Application of machine learning for predicting ground surface settlement beneath road embankments

Document Type : Research Paper


1 Department of Civil Engineering, Politeknik Ungku Omar,Jalan, Raja Musa Mahadi, 31400 Ipoh, Perak, Malaysia

2 Department of Surveying Science & Geomatics, Faculty of Architecture, Planning & Surveying, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia

3 Faculty of Architecture, Planning & Surveying, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia

4 Malaysia Institute of Transport (MITRANS), Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia


Predicting the maximum ground surface settlement (MGS) beneath road embankments is crucial for safe operation, particularly on soft foundation soils. Despite having been explored to some extent, this problem still has not been solved due to its inherent complexity and many effective factors. This study applied support vector machines (SVM) and artificial neural networks (ANN) to predict MGS. A total of four kernel functions are used to develop the SVM model, which is linear, polynomial, sigmoid, and Radial Basis Function (RBF). MGS was analysed using the finite element method (FEM) with three dimensionless variables: embankment height, applied surcharge, and side slope. In comparison to the other kernel functions, the Gaussian produced the most accurate results (MARE = 0.048, RMSE = 0.007). The SVM-RBF testing results are compared to those of the ANN presented in this study. As a result, SVM-RBF proved to be better than ANN when predicting MGS.


[1] K. Ahangari, S. R. Moeinossadat, and D. Behnia, Estimation of tunnelling-induced settlement by modern intelligent methods, Soils Found., 55, (4) (2015) 737–748, doi: 10.1016/j.sandf.2015.06.006.
[2] D. Basak, S. Pal, and D. C. Patranabis, Support vector regression, Neural Inf. Process. Rev., 11 (10)(2007)
[3] A. Bobet, Analytical Solutions for Shallow Tunnels in Saturated Ground, J. Eng. Mech., 127 (12)(2001) 1258–1266,
doi: 10.1061/(ASCE)0733-9399(2001)127:12(1258).
[4] A. F. Cabalar, A. Cevik, and C. Gokceoglu, Some applications of Adaptive Neuro-Fuzzy Inference System (ANFIS)
in geotechnical engineering, Comput. Geotech., 40 (2012) 14–33, doi: 10.1016/j.compgeo.2011.09.008.
[5] R. P. Chen, J. Zhu, W. Liu, and X. W. Tang, Ground movement induced by parallel EPB tunnels in silty soils,
Tunn. Undergr. Sp. Technol., 26 (1)(2011) 163–171, doi: 10.1016/j.tust.2010.09.004.
[6] C. Cortes and V. Vapnik, Support-vector networks, Mach. Learn., 20 (3)(1995) 273–297, doi: 10.1007/BF00994018.[7] S. R. Dindarloo and E. Siami-Irdemoosa, Maximum surface settlement based classification of shallow tunnels in
soft ground, Tunn. Undergr. Sp. Technol., 49 (2015) 320–327, doi: 10.1016/j.tust.2015.04.021.
[8] A. M. Ghaedi and A. Vafaei, Applications of artificial neural networks for adsorption removal of dyes from aqueous
solution: A review, Adv. Colloid Interface Sci., vol. 245, no. April, (2017) 20–39, doi: 10.1016/j.cis.2017.04.015.
[9] S. R. Gunn, Support vector machines for classification and regression, Southampton, 1998.
[10] S. Hansbo, Consolidation of clay by band-shaped prefabricated vertical drains, Gr. Eng., 12, (5)(1979) 16–27.
[11] Y. Huang, J. Li, and J. Fu, Review on Application of Artificial Intelligence in Civil Engineering, Comput. Model.
Eng. Sci., 121 (3) (2019) 845–875, doi: 10.32604/cmes.2019.07653.
[12] G. T. K. Lee and C. W. W. Ng, Effects of Advancing Open Face Tunneling on an Existing Loaded Pile, J. Geotech.
Geoenvironmental Eng., 131 (2)(2005) 193–201, doi: 10.1061/(ASCE)1090-0241(2005)131:2(193).
[13] L. Liu, H. Moayedi, A. S. A. Rashid, S. S. A. Rahman, and H. Nguyen, Optimizing an ANN model with genetic
algorithm (GA) predicting load-settlement behaviours of eco-friendly raft-pile foundation (ERP) system, Eng.
Comput., 36 (1) (2020) 421–433, doi: 10.1007/s00366-019-00767-4.
[14] N.-V. Luat, V.-Q. Nguyen, S. Lee, and K. Lee, An evolutionary hybrid optimization of MARS model in
predicting settlement of shallow foundations on sandy soils, Geomech. Eng., 21 (6)(2020) 583–598, doi:
[15] R. C. Mamat, A. M. Samad, A. Kasa, S. F. M. Razali, A. Ramli, and M. B. H. C. Omar, Slope stability prediction
of road embankment on soft ground treated with prefabricated vertical drains using artificial neural network, IAES
Int. J. Artif. Intell., 9 (2)(2020) 236–243, doi: 10.11591/ijai.v9.i2.pp236-243.
[16] R. C. Mamat, A. Kasa, S. F. M. Razali, A. M. Samad, A. Ramli, and M. R. M. Yazid, Application of artificial intelligence in predicting ground settlement on earth slope, AIP Conf. Proc., 2138 (2019) 040015, doi:
[17] R. C. Mamat, A. Ramli, A. M. Samad, A. Kasa, S. F. M. Razali, and M. B. H. C. Omar, Artificial neural networks
in slope of road embankment stability applications: a review and future perspectives, Int. J. Adv. Technol. Eng.
Explor., 8 (75)(2021). 304–319, doi: 10.19101/IJATEE.2020.762127.
[18] S. Men, L. Yan, J. Liu, H. Qian, and Q. Luo, A Classification Method for Seed Viability Assessment with Infrared
Thermography, Sensors, 17 (4) (2017) 845, doi: 10.3390/s17040845.
[19] M. R. Moghaddasi and M. Noorian-Bidgoli, ICA-ANN, ANN and multiple regression models for prediction of surface settlement caused by tunneling, Tunn. Undergr. Sp. Technol., 79 (2018) 197–209, doi:
[20] M. Mohammed, A. Sharafati, N. Al-Ansari, and Z. M. Yaseen, Shallow Foundation Settlement Quantification:
Application of Hybridized Adaptive Neuro-Fuzzy Inference System Model, Adv. Civ. Eng., (2020) 7381617, doi:
[21] J. A. Nasiri, N. M. Charkari, and S. Jalili, Least squares twin multi-class classification support vector machine,
Pattern Recognit., 48 (3) (2015) 984–992, doi: 10.1016/j.patcog.2014.09.020.
[22] O. Okwuashi and C. Ndehedehe, Tide modelling using support vector machine regression, J. Spat. Sci., 62 (1)
(2017) 29–46, doi: 10.1080/14498596.2016.1215272.
[23] A. Pourtaghi and M. A. Lotfollahi-Yaghin, Wavenet ability assessment in comparison to ANN for predicting
the maximum surface settlement caused by tunneling, Tunn. Undergr. Sp. Technol., 28 (1)(2012) 257–271, doi:
[24] A. J. Smola and B. Sch¨olkopf, A tutorial on support vector regression, Stat. Comput., 14 (3)(2004) pp. 199–222,
doi: 10.1023/B:STCO.0000035301.49549.88.
[25] L. V. Utkin and Y. A. Zhuk, An one-class classification support vector machine model by interval-valued training
data, Knowledge-Based Syst., 120 (2017) 43–56, doi: 10.1016/j.knosys.2016.12.022.
[26] A. Verruijt and J. R. Booker, Surface settlements due to deformation of a tunnel in an elastic half plane,
G´eotechnique, 46 (4) (1996) 753–756, doi: 10.1680/geot.1996.46.4.753.
[27] F. Wang, B. Gou, and Y. Qin, Modeling tunneling-induced ground surface settlement development using a wavelet smooth relevance vector machine, Comput. Geotech., 54 (2013) 125–132, 2013, doi:
[28] C. Yoo, Settlement behavior of embankment on geosynthetic-encased stone column installed soft ground – A
numerical investigation, Geotext. Geomembranes, 43 (6) (2015) 484–492, doi: 10.1016/j.geotexmem.2015.07.014.
[29] P. Zhang, H.-N. Wu, R.-P. Chen, and T. H. T. Chan, Hybrid meta-heuristic and machine learning algorithms for
tunneling-induced settlement prediction: A comparative study, Tunn. Undergr. Sp. Technol., 99 (2020) 103383,
doi: 10.1016/j.tust.2020.103383.
[30] L. Zhang, M. Zhao, Y. Hu, H. Zhao, and B. Chen, Semi-analytical solutions for geosynthetic-reinforced and
pile-supported embankment, Comput. Geotech., 44 (2012) 167–175, doi: 10.1016/j.compgeo.2012.04.001.[31] J. Zhou, X. Sh, K. Du, X. Qiu, X. Li, and H. S. Mitri, Feasibility of random-forest approach for prediction of
ground settlements induced by the construction of a shield-driven tunnel, Int. J. Geomech., 17 (6) (2017), doi:
[32] Y. Zhou, W. Su, L. Ding, and H. Luo, Predicting Safety Risks in Deep Foundation Pits in Subway Infrastructure Projects: Support Vector Machine Approach, J. Comput. Civ. Eng., 31 (5) (2017) 04017052, doi:
Volume 12, Special Issue
December 2021
Pages 1025-1034
  • Receive Date: 18 June 2021
  • Revise Date: 06 July 2021
  • Accept Date: 11 September 2021