Abstract
Earthquakes can cause violent liquefaction of the soil, resulting in unstable foundations that can cause serious damage to facilities such as buildings, roads, and dikes. This is a primary cause of major earthquake disasters. Therefore, the discrimination and prediction of earthquake-induced soil liquefaction has been a hot issue in geohazard research. The soil liquefaction assessment is an integral part of engineering practice. This paper evaluated a dataset of 435 seismic sand liquefaction events using machine learning algorithms. The dataset was analyzed using seven potential assessment parameters. Ten machine learning algorithms are evaluated for their ability to assess seismic sand liquefaction potential, including Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Naive Bayes (NB), K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), Classification Tree (CT), Support Vector Machine (SVM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM). A 10-fold cross-validation (CV) method was used in the modeling process to verify the predictive performance of the machine learning models. The final percentages of significant parameters that influenced the prediction results were obtained as Cyclic Stress Ratio (CSR) and Shear-Wave Velocity (VS1) with 56% and 38%, respectively. The final machine learning algorithms identified as suitable for seismic sand liquefaction assessment were the CT, RF, XGBoost algorithms, with the RF algorithm performing best.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Abbreviations
- Mw:
-
Earthquake magnitude
- a max :
-
Peak ground acceleration
- q c1Ncs, (N1)60 :
-
Equivalent clean sand normalized cone tip resistance
- F r :
-
Normalized friction ratio
- V S1 :
-
Normalized shear wave velocity
- σ′vo :
-
Vertical effective stress
- σ vo :
-
Vertical stress
- FC, F c :
-
Fines content
- ST:
-
Soil behavior type determined by the soil behavior type chart
- CSR:
-
Cyclic stress ratio
- PSO:
-
Particle swarm optimization
- KELM:
-
Kernel eXtreme learning machine
- GWO:
-
Grey wolf optimization
- r rup :
-
Closest distance to rupture surface
- I c :
-
Soil behavior type index
- D w :
-
Groundwater table depth
- D s :
-
Depth of soil deposit
- T s :
-
Thickness of soil layer
- a rms :
-
Root-mean-square acceleration
- GWT:
-
Groundwater table
- z :
-
Depth of target stratum
- DNN:
-
Deep neural network
- DT:
-
Decision tree
- BBN:
-
Bayesian belief network
References
Ahmad M, Tang XW, Qiu JN, et al. (2019) Evaluating Seismic Soil Liquefaction Potential Using Bayesian Belief Network, C4.5 Decision Tree Approaches. Appl Sci 9 (20): 4226. https://doi.org/10.3390/app9204226
Andrus RD (1997) Liquefaction resistance based on shear wave velocity. Proceeding of Nceer Workshop on Evaluation of Liquefaction Resistance of Soils. Natl Center Earthq Eng Res 1997:89–128
Andrus RD, Stokoe KH II (2000) Liquefaction resistance of soils from shear-wave velocity. J Geotech Geoenviron Eng 126 (11): 1015–1025. https://doi.org/10.1061/(ASCE)1090-0241(200o)126:11(1015)
Bertalot D, Brennan AJ, Villalobos FA (2013) Influence of bearing pressure on liquefaction-induced settlement of shallow foundations. Géotech 63 (5): 391–399. https://doi.org/10.1680/geot.11.P.040
Boulanger RW, Idriss IM (2014) CPT, SPT based Liquefaction Triggering Procedures. Report No.: UCD/CGM-14/01, Center for Geotechnical Modeling, Department of Civil, Environmental Engg., University of California, Davis, USA.
Boulanger RW, Idriss IM (2012) Probabilistic standard penetration test–based liquefaction–triggering procedure. J Geotech Geoenviron Eng 138 (10): 1185–1195. https://doi.org/10.1061/(ASCE)GT.1943-5606.0000700
Boulanger RW, Idriss IM (2016) CPT-based liquefaction triggering procedure. J Geotech Geoenviron Eng 142 (2): 04015065. https://doi.org/10.1061/(ASCE)GT.1943-5606.0001388
Cai GJ, Liu SY, Puppala AJ (2012) Liquefaction assessments using seismic piezocone penetration (SCPTU) test investigations in Tangshan region in China. Soil Dyn Earthquake Eng 41 141–150. https://doi.org/10.1016/j.soildyn.2012.05.008
Candanedo LM, Feldheim V, Deramaix D (2017) Data driven prediction models of energy use of appliances in a low-energy house. Energy Build 140 81–97. https://doi.org/10.1016/j.enbuild.2017.01.083
Cao ZZ, T. Leslie Youd, Yuan XM (2011) Gravelly soils that liquefied during 2008 Wenchuan, China earthquake, Ms=8.0. Soil Dyn Earthquake Eng 31 (8): 1132–1143. https://doi.org/10.1016/j.soildyn.2011.04.001
Chen GX, Kong MY, Sara Khoshnevisan, et al. (2019) Calibration of Vs-based empirical models for assessing soil liquefaction potential using expanded database. Bull Eng Geol Environ 78 (2): 945–957. https://doi.org/10.1007/s10064-017-1146-9
Chen LW, Yuan XM, Cao ZZ, et al. (2018) Characteristics, triggering conditions for naturally deposited gravelly soils that liquefied following the 2008 Wenchuan Mw 7.9 Earthquake, China. Earthq Spectra 34 (3): 1091–1111. https://doi.org/10.1193/032017eqso50m
Chou JS, Lin C (2013) Predicting Disputes in Public-Private Partnership Projects: Classification, Ensemble Models. J Comput Civ Eng 27 (1): 51–60. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000197
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20 (3): 273–297. https://doi.org/10.1007/BF00994018
Dankwa S, Zheng W (2019) Special issue on using machine learning algorithms in the prediction of Kyphosis disease: a comparative study. Appl Sci 9 (16): 3322. https://doi.org/10.3390/app9163322
Duan W, Zhao ZN, Cai GJ, et al. (2023) Vs-based assessment of soil liquefaction potential using ensembling of GWO–KLEM, Bayesian theorem: a full probabilistic design perspective. Acta Geotech 18:1863–1881. https://doi.org/10.1007/s11440-022-01695-2
Fisher RA (1936) The use of multiple measurements in taxonomic problems. Annals Eugenics 7 (2): 179–188. https://doi.org/10.1111/j.1469-1809.1936.tbo2137.x
Fix E, Hodges JL (1989) Discriminatory analysis. Nonparametric discrimination: consistency properties. Int Stat Rev/Rev Int Stat 57 (3): 238–247. https://doi.org/10.2307/1403797
Fu SC, Tatsuoka F (1984) Soil Liquefaction during Haicheng, Tangshan Earthquake in China; a Review. Soils Found 24 (4): 11–29. https://doi.org/10.3208/sandf1972.24.4_11
González-Rufino E, Carrión P, Cernadas E, et al. (2013) Exhaustive comparison of colour texture features, classification methods to discriminate cells categories in histological images of fish ovary. Pat Recognit 46 (9): 2391–2407. https://doi.org/10.1016/j.patcog.2013.02.009
Gvardinskas M (2017) Combined classification error rate estimator for the Fisher linear classifier. Inf Technol Control 45 (4): https://doi.org/10.5755/jo1.itc.45.4.14268
Hamada M, Kubo K, Isoyama R (1987) Earthquake Damage Caused by Liquefaction Induced Permanent Ground Displacement. Developments in Geotech Eng 49: 3–19. https://doi.org/10.1016/B978-o-444-98934-5.50006-7
Hanna AM, Ural D, Saygili G (2007) Evaluation of liquefaction potential of soil deposits using artificial neural networks. Eng Comput 24 (1): 5–16. https://doi.org/10.1108/02644400710718547
Hatanaka M, Uchida A, Ohara J (1997) Liquefaction Characteristics of A Gravelly Fill Liquefied During the 1995 Hyogo-Ken Nanbu Earthquake. Soils Found 37 (3): 107–115. https://doi.org/10.3208/sandf.37.3_107
Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal Mach Intell 20 (8): 832–844. https://doi.org/10.1109/34.709601
Hu JL, Tang XW, Qiu JN (2016) Assessment of seismic liquefaction potential based on Bayesian network constructed from domain knowledge, history data. Soil Dyn Earthquake Eng 89: 49–60. https://doi.org/10.1016/j.soildyn.2016.07.007
Hu JL, Liu HB (2019) Bayesian network models for probabilistic evaluation of earthquake-induced liquefaction based on CPT, Vs databases. Eng Geol 254 76–88. https://doi.org/10.1016/j.enggeo.2019.04.003
Hu Q, Li H, Zhang Y (2017) Liquefaction Evaluation Based on Dynamic Triaxial Test, Soil Seismic Response. J Geodesy Geodyn 37 (05): 531–535. https://doi.org/10.14075/j.jgg.2017.05.019 (In Chinese)
Idriss IM, Boulanger RW (2006) Semi-empirical procedures for evaluating liquefaction potential during earthquakes. Soil Dyn Earthq Eng 26 (2): 115–130. https://doi.org/10.1016/j.soildyn.2004.11.023
Ishac MF, Heidebrecht AC (1982) Energy dissipation, seismic liquefaction in sands. Earthq Eng Struct Dyn 10 (1): 59–68. https://doi.org/10.1002/eqe.4290100105
Ishihara K, Koga Y (1981) Case Studies of Liquefaction in the 1964 Niigata Earthquake. Soils Found 21 (3): 35–52. https://doi.org/10.3208/sandf1972.21.3_35
Jas K, Dodagoudar GR (2023a) Explainable machine learning model for liquefaction potential assessment of soils using XGBoost-SHAP. Soil Dyn Earthq Eng 165 107662. https://doi.org/10.1016/j.soildyn.2022.107662
Jas K, Dodagoudar GR (2023b) Liquefaction Potential Assessment of Soils Using Machine Learning Techniques: A State-of-the-Art Review from 1994–2021. Int J Geomech 23 (7): 03123002. https://doi.org/10.1061/IJGNAI.GMENG-7788
Kayen R, Moss RES, Thompson EM, et al. (2013) Shear-Wave Velocity-Based Probabilistic, Deterministic Assessment of Seismic Soil Liquefaction Potential. J Geotech Geoenviron Eng. 139 (3): 407–419. https://doi.org/10.1061/(ASCE)GT.1943-5606.0000743
Kemal P, Güneş, S, Arslan A (2008) A cascade learning system for classification of diabetes disease: Generalized discriminant analysis, least square support vector machine. Expert Syst Appl 34 (1): 482–487. https://doi.org/10.1016/j.eswa.2006.09.012
Kohavi R (1995) A study of cross-validation, bootstrap for accuracy estimation, model selection. In: International joint conference on Artificial intelligence. Morgan Kaufmann Publishers Inc. 1995
Kohestani VR, Hassanlourad M, Ardakani A (2015) Evaluation of liquefaction potential based on CPT data using random forest. Nat Hazard 79 (2): 1079–1089. https://doi.org/10.1007/s11069-015-1893-5
Kotsiantis SB, Zaharakis ID, Pintelas PE (2006) Machine learning: a review of classification, combining techniques. Artif Intell Rev 26 (3): 159–190. https://doi.org/10.1007/s10462-007-9052-3
Kuo YS, Chong KJ, Tseng YH. et al. (2020) Assessment on liquefaction potential of seabed soil in Chang-Bin Offshore wind farm considering parametric uncertainty of standard penetration tests. Eng Geol 267 105497. https://doi.org/10.1016/j.enggeo.2020.105497
Li H, Yamanishi KJ (2002) Text classification using ESC-based stochastic decision lists. Inf Process Manag 38 (3): 343–361. https://doi.org/10.1016/80306-4573(01)00038-3
Li ZX, Hou GY, Wang KD, et al. (2021) Deformation monitoring of cracked concrete structures based on distributed optical fiber sensing technology. Opt Fiber Technol 61 102446. https://doi.org/10.1016/j.yofte.2020.102446
Liu HJ, Xue XH (2004) Artificial neural network model for prediction of seismic liquefaction of sand soil. Rock Soil Mech., 25 (12): 1942–1941. https://doi.org/10.1016/j.yofte.2020.102446
Lodge AL. (1994) Shear wave velocity measurements for subsurface characterization. PhD thesis, University of California, Berkeley.
Luebbers M (2006) Discussion of “Standard penetration test-based probabilistic, deterministic assessment of seismic soil liquefaction potential” by K. Onder Cetin, Raymond B. Seed, Armen Der Kiureghian, Kohji Tokimatsu, Leslie F. Harder Jr., Robert E. Kayen, Robert E. S. Moss. J Geotech Geoenviron Eng 132 (5): 667–667. https://doi.org/10.1061/(ASCE)1090-0241(2006)132:5(667)
Madeh PS, El-Diraby TE (2020) Role of Data Analytics in Infrastructure Asset Management: Overcoming Data Size, Quality Problems. J Transp Eng Part B Pavem 146 (2): 04020022. https://doi.org/10.1061/JPEODX.0000175
Mahesh P (2006) Support vector machines-based modelling of seismic liquefaction potential. Int J Numer Anal Methods Geomech 30 (10): 983–996. https://doi.org/10.1002/nag.509
Mary VR, Latha GM (2014) Shaking table tests to investigate the influence of various factors on the liquefaction resistance of sands. Nat Hazard 73 (3): 1337–1351. https://doi.org/10.1007/s11069-014-1142-3
Mashudi NA, Rossli SA, Ahmad N, et al. (2021) Comparison on some machine learning techniques in breast cancer classification. In: 2020 IEEE-EMBS Conference on Biomedical Engineering, Sciences (IECBES) 2021: 499–504. https://doi.org/10.1109/IECBES48179.2021.9398837
Ministry of Housing, Urban-Rural Development of the People’s Republic of China. (2010) GB50011-2010 Code for seismic design of buildings. Beijing: China Architecture, Building Press. (In Chinese)
Ministry of Urban, Rural Construction, Environmental Protection of the People’s Republic of China (1989) GBJ11-89 Code for seismic design of buildings. Beijing:China Architecture, Building Press (In Chinese)
Moss RE, Seed RB, Kayen RE, et al. (2006) CPT-Based Probabilistic, Deterministic Assessment of In Situ Seismic Soil Liquefaction Potential. J Geotech Geoenviron Eng 132 (8): 1032–1051. https://doi.org/10.1061/(ASCE)1090-0241(2006)132:8(1032)
Muduli PK, Das SK (2015) Model uncertainty of SPT-based method for evaluation of seismic soil liquefaction potential using multi-gene genetic programming. Soils Found 55 (2): 258–275. 1p.1016/j.sandf.2015.02.003
Nejad AS, Güler E, Özturan M (2018) Evaluation of Liquefaction Potential Using Random Forest Method and Shear Wave Velocity Results. 2018 International Conference on Applied Mathematics & Computational Science (ICAMCS.NET) 2018: 23–233. https://doi.org/10.1109/icamcs.net46018.2018.00012
Ohsaki Y. (1966) Niigata Earthquakes, 1964 Building Damage, Soil Condition. Soils Found 6 (2): 14–37. https://doi.org/10.3208/sandf1960.6.2_14
Robertson PK, Wride CE (1998) Evaluating cyclic liquefaction potential using the cone penetration test. Can Geotech J 35 (3): 442–459. https://doi.org/10.1139/t98-017
Robertson PK (2015) Comparing CPT, Vs Liquefaction Triggering Methods. J Geotech Geoenviron Eng 141 (9): 04015037. https://doi.org/10.1061/(ASCE)GT.1943-5606.0001338
Robertson PK, Woeller DJ, Finn WDL (1992) Seismic cone penetration test for evaluating liquefaction potential under cyclic loading. Can Geotech J 29 (4): 686–695. https://doi.org/10.1139/t92-075
Samui P, Sitharam TG (2011b) Machine learning modelling for predicting soil liquefaction susceptibility. Nat. Hazards Earth Syst Sci 11 (1): 1–9. https://doi.org/10.5194/nhess-11-1-2011
Samui P (2007) Seismic liquefaction potential assessment by using Relevance Vector Machine. Earthquake Eng Eng Vibr 6 (4): 331–336. https://doi.org/10.1007/s11803-007-0766-7
Samui P (2011a) Least square support vector machine, relevance vector machine for evaluating seismic liquefaction potential using SPT. Nat Hazard 59 (2): 811–822. https://doi.org/10.1007/s11069-011-9797-5
Sassa S, Takagawa T (2019) Liquefied gravity flow-induced tsunami: first evidence, comparison from the 2018 Indonesia Sulawesi earthquake, tsunami disasters. Landslides 16 (1): 195–200. https://doi.org/10.1007/s10346-018-1114-x
Seed HB, Idriss IM (1971) Simplified procedure for evaluating soil liquefaction potential. J Soil Mech Found Div 97 (9): 1249–1273. https://doi.org/10.1061/JSFEAQ.0001662
Seed HB, Idriss IM, Arango I (1983) Evaluation of liquefaction potential using field performance data. J Geotech Eng 109 (3): 458–482. https://doi.org/10.1061/(ASCE)0733-9410(1983)109:3(458)
Venables WN, Ripley BD (2002) Modern Applied Statistics With S New York, Springer-Verlag.
Vipin KS, Sitharam TG, Anbazhagan P (2010) Probabilistic evaluation of seismic soil liquefaction potential based on SPT data. Nat Hazard 53 (3): 547–560. https://doi.org/10.1007/s11069-009-9447-3
Youd TL, Idriss IM, Andrus RD, et al. (2001) Liquefaction resistance of soils: summary report from the 1996 NCEER, 1998 NCEER/NSF Workshops on evaluation of liquefaction resistance of soils. J Geotech Geoenviron Eng 127 (10): 817–833. https://doi.org/10.1061/(ASCE)1090-0241(2001)127:10(817)
Yu H, Zheng H, Mao WW, et al. (2012) Triaxial tests on the fluidic behavior of post-liquefaction sand. Environ Earth Sci 67 (8): 2325–2330. https://doi.org/10.1007/s12665-012-1679-y
Yuan HM, Yang SH, Andrus RD, et al. (2004) Liquefaction-induced ground failure: a study of the Chi-Chi earthquake cases. Eng Geol 71 (1): 141–155. https://doi.org/10.1016/80013-7952(03)00130-3
Zhang LX, Wang C, Wang ZQ, et al. (2003) Study on large-scale shaking table proportional model test for free-ground liquefaction arisen from earthquake. Earthquake Eng Eng Vibr (06):138–143. https://doi.org/10.13197/j.eeev.2003.06.022 (In Chinese)
Zhang YG, Xie YL, Zhang Y, et al. (2021) The adoption of deep neural network (DNN) to the prediction of soil liquefaction based on shear wave velocity. Bull Eng Geol Environ 80 (6): 5053–5060. https://doi.org/10.1007/s10064-021-02250-1
Zhao ZN, Duan W, Cai GJ (2021) A novel PSO-KELM based soil liquefaction potential evaluation system using CPT, Vs measurements. Soil Dyn Earthquake Eng 150 https://doi.org/10.1016/j.soildyn.2021.106930
Zhao ZN, Duan W, Cai GJ, et al. (2022) CPT-based fully probabilistic seismic liquefaction potential assessment to reduce uncertainty: Integrating XGBoost algorithm with Bayesian theorem. Comput Geotech 149 104868. https://doi.org/10.1016/j.compgeo.2022.104868
Zhou J, Huang S, Zhou T, et al. (2022) Employing a genetic algorithm, grey wolf optimizer for optimizing RF models to evaluate soil liquefaction potential. Artif Intell Rev 55 (7): 5673–5705. https://doi.org/10.1007/s10462-022-10140-5
Acknowledgments
The authors acknowledge financial support from the Doctoral Innovative Talent Cultivation Fund at China University of Mining and Technology (Beijing) (No. BBJ2023049).
Author information
Authors and Affiliations
Contributions
SUI Qi-ru: Conceptualization; Data Curation; Visualization; Investigation; Writing–original draft; Writing–review & editing; Funding acquisition; CHEN Qin-huang: Methodology; Data Curation; Software; Visualization; Investigation; Writing–review & editing; WANG Dan-dan: Investigation; Visualization; Writing–review & editing; TAO Zhigang: Conceptualization; Supervision; Project administration
Corresponding authors
Ethics declarations
Data Availability: The current research analysis dataset can be publicly obtained based on the cited references (Cai et al. 2012 (https://doi.org/10.1016/j.soildyn.2012.05.008); Kayen et al. 2013 (https://doi.org/10.1061/(ASCE)GT.1943-5606.0000743)). The data presented in this study are available on request from the corresponding author.
Conflict of Interest: The authors declare no conflict of interest.
Rights and permissions
About this article
Cite this article
Sui, Qr., Chen, Qh., Wang, Dd. et al. Application of machine learning to the Vs-based soil liquefaction potential assessment. J. Mt. Sci. 20, 2197–2213 (2023). https://doi.org/10.1007/s11629-022-7809-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11629-022-7809-4