Scholar] [CrossRef]
- Khabbaz, H.; Gibson, R.; Fatahi, B. Effect of constructing twin tunnels under a building supported by pile foundations in the Sydney central business district. Undergr. Space 2019, 4, 261–276. [Google Scholar] [CrossRef]
- Li, Y.; Zhang, W. Investigation on passive pile responses subject to adjacent tunnelling in anisotropic clay. Comput. Geotech. 2020, 127, 103782. [Google Scholar] [CrossRef]
- Masini, L.; Rampello, S.; Soga, K. An Approach to Evaluate the Efficiency of Compensation Grouting. J. Geotech. Geoenvironmental Eng. 2014, 140, 04014073. [Google Scholar] [CrossRef]
- Bilotta, E.; Russo, G. Use of a Line of Piles to Prevent Damages Induced by Tunnel Excavation. J. Geotech. Geoenvironmental Eng. 2011, 137, 254–262. [Google Scholar] [CrossRef]
- Bai, Y.; Yang, Z.; Jiang, Z. Key protection techniques adopted and analysis of influence on adjacent buildings due to the Bund Tunnel construction. Tunn. Undergr. Space Technol. 2014, 41, 24–34. [Google Scholar] [CrossRef]
- Chen, R.P.; Zhang, P.; Kang, X.; Zhong, Z.Q.; Liu, Y.; Wu, H.N. Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods. Soils Found. 2019, 59, 284–295. [Google Scholar] [CrossRef]
- Hasanipanah, M.; Noorian-Bidgoli, M.; Jahed Armaghani, D.; Khamesi, H. Feasibility of PSO-ANN model for predicting surface settlement caused by tunneling. Eng. Comput. 2016, 32, 705–715. [Google Scholar] [CrossRef]
- Zhang, L.; Wu, X.; Ji, W.; AbouRizk, S.M. Intelligent approach to estimation of tunnel-induced ground settlement using wavelet packet and support vector machines. J. Comput. Civ. Eng. 2017, 31, 04016053. [Google Scholar] [CrossRef]
- Lei, X.; Sun, L.; Xia, Y. Lost data reconstruction for structural health monitoring using deep convolutional generative adversarial networks. Struct. Health Monit. 2021, 20, 2069–2087. [Google Scholar] [CrossRef]
- Lei, X.; Sun, Z.; Wang, A.; Guo, T.; Nagayama, T. Estimation of Bridge Girder Cumulative Displacement for Component Operational Warning Using Bayesian Neural Networks. Struct. Control. Health Monit. 2025, 2025, 9974584. [Google Scholar] [CrossRef]
- Sahoo, S.; Russo, T.A.; Elliott, J.; Foster, I. Machine learning algorithms for modeling groundwater level changes in agricultural regions of the United States. Water Resour. Res. 2017, 53, 3878–3895. [Google Scholar] [CrossRef]
- Zhang, N.; Zhou, A.; Pan, Y.; Shen, S.L. Measurement and prediction of tunnelling-induced ground settlement in karst region by using expanding deep learning method. Measurement 2021, 183, 109700. [Google Scholar] [CrossRef]
- Hu, D.; Hu, Y.; Hu, R.; Tan, Z.; Ni, P.; Chen, Y.; Xiang, X.J.; Li, Y.S.; Liu, J. Machine Learning–Finite Element Mesh Optimization-Based Modeling and Prediction of Excavation-Induced Shield Tunnel Ground Settlement. Int. J. Comput. Methods 2024, 22, 2450066. [Google Scholar] [CrossRef]
- Zhang, N.; Shen, S.L.; Zhou, A.; Jin, Y.F. Application of lstm approach for modelling stress–strain behaviour of soil. Appl. Soft Comput. 2021, 100, 106959. [Google Scholar] [CrossRef]
- Samek, W.; Montavon, G.; Vedaldi, A.; Hansen, L.K.; Müller, K.-R. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning; Springer: London, UK, 2019. [Google Scholar]
- Verma, V.K.; Liang, K.; Mehta, N.; Carin, L. Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning. In Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 3–7 January 2024. [Google Scholar]
- Griffiths, D.V.; Fenton, G.A. Probabilistic slope stability analysis by finite elements. J. Geotech. Geoenvironmental Eng. 2004, 130, 507–518. [Google Scholar] [CrossRef]
- Griffiths, D.V.; Fenton, G.A. Probabilistic Settlement Analysis by Stochastic and Random Finite-Element Methods. J. Geotech. Geoenvironmental Eng. 2009, 135, 1629–1637. [Google Scholar] [CrossRef]
- Pan, Y.; Liu, Y.; Tyagi, A.; Lee, F.H.; Li, D.Q. Model-independent strength-reduction factor for effect of spatial variability on tunnel with improved soil surrounds. Géotechnique 2021, 71, 406–422. [Google Scholar] [CrossRef]
- Liu, D.; Zhang, W.; Duan, K.; Zuo, J.; Li, M.; Zhang, X.; Liang, X. Intelligent prediction and optimization of ground settlement induced by shield tunneling construction. Tunn. Undergr. Space Technol. 2025, 160, 106486. [Google Scholar] [CrossRef]
- Sha, F.; Zhang, M.; Dong, Y.; Wang, Q.; Ni, L. A review on the key factors influencing the stability of shield tunneling. KSCE J. Civ. Eng. 2025; in press. [Google Scholar]
- Su, J.; Wang, Y.; Niu, X.; Sha, S.; Yu, J. Prediction of ground surface settlement by shield tunneling using XGBoost and Bayesian Optimization. Eng. Appl. Artif. Intell. 2022, 114, 105020. [Google Scholar] [CrossRef]
- Santos, O.J.; Celestino, T.B. Artificial neural networks analysis of são paulo subway tunnel settlement data. Tunn. Undergr. Space Technol. 2008, 23, 481–491. [Google Scholar] [CrossRef]
- Duchi, J.; Hazan, E.; Singer, Y. Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn Res. 2011, 12, 2121–2159. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. Int. Conf. Learn 2015, 5, 1–13. [Google Scholar]
- Nash, J.E.; Sutcliffe, J.V. River flow forecasting through conceptual models part I—A discussion of principles. J. Hydrol. 1970, 10, 282–290. [Google Scholar] [CrossRef]
MAML-BPNN and MAML-BPNN | |
---|---|
Weight decay | 0.0005 |
Base-learning rate | 0.001 |
Meta-learning rate | 0.001 |
Epochs (MAML-BPNN) | 66,220 |
Epochs (MAML-LSTM) | 102,580 |
Inner steps in base-training stage | 5 |
The method of adjusted learning rate | The cosine function adjusts the learning rate, i.e., CosineAnnealingLR scheduler, with the length of the period being 20. |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
He, W.; Chen, G.-B.; Qian, W.; Chen, W.-L.; Tang, L.; Kong, X. Model-Agnostic Meta-Learning in Predicting Tunneling-Induced Surface Ground Deformation. Symmetry 2025, 17, 1220. https://doi.org/10.3390/sym17081220
He W, Chen G-B, Qian W, Chen W-L, Tang L, Kong X. Model-Agnostic Meta-Learning in Predicting Tunneling-Induced Surface Ground Deformation. Symmetry. 2025; 17(8):1220. https://doi.org/10.3390/sym17081220
Chicago/Turabian StyleHe, Wei, Guan-Bin Chen, Wenlian Qian, Wen-Li Chen, Liang Tang, and Xiangxun Kong. 2025. "Model-Agnostic Meta-Learning in Predicting Tunneling-Induced Surface Ground Deformation" Symmetry 17, no. 8: 1220. https://doi.org/10.3390/sym17081220
APA StyleHe, W., Chen, G.-B., Qian, W., Chen, W.-L., Tang, L., & Kong, X. (2025). Model-Agnostic Meta-Learning in Predicting Tunneling-Induced Surface Ground Deformation. Symmetry, 17(8), 1220. https://doi.org/10.3390/sym17081220