M5 Soft Computing Techniques for Assessment of Soil Liquefaction

Document Type : Regular Paper

Authors

1 Lecturer, Department of Civil Engineering, Pundra University of Science and Technology, Bangladesh

2 Lecturer, Department of Civil Engineering, Hajee Mohammad Danesh Science and Technology University, Bangladesh

Abstract

It is essential to precisely estimate the liquefaction potential because soil liquefaction is a factor that raises the quantity and intensity of losses in an earthquake. In the past, the prediction of soil liquefaction was based on multiple analytical inferences. The purpose of this research is to develop an M5 model for both classification and regression in order to investigate the suitability of the M5 decision tree for liquefaction assessment. Additionally, the divisional approaches of fuzzy clustering means (FCM), kfold clustering, and grid search cross-validation (Gridsearch CV) are investigated in order to create effective regression and classification models. In this work, specific models are developed using a data set of 200 boreholes from standard penetration tests on soils in the Dinajpur region. The efficacy of the constructed models is assessed using several performance measures, such as root mean squared error (RMSE), mean absolute error (MAE), and coefficient of correlation (R) for regression models, and accuracy, precision, and AUC value for classification models. Based on the results, it was found that the M5 decision tree regression model shows R = 0.95, IoA = 0.86, and IoS = 0.96 for testing and R = 0.93, IoA = 0.88, and IoS = 0.96 for training data. On the other hand, the classification model shows accuracy = 95%, recall = 1, and F1 score = 0.97 for testing and 98.75%, 1, and 0.99 for training, respectively. Both of these results were found for the Kfold technique, which predicts a more accurate value than other divisional approaches.

Graphical Abstract

M5 Soft Computing Techniques for Assessment of Soil Liquefaction

Highlights

  • This work aims to examine the applicability of M5 decision tree machine learning algorithms to predict liquefaction vulnerability.
  • Both classification and regression models have been developed to determine nonlinear relationships between the physical properties of the soil.
  • In this study, 200 data sets were used for different divisional approaches such as grid search cross validation (Gridsearch Cv), kfold clustering means, and fuzzy clustering means (FCM) to develop successful regression and classification models.
  • It was found that the developed M5 decision tree regression model shows R = 0.9471 for testing and R = 0.9297 for training.
  • The developed M5 decision tree classification model shows an accuracy of 95% for testing and 98.75% for training.
  • The Kfold cross-validation technique predicted a more accurate value compared to other divisional approaches.

Keywords

Main Subjects

References

[1]     Huang Y, Yu M. Review of soil liquefaction characteristics during major earthquakes of the twenty-first century. Nat Hazards 2013;65:2375–84. https://doi.org/10.1007/s11069-012-0433-9.
[2]     Castro G, Poulos SJ. Factors Affecting Liquefaction and Cyclic Mobility. J Geotech Eng Div 1977;103:501–16. https://doi.org/10.1061/AJGEB6.0000433.
[3]     Youd T. Major cause of earthquake damage is ground failure. Civ Eng 1978;48:47–51.
[4]     Bao X, Jin Z, Cui H, Chen X, Xie X. Soil liquefaction mitigation in geotechnical engineering: An overview of recently developed methods. Soil Dyn Earthq Eng 2019;120:273–91. https://doi.org/10.1016/j.soildyn.2019.01.020.
[5]     Youd TL, Idriss IM. Liquefaction Resistance of Soils: Summary Report from the 1996 NCEER and 1998 NCEER/NSF Workshops on Evaluation of Liquefaction Resistance of Soils. J Geotech Geoenvironmental Eng 2001;127:297–313. https://doi.org/10.1061/(ASCE)1090-0241(2001)127:4(297).
[6]     Ayasrah M, Qiu H, Zhang X, Daddow M. Prediction of Ground Settlement Induced by Slurry Shield Tunnelling in Granular Soils. Civ Eng J 2020;6:2273–89. https://doi.org/10.28991/cej-2020-03091617.
[7]     Youd JM, Newman JMB, Clark MG, Appleby GJ, Rattigan S, Tong ACY, et al. Increased metabolism of infused 1‐methylxanthine by working muscle. Acta Physiol Scand 1999;166:301–8. https://doi.org/10.1046/j.1365-201x.1999.00572.x.
[8]     Rahman MM, Hossain MB, Roknuzzaman M. Effect of peak ground acceleration (PGA) on liquefaction behavior of subsoil: A case study of Dinajpur Sadar Upazila, Bangladesh. AIP Conf. Proc., 2023, p. 030002. https://doi.org/10.1063/5.0129770.
[9]     Monkul MM, Gültekin C, Gülver M, Akın Ö, Eseller-Bayat E. Estimation of liquefaction potential from dry and saturated sandy soils under drained constant volume cyclic simple shear loading. Soil Dyn Earthq Eng 2015;75:27–36. https://doi.org/10.1016/j.soildyn.2015.03.019.
[10]   V. Galavi, A. Petalas RBJB. No Title n.d.
[11]    Goh AT. Probabilistic neural network for evaluating seismic liquefaction potential. Can Geotech J 2002;39:219–32. https://doi.org/10.1139/t01-073.
[12]   Chen Z, Li H, Goh ATC, Wu C, Zhang W. Soil Liquefaction Assessment Using Soft Computing Approaches Based on Capacity Energy Concept. Geosciences 2020;10:330. https://doi.org/10.3390/geosciences10090330.
[13]   Liu L, Zhang S, Yao X, Gao H, Wang Z, Shen Z. Liquefaction Evaluation Based on Shear Wave Velocity Using Random Forest. Adv Civ Eng 2021;2021:1–9. https://doi.org/10.1155/2021/3230343.
[14]   Talamkhani S, Naeini SA, Ardakani A. Prediction of Static Liquefaction Susceptibility of Sands Containing Plastic Fines Using Machine Learning Techniques. Geotech Geol Eng 2023;41:3057–74. https://doi.org/10.1007/s10706-023-02444-2.
[15]   MY F, LA A-H, MM A, AA J, SA A-H. Coupled Finite Element and Artificial Neural Network Analysis of Interfering Strip Footings in Saturated Cohesive Soils. Transp Infrastruct Geotechnol 2024;11:2168–85. https://doi.org/10.1007/s40515-023-00369-0.
[16]   Barkhordari MS, Fattahi H, Armaghani DJ, Khan NM, Afrazi M, Asteris PG. Failure mode identification in reinforced concrete flat slabs using advanced ensemble neural networks. Multiscale Multidiscip Model Exp Des 2024. https://doi.org/10.1007/s41939-024-00554-9.
[17]   Rahman M, Hossain M, Sayed A, Thakur S. Assesment of Liquefaction Potential Based on the Logistic Regression Machine Learning Algorithm. 7th Int. Conf. Civ. Eng. Sustain. Dev. (ICCESD 2024), 2024, p. 1–11. https://doi.org/10.13140/RG.2.2.24047.65440.
[18]   Goh ATC. Seismic Liquefaction Potential Assessed by Neural Networks. J Geotech Eng 1994;120:1467–80. https://doi.org/10.1061/(ASCE)0733-9410(1994)120:9(1467).
[19]   Pal M. Support vector machines-based modelling of seismic liquefaction potential. Int J Numer Anal Methods Geomech 2006;30:983–96. https://doi.org/10.1002/nag.509.
[20]   Samui P, Hariharan R. A unified classification model for modeling of seismic liquefaction potential of soil based on CPT. J Adv Res 2015;6:587–92. https://doi.org/10.1016/j.jare.2014.02.002.
[21]   Xue X, Liu E. Seismic liquefaction potential assessed by neural networks. Environ Earth Sci 2017;76:192. https://doi.org/10.1007/s12665-017-6523-y.
[22]   Ramakrishnan D, Singh TN, Purwar N, Barde KS, Gulati A, Gupta S. Artificial neural network and liquefaction susceptibility assessment: a case study using the 2001 Bhuj earthquake data, Gujarat, India. Comput Geosci 2008;12:491–501. https://doi.org/10.1007/s10596-008-9088-8.
[23]   Venkatesh K, Kumar V, Tiwari RP. APPRAISAL OF LIQUEFACTION POTENTIAL USING NEURAL NETWORK AND NEURO FUZZY APPROACH. Appl Artif Intell 2013;27:700–20. https://doi.org/10.1080/08839514.2013.823326.
[24]   Zhang Y, Qiu J, Zhang Y, Wei Y. The adoption of ELM to the prediction of soil liquefaction based on CPT. Nat Hazards 2021;107:539–49. https://doi.org/10.1007/s11069-021-04594-z.
[25]   Samui P, Sitharam TG. Machine learning modelling for predicting soil liquefaction susceptibility. Nat Hazards Earth Syst Sci 2011;11:1–9. https://doi.org/10.5194/nhess-11-1-2011.
[26]   Kumar DR, Samui P, Burman A. Prediction of Probability of Liquefaction Using Soft Computing Techniques. J Inst Eng Ser A 2022;103:1195–208. https://doi.org/10.1007/s40030-022-00683-9.
[27]   Kohestani VR, Hassanlourad M, Ardakani A. Evaluation of liquefaction potential based on CPT data using random forest. Nat Hazards 2015;79:1079–89. https://doi.org/10.1007/s11069-015-1893-5.
[28]   Zou M, Jiang W-G, Qin Q-H, Liu Y-C, Li M-L. Optimized XGBoost Model with Small Dataset for Predicting Relative Density of Ti-6Al-4V Parts Manufactured by Selective Laser Melting. Materials (Basel) 2022;15:5298. https://doi.org/10.3390/ma15155298.
[29]   Momeni E, Jahed Armaghani D, Hajihassani M, Mohd Amin MF. Prediction of uniaxial compressive strength of rock samples using hybrid particle swarm optimization-based artificial neural networks. Measurement 2015;60:50–63. https://doi.org/10.1016/j.measurement.2014.09.075.
[30]   Mostazid M, Rahman M, Rahman M. Seismic Vulnerability Assessment of Existing RCC Buildings in Dinajpur City: A Case Study on Ward No. 06. Proc. Int. Conf. Planning, Archit. Civ. Eng., 2019, p. 1–6.
[31]   Oldham RD. Report on the great earthquake of 12th June 1897. 1899.
[32]   Stuart M. The Srimangal earthquake of 8th July 1918. Mem Geo Surv India 1920;46:1–70.
[33]   Hossain MS, Kamal ASMM, Rahman MZ, Farazi AH, Mondal DR, Mahmud T, et al. Assessment of soil liquefaction potential: a case study for Moulvibazar town, Sylhet, Bangladesh. SN Appl Sci 2020;2:777. https://doi.org/10.1007/s42452-020-2582-x.
[34]   Hossain MB, Roknuzzaman M, Rahman MM. Liquefaction Potential Evaluation by Deterministic and Probabilistic Approaches. Civ Eng J 2022;8:1459–81. https://doi.org/10.28991/CEJ-2022-08-07-010.
[35]   Morino M, Maksud Kamal ASM, Muslim D, Ekram Ali RM, Kamal MA, Zillur Rahman M, et al. Seismic event of the Dauki Fault in 16th century confirmed by trench investigation at Gabrakhari Village, Haluaghat, Mymensingh, Bangladesh. J Asian Earth Sci 2011;42:492–8. https://doi.org/10.1016/j.jseaes.2011.05.002.
[36]   Morino M, Kamal ASMM, Akhter SH, Rahman MZ, Ali RME, Talukder A, et al. A paleo-seismological study of the Dauki fault at Jaflong, Sylhet, Bangladesh: Historical seismic events and an attempted rupture segmentation model. J Asian Earth Sci 2014;91:218–26. https://doi.org/10.1016/j.jseaes.2014.06.002.
[37]   Steckler MS, Mondal DR, Akhter SH, Seeber L, Feng L, Gale J, et al. Locked and loading megathrust linked to active subduction beneath the Indo-Burman Ranges. Nat Geosci 2016;9:615–8. https://doi.org/10.1038/ngeo2760.
[38]   Idriss IM, Boulanger RW. Semi-empirical procedures for evaluating liquefaction potential during earthquakes. Soil Dyn Earthq Eng 2006;26:115–30. https://doi.org/10.1016/j.soildyn.2004.11.023.
[39]   Jahangiri A, Rakha HA. Applying Machine Learning Techniques to Transportation Mode Recognition Using Mobile Phone Sensor Data. IEEE Trans Intell Transp Syst 2015;16:2406–17. https://doi.org/10.1109/TITS.2015.2405759.
[40]   Zhang D, Tsai J. Advances in Machine Learning Applications in Software Engineering. Idea Group Inc; 2007.
[41]   Quinlan J. Learning with continuous classes. Proc. 5th Aust. Jt. Conf. Artif. Intell., WORLD SCIENTIFIC; 1992, p. 1–410. https://doi.org/10.1142/9789814536271.
[42]   Wang Y, Witten I. Induction of model trees for predicting continuous lasses. Proc. ninth Eur. Conf. Mach. Learn., 1997, p. 128–37.

Files

History

  • Receive Date: 06 July 2024
  • Revise Date: 12 November 2024
  • Accept Date: 14 January 2025

Share

How to cite

Statistics