Hybrid Random Forest-Based Models for Earth Pressure Balance Tunneling-Induced Ground Settlement Prediction
Source abstract
Abstract
Construction-induced ground settlement is a serious hazard in underground tunnel construction. Accurate ground settlement prediction has great significance in ensuring the surface building’s stability and human safety. To that end, 148 sets of data were collected from the Singapore Circle Line rail traffic project containing seven defining parameters to create a database for predicting ground settlement. These parameters are the tunnel depth (H), the tunnel advance rate (AR), the EPB earth pressure (EP), the mean SPTN value from the soil crown to the surface (Sm), the mean water content of the soil layer (MC), the mean modulus of elasticity of the soil layer (E), and the grout pressure used for injecting grout into the tail void (GP). Three hybrid models consisting of random forest (RF) and three types of meta-heuristics, Ant Lion Optimizier (ALO), Multi-Verse Optimizer (MVO), and Grasshopper Optimization Algorithm (GOA), were developed to predict ground settlement. Furthermore, the mean absolute error (MAE), the mean absolute percentage error (MAPE), the coefficient of determination (R2) and the root mean square error (RMSE) were used to assess predictive performance of the constructed models for predicting ground settlement. The evaluation results demonstrated that the GOA-RF with a population size of 10 has achieved the most outstanding predictive capability with the indices of MAE (Training set: 2.8224; Test set: 2.3507), MAPE (Training set: 40.5629; Test set: 38.5637), R2 (Training set: 0.9487; Test set: 0.9282), and RMSE (Training set: 4.93; Test set: 3.1576). Finally, the sensitivity analysis results indicated that MC, AR, Sm, and GP have a significant impact on ground settlement prediction based on the GOA-RF model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geotechnical Engineering and Analysis · Geotechnical Engineering and Underground Structures · Tunneling and Rock Mechanics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Resources and Safety Engineering, Central South University, Changsha 410083, China
Laboratory 3SR, CNRS UMR 5521, Grenoble Alpes University, 38000 Grenoble, France
Norin Mining Ltd., Beijing 100053, China
Funding
National Natural Science Foundation Project of China · Distinguished Youth Science Foundation of Hunan Province of China
References (96)
Show source-provided references
1. Research trends in information technology applications in construction safety engineering and management10.15302/J-FEM-2014034 ↗
2. Strategies to reduce ground settlement from shallow tunnel excavation: A case study in China10.1061/(ASCE)CO.1943-7862.0001087 ↗
3. Analysis and design of partial ground improvement in deep excavations10.1016/j.compgeo.2007.09.005 ↗
4. Deep excavation-induced ground surface movement characteristics—A numerical investigation10.1016/j.compgeo.2007.05.002 ↗
5. Maximum surface settlement based classification of shallow tunnels in soft ground10.1016/j.tust.2015.04.021 ↗
6. Shield tunneling and environment protection in Shanghai soft ground10.1016/j.tust.2008.12.005 ↗
7. Treatment of uncertainty in risk assessments in the Rogfast road tunnel project10.1016/j.ssci.2012.12.012 ↗
8. 3-D strong tilting observed in tall, isolated brick chimneys during the excavation of the Athens Metro10.1007/s12518-014-0138-8 ↗
9. Probabilistic analysis of tunneling-induced building safety assessment using a hybrid FE-copula model10.1080/15732479.2017.1386691 ↗
10. O’Reilly, M.P., and New, B.M. (1982). Settlements above Tunnels in the United Kingdom—Their Magnitude and Prediction, Institution of Mining Metallurgy. No. Monograph.
11. Peck, R.B. (1969, January 29). Deep excavations and tunneling in soft ground. Proceedings of the 7th International Conference on Soil Mechanics and Foundation Engineering (Mexico), Mexico City, Mexico.
12. Analytical prediction for tunneling-induced ground movements in clays10.1061/(ASCE)1090-0241(1998)124:9(846) ↗
13. A 3D finite element simulation model for TBM tunnelling in soft ground10.1002/nag.395 ↗
14. Settlements induced by tunneling in soft ground10.1016/j.tust.2006.11.001 ↗
15. Neural network based prediction of ground surface settlements due to tunnelling10.1016/S0266-352X(01)00011-8 ↗
16. Calculation of surface settlements caused by EPBM tunneling using artificial neural network, SVM, and Gaussian processes10.1007/s12665-012-2214-x ↗
17. Modeling tunneling-induced ground surface settlement development using a wavelet smooth relevance vector machine10.1016/j.compgeo.2013.07.004 ↗
18. Feasibility of random-forest approach for prediction of ground settlements induced by the construction of a shield-driven tunnel10.1061/(ASCE)GM.1943-5622.0000817 ↗
19. Zhou, J., Shi, X.Z., Du, K., Qiu, X.Y., Li, X.B., and Mitri, H.S. (2016, January 25–27). Development of the ground movements due to shield tunnelling prediction model using random forests. Proceedings of the 4th GeoChina International Conference, Shandong, China.10.1061/9780784480106.014 ↗
20. A critical evaluation of machine learning and deep learning in shield-ground interaction prediction10.1016/j.tust.2020.103593 ↗
21. Limitations in application of finite element method in acoustic numerical simulation
22. Ground deformations resulting from shield tunnelling in London Clay10.1139/t74-039 ↗
23. Prediction of ground settlements associated with shield tunnelling10.3208/sandf1972.18.4_47 ↗
24. Ground movements due to construction of cut and cover structures and slurry shield tunnel of the Cairo metro10.1016/S0886-7798(99)00044-9 ↗
25. Mair, R.J., and Taylor, R.N. (1999). International Society for Soil Mechanics and Foundation Engineering, Proceedings of the Fourteenth International Conference on Soil Mechanics and Foundation Engineering, Hamburg, Germany, 6–12 September 1997, CRC Press.
26. Surface settlement predictions for Istanbul Metro tunnels excavated by EPB-TBM10.1007/s12665-010-0530-6 ↗
27. Effects of important factors on surface settlement prediction for metro tunnel excavated by EPB10.1016/j.tust.2013.02.002 ↗
28. Analysis of undrained soil deformation due to ground loss10.1680/geot.1987.37.3.301 ↗
29. Surface settlements due to deformation of a tunnel in an elastic half plane10.1680/geot.1998.48.5.709 ↗
30. Effects of different tunnel face advance excavation on the settlement by FEM10.1016/S0886-7798(03)00068-3 ↗
31. FEM modelling of a large piled raft for settlement control in weak rock10.1016/j.engstruct.2007.02.001 ↗
32. A proposed methodology for analysis of ground settlements caused by tunneling, with particular reference to the “buoyancy” effect10.1016/j.tust.2010.07.004 ↗
33. Longitudinal settlement profile in shallow tunnels in drained conditions10.1061/(ASCE)GM.1943-5622.0000447 ↗
34. Settlement analysis of saturated tailings dam treated by CFG pile composite foundation
35. Back analysis for tunnelling induced ground movements and stress redistribution10.1016/j.tust.2005.02.007 ↗
36. Estimating maximum surface settlement due to EPBM tunneling by Numerical-Intelligent approach—A case study: Tehran subway line 710.1016/j.trgeo.2018.11.009 ↗
37. Settlement behaviors of existing tunnel caused by obliquely under-crossing shield tunneling in close proximity with small intersection angle10.1016/j.tust.2019.103258 ↗
38. Cui, X., Zhou, R., Guo, G., Du, B., and Liu, H. (2021). Effects of differential subgrade settlement on slab track deformation based on a DEM-FDM coupled approach. Appl. Sci., 11.10.3390/app11041384 ↗
39. Modeling of tunnel excavation using a hybrid DEM/BEM method10.1111/1467-8667.00284 ↗
40. Face stability analysis of shallow shield tunnels in dry sandy ground using the discrete element method10.1016/j.compgeo.2010.11.003 ↗
41. Use of a two-dimensional discrete-element line-sink model to gain insight into tunnelling-induced deformations10.1680/geot.12.T.003 ↗
42. Liu, C., Pan, L., Wang, F., Zhang, Z., Cui, J., Liu, H., Duan, Z., and Ji, X. (2019). Three-dimensional discrete element analysis on tunnel face instability in cobbles using ellipsoidal particles. Materials, 12.10.3390/ma12203347 ↗
43. DEM simulation of rock creep in tunnels using Rate Process Theory10.1016/j.compgeo.2021.104559 ↗
44. Support vector machine applied to settlement of shallow foundations on cohesionless soils10.1016/j.compgeo.2007.06.014 ↗
45. Prediction of pile settlement using artificial neural networks based on standard penetration test data10.1016/j.compgeo.2009.04.003 ↗
46. Le, L.T., Nguyen, H., Dou, J., and Zhou, J. (2019). A comparative study of PSO-ANN, GA-ANN, ICA-ANN, and ABC-ANN in estimating the heating load of buildings’ energy efficiency for smart city planning. Appl. Sci., 9.10.3390/app9132630 ↗
47. Six novel hybrid extreme learning machine–swarm intelligence optimization (ELM–SIO) models for predicting backbreak in open-pit blasting10.1007/s11053-022-10082-3 ↗
48. Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration10.1007/s00366-021-01393-9 ↗
49. Zhou, J., Dai, Y., Huang, S., Armaghani, D.J., and Qiu, Y. (2022). Proposing several hybrid SSA—Machine learning techniques for estimating rock cuttability by conical pick with relieved cutting modes. Acta Geotech., 1–16.10.1007/s11440-022-01685-4 ↗
50. COSMA-RF: New intelligent model based on chaos optimized slime mould algorithm and random forest for estimating the peak cutting force of conical picks10.1016/j.trgeo.2022.100806 ↗
51. Stability prediction of underground entry-type excavations based on particle swarm optimization and gradient boosting decision tree10.1016/j.undsp.2022.08.002 ↗
52. Modular neural networks for predicting settlements during tunneling10.1061/(ASCE)1090-0241(1998)124:5(389) ↗
53. Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling10.1016/j.tust.2005.06.007 ↗
54. Reliability assessment of EPB tunnel-related settlement10.12989/gae.2010.2.1.057 ↗
55. Artificial neural network application for the prediction of ground surface movements induced by shield tunnelling10.1139/T10-023 ↗
56. Simulation of longitudinal surface settlement due to tunnelling using artificial neural network
57. Wavenet ability assessment in comparison to ANN for predicting the maximum surface settlement caused by tunneling10.1016/j.tust.2011.11.008 ↗
58. Feasibility of PSO-ANN model for predicting surface settlement caused by tunneling10.1007/s00366-016-0447-0 ↗
59. Intelligent approach to estimation of tunnel-induced ground settlement using wavelet packet and support vector machines10.1061/(ASCE)CP.1943-5487.0000621 ↗
60. Prediction of maximum surface settlement caused by earth pressure balance shield tunneling using random forest
61. Determination of earth pressure balance tunnel-related maximum surface settlement: A multivariate adaptive regression splines approach10.1007/s10064-016-0937-8 ↗
62. Intelligent prediction of surrounding rock deformation of shallow buried highway tunnel and its engineering application10.1016/j.tust.2019.04.013 ↗
63. Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods10.1016/j.sandf.2018.11.005 ↗
64. Prediction of shield tunneling-induced ground settlement using machine learning techniques10.1007/s11709-019-0561-3 ↗
65. Evolutionary hybrid neural network approach to predict shield tunneling-induced ground settlements10.1016/j.tust.2020.103594 ↗
66. Hybrid meta-heuristic and machine learning algorithms for tunneling-induced settlement prediction: A comparative study10.1016/j.tust.2020.103383 ↗
67. Optimized adaptive neuro-fuzzy inference system using metaheuristic algorithms: Application of shield tunnelling ground surface settlement prediction10.1155/2021/6666699 ↗
68. Soft computing approach for prediction of surface settlement induced by earth pressure balance shield tunneling10.1016/j.undsp.2019.12.003 ↗
69. Random forests10.1023/A:1010933404324 ↗
70. Chen, Y., Yong, W., Li, C., and Zhou, J. (2022). Predicting the Thickness of an Excavation Damaged Zone around the Roadway Using the DA-RF Hybrid Model. Comput. Model. Eng. Sci., 1–20.10.32604/cmes.2023.025714 ↗
71. A hybrid metaheuristic approach using random forest and particle swarm optimization to study and evaluate backbreak in open-pit blasting10.1007/s00521-021-06776-z ↗
72. Random forest and bayesian network techniques for probabilistic prediction of flyrock induced by blasting in quarry sites10.1007/s11053-019-09611-4 ↗
73. Developing hybrid ELM-ALO, ELM-LSO and ELM-SOA models for predicting advance rate of TBM10.1016/j.trgeo.2022.100819 ↗
74. Yu, Z., Shi, X., Zhou, J., Chen, X., and Qiu, X. (2020). Effective assessment of blast-induced ground vibration using an optimized random forest model based on a Harris hawks optimization algorithm. Appl. Sci., 10.10.3390/app10041403 ↗
75. Zhang, H., Zhou, J., Jahed Armaghani, D., Tahir, M.M., Pham, B.T., and Huynh, V.V. (2020). A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration. Appl. Sci., 10.10.3390/app10030869 ↗
76. Zhou, J., Li, E., Wei, H., Li, C., Qiao, Q., and Armaghani, D.J. (2019). Random forests and cubist algorithms for predicting shear strengths of rockfill materials. Appl. Sci., 9.10.3390/app9081621 ↗
77. Prediction of ground vibration induced by blasting operations through the use of the Bayesian Network and random forest models10.1016/j.soildyn.2020.106390 ↗
78. Performance evaluation of hybrid YYPO-RF, BWOA-RF and SMA-RF models to predict plastic zones around underground powerhouse caverns10.1007/s40948-022-00496-x ↗
79. Optimization of random forest through the use of MVO, GWO and MFO in evaluating the stability of underground entry-type excavations10.1016/j.tust.2022.104494 ↗
80. Prediction of rockburst classification using Random Forest10.1016/S1003-6326(13)62487-5 ↗
81. Tao, H., Jingcheng, W., and Langwen, Z. (2015, January 23–25). Prediction of hard rock TBM penetration rate using random forests. Proceedings of the 27th Chinese Control and Decision Conference (2015 CCDC), Qingdao, China.10.1109/CCDC.2015.7162572 ↗
82. Effectiveness of predicting tunneling-induced ground settlements using machine learning methods with small datasets10.1016/j.jrmge.2021.08.018 ↗
83. The ant lion optimizer10.1016/j.advengsoft.2015.01.010 ↗
84. Multi-verse optimizer: A nature-inspired algorithm for global optimization10.1007/s00521-015-1870-7 ↗
85. The cyclic model simplified10.1016/j.newar.2005.01.003 ↗
86. Grasshopper optimisation algorithm: Theory and application10.1016/j.advengsoft.2017.01.004 ↗
87. Tunnelling projects in Singapore: An overview10.1016/S0886-7798(00)00004-3 ↗
88. Izumi, C., Khatri, N.N., Norrish, A., and Davies, R. (2017). Tunnels and Underground Structures, Routledge.
89. Local settlements and sinkholes due to EPB tunnelling10.1680/geng.2003.156.4.193 ↗
90. Geological and geotechnical features of Singapore: An overview10.1016/S0886-7798(00)00005-5 ↗
91. Prediction of blasting mean fragment size using support vector regression combined with five optimization algorithms10.1016/j.jrmge.2021.07.013 ↗
92. Predicting TBM penetration rate in hard rock condition: A comparative study among six XGB-based metaheuristic techniques10.1016/j.gsf.2020.09.020 ↗
93. Comparative performance of six supervised learning methods for the development of models of hard rock pillar stability prediction10.1007/s11069-015-1842-3 ↗
94. Classification of rockburst in underground projects: Comparison of ten supervised learning methods10.1061/(ASCE)CP.1943-5487.0000553 ↗
95. Summarizing multiple aspects of model performance in a single diagram10.1029/2000JD900719 ↗
96. A low-cost INS/GPS integration methodology based on random forest regression10.1016/j.eswa.2013.02.002 ↗