A back analysis scheme for refined soil stratification based on integrating borehole and CPT data

Abstract

Utilizing both borehole and Cone Penetration Testing (CPT) data in soil stratification helps to get more convincing soil stratification results. However, the soil classification results revealed by borehole (Unified Soil Classification System, USCS) and CPT tests (soil behavior type, SBT) are commonly not consistent. This study proposes a feasible solution to integrate the borehole and CPT data with the tree-based method. The tree-based method is naturally suitable for soil stratification tasks as it aims to divide the subsurface space into several clusters based on the similarities of the soil types. A novel boundary dictionary method is proposed to enhance the model performance on complex soil layer conditions. A probabilistic mapping matrix between the USCS-SBT system is built based on a collected municipal database with collocated borehole and CPT data. The optimal soil stratification results can be selected based on considering multiple borehole information and pruning the structure of trees. The structure of the trees can be optimized in a back analysis perspective with the Sequential Model-Based Global Optimization (SMBO) algorithm which aims to maximize the possibility of observing the borehole information based on the USCS-SBT probabilistic mapping matrix. The uncertainties of the optimal soil stratification results can be estimated based on a weighted Gini index method. The performance of the proposed method is validated based on a real case in New Zealand with a cross-validation method. The results indicate that the proposed method is robust and effective.

Keywords

Soil stratification / Data integration / Borehole / CPT / Tree-based method

References

[1] ASTM, 2017. Standard Practice for Classification of Soils for Engineering Purposes (Unified Soil Classification System) 1. ASTM international.

[2] Cao Z.J., Zheng S., Li D.Q., Phoon K.K., 2018. Bayesian identification of soil stratigraphy based on soil behaviour type index. Can. Geotech. J. 56, 570-586, https://doi.org/10.1139/cgj-2017-0714.

[3] Ching J., Wu T.J., Stuedlein A.W., Bong T., 2018. Estimating horizontal scale of fluctuation with limited CPT soundings. Geosci. Front. 9, 1597-1608, https://doi.org/10.1016/j.gsf.2017.11.008.

[4] Ching J., Wang J.S., Juang C.H., Ku C.S., 2015. Cone penetration test (CPT)- based stratigraphic profiling using the wavelet transform modulus maxima method. Can. Geotech. J. 52, 1993-2007, https://doi.org/10.1139/cgj-2015-0027.

[5] Frohlich H., Zell A., 2005. Efficient parameter selection for support vector machines in classification and regression via model-based global optimization, in:Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005., IEEE. pp. 1431-1436.

[6] Hu Y., Wang Y., 2020. Probabilistic soil classification and stratification in a vertical cross-section from limited cone penetration tests using random field and Monte Carlo simulation. Comput. Geotech. 124, 103634, https://doi.org/10.1016/j.compgeo.2020.103634.

[7] Jing S., Liu C., Li G., Yan G., Zhang Y., 2017. An efficient algorithm for parallel computation of rough entropy using cuda, in: 2017 13th International Conference on Computational Intelligence and Security (CIS), IEEE. pp. 1-5.

[8] Kim H.S., Ji Y., 2022. Three-dimensional geotechnical-layer mapping in Seoul using borehole database and deep neural network-based model. Eng. Geol. 297, 106489, https://doi.org/10.1016/j.enggeo.2021.106489.

[9] Mayne P.W., Christopher B.R., DeJong J., 2002. Subsurface Investigations- Geotechnical Site Characterization: Reference Manual. Technical Report. United States. Federal Highway Administration.

[10] NZGD, 2022. New Zealand Geotechnical Database (NZGD). Available at

[11] Parr T., Grover P., 2020. Dtreeviz: Decision tree visualization.

[12] Rauter S., Tschuchnigg F., 2021. CPT Data Interpretation Employing Different Machine Learning Techniques. Geosciences 11, 265, https://doi.org/10.3390/geosciences11070265.

[13] Reale C., Gavin K., Librić L., Jurić-Kaćunić D., 2018. Automatic classification of fine-grained soils using CPT measurements and Artificial Neural Networks. Adv. Eng. Inform. 36, 207-215, https://doi.org/10.1016/j.aei.2018.04.003.

[14] Robertson P.K., 1990. Soil classification using the cone penetration test. Can. Geotech. J. 27, 151-158, https://doi.org/10.1139/t90-014.

[15] Robertson P.K., 2010. Soil behaviour type from the CPT: An update,in:2nd International Symposium on Cone Penetration Testing, Cone Penetration Testing Organizing Committee. p. 8.

[16] Shi C., Wang Y., 2021. Non-parametric machine learning methods for interpolation of spatially varying non-stationary and non-Gaussian geotechnical properties. Geosci. Front. 12, 339-350, https://doi.org/10.1016/j.gsf.2020.01.011.

[17] Wang Z.Z., Hu Y., Guo X., He X., Kek H.Y., Ku T., Goh S.H., Leung C.F., 2023. Predicting geological interfaces using stacking ensemble learning with multi-scale features. Can. Geotech. J. https://doi.org/10.1139/cgj-2022-0365.

[18] Wang X., Wang H., Liang R.Y., Liu Y., 2019. A semi-supervised clustering-based approach for stratification identification using borehole and cone penetration test data. Eng. Geol. 248, 102-116, https://doi.org/10.1016/j.enggeo.2018.11.014.

[19] Wu J., Chen X.Y., Zhang H., Xiong L.D., Lei H., Deng S.H., 2019. Hyperparameter optimization for machine learning models based on Bayesian optimization. j.Electron. Sci. Tech. 17, 26-40.

[20] Wu S., Zhang J.M., Wang R., 2021. Machine learning method for CPTu based 3D stratification of New Zealand geotechnical database sites. Adv. Eng. Inform. 50, 101397, https://doi.org/10.1016/j.aei.2021.101397.

[21] Xiao T., Zou H.F., Yin K.S., Du Y., Zhang L.M., 2021. Machine learningenhanced soil classification by integrating borehole and CPTU data with noise filtering. B. Eng. Geol. Environ. 80, 9157-9171, https://doi.org/10.1007/s10064-021-02478-x.

[22] Xie J., Huang J., Zeng C., Huang S., Burton G.J., 2022. A generic framework for geotechnical subsurface modeling with machine learning. j.Rock Mechan. Geotech. Eng. 14(5): 1366-1379, https://doi.org/10.1016/j.jrmge.2022.08.001.

[23] Zhang Z., Tumay M.T., 1999. Statistical to fuzzy approach toward CPT soil classification. j.Geotech. Geoenviron. Eng. 125, 179.

[24] Zhao T., Wang Y., 2020. Interpolation and stratification of multilayer soil property profile from sparse measurements using machine learning methods. Eng. Geol. 265, 105430, https://doi.org/10.1016/j.enggeo.2019.105430.

[25] Zhao T., Xu L., Wang Y., 2020. Fast non-parametric simulation of 2D multi-layer cone penetration test (CPT) data without pre-stratification using Markov Chain Monte Carlo simulation. Eng. Geol. 273, 105670, https://doi.org/10.1016/j.enggeo.2020.105670.

[26] Zhao T., Wang Y., Lu S.-F., Xu L., 2022. Fast stratification of geological cross-section from CPT results with missing data using multitask and modified Bayesian compressive sensing. Can. Geotech. J. https://doi.org/10.1139/cgj-2022-0131.