A Bayesian unsupervised learning approach for identifying soil stratification using cone penetration data

Canadian Geotechnical Journal - Tập 56 Số 8 - Trang 1184-1205 - 2019
Hui Wang1, Xiangrong Wang1, Florian Wellmann2, Robert Y. Liang1
1Department of Civil and Environmental Engineering and Engineering Mechanics, The University of Dayton, Dayton, OH 45469-0243, USA
2The Aachen Institute for Advanced Study in Computational Engineering Science (AICES), RWTH Aachen University, Aachen 52062, Germany.

Tóm tắt

This paper presents a novel perspective to understanding the spatial and statistical patterns of a cone penetration dataset and identifying soil stratification using these patterns. Both local consistency in physical space (i.e., along depth) and statistical similarity in feature space (i.e., logQt–logFrspace, where Qtis the normalized tip resistance and Fris the normalized friction ratio, or the Robertson chart) between data points are considered simultaneously. The proposed approach, in essence, consists of two parts: (i) a pattern detection approach using the Bayesian inferential framework and (ii) a pattern interpretation protocol using the Robertson chart. The first part is the mathematical core of the proposed approach, which infers both spatial pattern in physical space and statistical pattern in feature space from the input dataset; the second part converts the abstract patterns into intuitive spatial configurations of multiple soil layers having different soil behavior types. The advantages of the proposed approach include probabilistic soil classification and identification of soil stratification in an automatic and fully unsupervised manner. The proposed approach has been implemented in MATLAB R2015b and Python 3.6, and tested using various datasets including both synthetic and real-world cone penetration test soundings. The results show that the proposed approach can accurately and automatically detect soil layers with quantified uncertainty and reasonable computational cost.

Từ khóa


Tài liệu tham khảo

Barnard J., 2000, Statistica Sinica, 10, 1281

10.1111/j.2517-6161.1974.tb00999.x

10.1111/j.2517-6161.1986.tb01412.x

10.1109/34.865189

10.1007/BF02294361

Briaud, J.L. 2000. The national geotechnical experimentation sites at Texas A&M University: clay and sand, a summary.InNational Geotechnical Experimentation Sites. Geotechnical Special Publication 93. ASCE. pp. 26–51. 10.1061/9780784404843.ch02.

10.1061/(ASCE)GT.1943-5606.0000765

10.1139/cgj-2017-0714

10.1016/0031-3203(94)00125-6

10.1016/S0031-3203(02)00027-4

10.1061/(ASCE)EM.1943-7889.0001240

10.1139/cgj-2015-0027

Ching J.Y., 2017, Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, ASCE-ASME, 3, 04017021, 10.1061/AJRUA6.0000926

10.1016/j.compgeo.2008.02.005

10.1080/17499518.2015.1072637

10.1109/TPAMI.2003.1227985

10.1093/comjnl/41.8.578

10.1198/016214502760047131

Gelman, A., Carlin, J.B., Stern, H.S., Dunson, D.B., Vehtari, A., and Rubin, D.B. 2014. Bayesian data analysis. CRC Press, Boca Raton, Fla.

10.1109/TPAMI.1984.4767596

10.1061/(ASCE)1090-0241(2002)128:12(986)

10.1214/13-BA815

10.1080/17499510701345175

McLachlan, G.J., and Basford, K.E. 1988. Mixture models. Inference and applications to clustering.InStatistics: textbooks and monographs. Vol. 1. Dekker, New York.

McLachlan, G.J., and Krishnan, T. 2007. The EM algorithm and extensions. Wiley-Interscience, New York.

McLachlan, G., and Peel, D. 2004. Finite mixture models. John Wiley & Sons, Hoboken, N.J.

Pedregosa F., 2011, Journal of Machine Learning Research, 12, 2825

10.1139/t99-038

10.1061/(ASCE)1090-0241(2003)129:7(649)

10.1139/t90-014

10.1139/T09-065

10.1007/s11004-016-9663-9

10.1016/j.enggeo.2010.05.013

10.1139/cgj-2013-0004

10.3390/e15041464

10.1016/j.tecto.2011.05.001

10.1111/j.1467-8667.2009.00648.x

10.1061/(ASCE)1090-0241(1999)125:3(179)