Soil liquefaction assessment by using hierarchical Gaussian Process model with integrated feature and instance based domain adaption for multiple data sources

Abstract

For soil liquefaction prediction from multiple data sources, this study designs a hierarchical machine learning model based on deep feature extraction and Gaussian Process with integrated domain adaption techniques. The proposed model first combines deep fisher discriminant analysis (DDA) and Gaussian Process (GP) in a unified framework, so as to extract deep discriminant features and enhance the model performance for classification. To deliver fair evaluation, the classifier is validated in the approach of repeated stratified K-fold cross validation. Then, five different data resources are presented to further verify the model’s robustness and generality. To reuse the gained knowledge from the existing data sources and enhance the generality of the predictive model, a domain adaption approach is formulated by combing a deep Autoencoder with TrAdaboost, to achieve good performance over different data records from both the in-situ and laboratory observations. After comparing the proposed model with classical machine learning models, such as supported vector machine, as well as with the state-of-art ensemble learning models, it is found that, regarding seismic-induced liquefaction prediction, the predicted results of this model show high accuracy on all datasets both in the repeated cross validation and Wilcoxon signed rank test. Finally, a sensitivity analysis is made on the DDA-GP model to reveal the features that may significantly affect the liquefaction.

Keywords

Liquefaction / Machine learning / Deep fisher discriminant analysis / Gaussian Process / Ensemble methods / Domain adaption

References

[1] AlaviAH, GandomiAH. Energy-based numerical models for assessment of soil liquefaction. Geoscience Frontiers, 2012, 3(4

[2] AlobaidiMH, MeguidMA, ChebanaF. Predicting seismic-induced liquefaction through ensemble learning frameworks. Scientific Reports, 2019, 9 1):1-12

[3] BanerjeeA, DunsonDB, TokdarST. Efficient gaussian process regression for large datasets. Biometrika, 2013, 100(1):75-89

[4] BaoX, JinZ, CuiH, ChenX, XieX. Soil liquefaction mitigation in geotechnical engineering: An overview of recently developed methods. Soil Dynamics and Earthquake Engineering, 2019, 120: 273-291

[5] Benesty, J., Chen, J., Huang, Y., & Cohen, I. (2009). Pearson correlation coefficient. In Noise reduction in speech processing, Springer. pp 1–4.

[6] BilogurA. Missingno: A missing data visualization suite. Journal of Open Source Software, 2018, 3(22):547

[7] Buitinck, L., Louppe, G., Blondel, M., Pedregosa, F., Mueller, A., Grisel, O., Niculae, V., Prettenhofer, P., Gramfort, A., Grobler, J., Layton, R., VanderPlas, J., Joly, A., Holt, B., Varoquaux, G. (2013). API design for machine learning software: experiences from the scikit-learn project. In ECML PKDD Workshop: Languages for data mining and machine learning, pp 108–122.

[8] Cai, M., Hocine, O., Mohammed, A.S., Chen, X., Amar, M.N., & Hasanipanah, M. (2021). Integrating the lssvm and rbfnn models with three optimization algorithms to predict the soil liquefaction potential. Engineering with Computers, 1–13.

[9] ChandrashekarG, SahinF. A survey on feature selection methods. Computers & Electrical Engineering, 2014, 40(1):16-28

[10] ChenZ, LiH, GohATC, ChongzhiWu, ZhangW. Soil liquefaction assessment using soft computing approaches based on capacity energy concept. Geosciences, 2020, 10(9):330

[11] Clark, L. A., & Pregibon, D. (2017). Tree-based models. In Statistical models in S, pp 377–419. Routledge.

[12] CristianiniN, Shawe-TaylorJ, et al.. An introduction to support vector machines and other kernel-based learning methods, 2000 Cambridge University Press

[13] Dai, W., Yang, Q., Xue, G.-R., & Yu, Y. (2007). Boosting for transfer learning. In Proceedings of the 24th international conference on machine learning, ICML ’07, pp 193–200, New York, NY, USA, 2007. Association for Computing Machinery.

[14] de Mathelin, A., Deheeger, F., Richard, G., Mougeot, M., & Vayatis, N. (2021). Adapt: Awesome domain adaptation python toolbox. arXiv preprint arXiv:2107.03049.

[15] DemšarJ. Statistical comparisons of classifiers over multiple data sets. The Journal of Machine Learning Research, 2006, 7: 1-30

[16] DingZ, ShaoM, YunFu. Incomplete multisource transfer learning. IEEE Transactions on Neural Networks and Learning Systems, 2016, 29(2):310-323

[17] Dorogush, A.V., Ershov, V., & Gulin, A. (2018). Catboost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363.

[18] Dίaz-Vico, D., Omari, A., Torres-Barrán, A., Dorronsoro, J.R. (2017). Deep fisher discriminant analysis. In International WorkConference on Artificial Neural Networks, pp 501–512. Springer.

[19] GabriéM, ManoelA, LuneauC, BarbierJ, MacrisN, KrzakalaF, ZdeborováL. Entropy and mutual information in models of deep neural networks. Journal of Statistical Mechanics: Theory and Experiment, 2019, 2019(12

[20] GalaviV, PetalasA, BrinkgreveRBJ. Finite element modelling of seismic liquefaction in soils. Geotechnical Engineering Journal of the SEAGS & AGSSEA, 2013, 44 3):2013

[21] Gandomi, A.H., Fridline, M.M., & Roke D.A. (2013). Decision tree approach for soil liquefaction assessment. The Scientific World Journal, 2013.

[22] GohATC, GohSH. Support vector machines: Their use in geotechnical engineering as illustrated using seismic liquefaction data. Computers and Geotechnics, 2007, 34(5):410-421

[23] GoharzayM, NoorzadA, ArdakaniAM, JalalM. A worldwide SPT-based soil liquefaction triggering analysis utilizing gene expression programming and Bayesian probabilistic method. Journal of Rock Mechanics and Geotechnical Engineering, 2017, 9(4):683-693

[24] GoharzayM, NoorzadA, ArdakaniAM, JalalM. Computer-aided SPT-based reliability model for probability of liquefaction using hybrid pso and ga. Journal of Computational Design and Engineering, 2020, 7(1):107-127

[25] HackelingG. Mastering machine learning with scikit-learn, 2017 Cham Packt Publishing Ltd

[26] HannaAM, UralD, SaygiliG. Neural network model for liquefaction potential in soil deposits using turkey and Taiwan earthquake data. Soil Dynamics and Earthquake Engineering, 2007, 27(6):521-540

[27] HoangN-D, BuiDT. Predicting earthquake-induced soil liquefaction based on a hybridization of kernel fisher discriminant analysis and a least squares support vector machine: A multi-dataset study. Bulletin of Engineering Geology and the Environment, 2018, 77(1):191-204

[28] HuangYu, MiaoYu. Review of soil liquefaction characteristics during major earthquakes of the twenty-first century. Natural Hazards, 2013, 65(3):2375-2384

[29] HubermanM, LangholzB. Application of the missingindicator method in matched case-control studies with incomplete data. American Journal of Epidemiology, 1999, 150(12):1340-1345

[30] JahangiriA, RakhaHA. Applying machine learning techniques to transportation mode recognition using mobile phone sensor data. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(5):2406-2417

[31] JefferiesM, BeenK. Soil liquefaction: A critical state approach, 2019 CRC Press

[32] JileiHu, WangJ, ZouW, YangB. Datasets for gravelly soil liquefaction case histories. Data in Brief, 2021, 36

[33] JuangCH, ChenCJ. A rational method for development of limit state for liquefaction evaluation based on shear wave velocity measurements. International Journal for Numerical and Analytical Methods in Geomechanics, 2000, 24(1):1-27

[34] Kanasewich, E.R. (1981). Time sequence analysis in geophysics. University of Alberta.

[35] KeG, MengQi, FinleyT, WangT, ChenW, MaW, YeQ, LiuT-Y. Lightgbm: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 2017, 30: 3146-3154

[36] KramerSL. Geotechnical earthquake engineering, 1996 Prentice Hall

[37] KuhnM, JohnsonK, et al.. Applied predictive modeling, 2013 Springer

[38] KumarD, SamuiP, KimD, SinghA. A novel methodology to classify soil liquefaction using deep learning. Geotechnical and Geological Engineering, 2021, 39(2):1049-1058

[39] KurnazTF, KayaY. Spt-based liquefaction assessment with a novel ensemble model based on gmdh-type neural network. Arabian Journal of Geosciences, 2019, 12(15):1-14

[40] Leslie YoudT, IdrissIM. Liquefaction resistance of soils: Summary report from the 1996 NCEER and 1998 NCEER/NSF workshops on evaluation of liquefaction resistance of soils. Journal of Geotechnical and Geoenvironmental Engineering, 2001, 127(4):297-313

[41] Liang, S., & Srikant, R. (2016). Why deep neural networks for function approximation? arXiv preprint arXiv:1610.04161.

[42] Little, R.J.A., & Rubin, D.B. (2002). Single imputation methods. Statistical analysis with missing data, pp 59–74.

[43] MhaskeSY, ChoudhuryD. Gis-based soil liquefaction susceptibility map of Mumbai city for earthquake events. Journal of Applied Geophysics, 2010, 70(3):216-225

[44] Miao, Y.-Q., Farahat, A.K., & Kamel, M.S. (2015). Ensemble kernel mean matching. In 2015 IEEE International Conference on Data Mining. IEEE, pp 330–338.

[45] Murat MonkulM, GültekinC, GülverM, AkınÖ, Eseller-BayatE. Estimation of liquefaction potential from dry and saturated sandy soils under drained constant volume cyclic simple shear loading. Soil Dynamics and Earthquake Engineering, 2015, 75: 27-36

[46] Onder CetinK, SeedRB, KayenRE, MossRES, Tolga BilgeH, IlgacM, ChowdhuryK. Dataset on sptbased seismic soil liquefaction. Data in Brief, 2018, 20: 544-548

[47] PalM. Support vector machines-based modelling of seismic liquefaction potential. International Journal for Numerical and Analytical Methods in Geomechanics, 2006, 30(10):983-996

[48] PedregosaF, VaroquauxG, GramfortA, MichelV, ThirionB, GriselO, BlondelM, PrettenhoferP, WeissR, DubourgV, VanderplasJ, PassosA, CournapeauD, BrucherM, PerrotM, DuchesnayE. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 2011, 12: 2825-2830

[49] RahbarzareA, AzadiM. Improving prediction of soil liquefaction using hybrid optimization algorithms and a fuzzy support vector machine. Bulletin of Engineering Geology and the Environment, 2019, 78(7):4977-4987

[50] Rasmussen, C.E. (2003). Gaussian processes in machine learning. In Summer school on machine learning. Springer, pp 63–71.

[51] SamuiP, JaganJ, HariharanR. An alternative method for determination of liquefaction susceptibility of soil. Geotechnical and Geological Engineering, 2016, 34(2):735-738

[52] SamuiP, SitharamTG. Machine learning modelling for predicting soil liquefaction susceptibility. Natural Hazards and Earth System Sciences, 2011, 11(1):1-9

[53] Sigrist, F. (2020). Gaussian Process boosting. arXiv preprint arXiv:2004.02653.

[54] SobolIM. Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates. Mathematics and Computers in Simulation, 2001, 55(1–3):271-280

[55] SteinwartI, ChristmannA. Support vector machines, 2008 Springer Science & Business Media

[56] SugiyamaM, SuzukiT, NakajimaS, KashimaH, von BünauP, KawanabeM. Direct importance estimation for covariate shift adaptation. Annals of the Institute of Statistical Mathematics, 2008, 60(4):699-746

[57] Wen, X., Jing, H., & Yanfeng, S. (2020). Transfer learning and deep domain adaptation. Advances and Applications in Deep Learning, 45.

[58] WilliamsCKI, RasmussenCE. Gaussian processes for machine learning, 2006 MIT Press

[59] XueX, YangX. Application of the adaptive neurofuzzy inference system for prediction of soil liquefaction. Natural Hazards, 2013, 67(2):901-917

[60] YoudJM, NewmanJMB, ClarkMG, ApplebyGJ, RattiganS, TongACY, VincentMA. Increased metabolism of infused 1-methylxanthine by working muscle. Acta Physiologica Scandinavica, 1999, 166(4):301-308

[61] Zhang, Y., Xie, Y., Zhang, Y., Qiu, J., & Wu, S. (2021). The adoption of deep neural network (dnn) to the prediction of soil liquefaction based on shear wave velocity. Bulletin of Engineering Geology and the Environment, 1–8.

[62] ZhangJ, WangY. An ensemble method to improve prediction of earthquake-induced soil liquefaction: A multi-dataset study. Neural Computing and Applications, 2021, 33(5):1533-1546

[63] Zhou, J., Huang, S., Wang, M., & Qiu, Y. (2021). Performance evaluation of hybrid ga–svm and gwo–svm models to predict earthquakeinduced liquefaction potential of soil: A multi-dataset investigation. Engineering with Computers, 1–19.

[64] ZhouJ, LiE, WangM, ChenX, ShiX, JiangL. Feasibility of stochastic gradient boosting approach for evaluating seismic liquefaction potential based on spt and cpt case histories. Journal of Performance of Constructed Facilities, 2019, 33(3):04019024

[65] ZhuJ, GeZ, SongZ, GaoF. Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data. Annual Reviews in Control, 2018, 46: 107-133

[66] ZhuangX, ZhouS. The prediction of self-healing capacity of bacteria-based concrete using machine learning approaches. Computers, Materials & Continua, 2019, 59(2019):1