Application of machine learning to the identification of quick and highly sensitive clays from cone penetration tests

应用机器学习方法从静力触探结果中识别快黏土和高灵敏度黏土

Abstract

Geotechnical classification is vital for site characterization and geotechnical design. Field tests such as the cone penetration test with pore water pressure measurement (CPTu) are widespread because they represent a faster and cheaper alternative for sample recovery and testing. However, classification schemes based on CPTu measurements are fairly generic because they represent a wide variety of soil conditions and, occasionally, they may fail when used in special soil types like sensitive or quick clays. Quick and highly sensitive clay soils in Norway have unique conditions that make them difficult to be identified through general classification charts. Therefore, new approaches to address this task are required. The following study applies machine learning methods such as logistic regression, Naive Bayes, and hidden Markov models to classify quick and highly sensitive clays at two sites in Norway based on normalized CPTu measurements. Results showed a considerable increase in the classification accuracy despite limited training sets.

概要

目的

研究机器学习技术在利用孔压静力触探测试(CPTu)识别高灵敏度黏土和快黏土的潜力。

创新点

1. 成功应用机器学习方法从CPTu结果中分类出高灵敏度黏土和快黏土,并将结果与不同地点的实际土层进行了比较。 2. 通过对机器学习算法的多次训练确定了可以获得良好结果的最少CPTu个数。

方法

1. 基于对两个位置已知和土层确定的CPTu数据集的分析,使用3种机器学习图像分类方法(逻辑回归、朴素贝叶斯和隐藏马尔科夫模型)将CPTu数据用于样本分类。2. 将结果与实际土层进行比较,识别高灵敏度黏土和快黏土,并从计算性能度量方面比较3个方法的优缺点。

结论

仅采用4个CPTu训练样本便可获得基于逻辑回归、朴素贝叶斯和隐藏马尔科夫模型的识别高灵敏度黏土和快黏土的3个分类模型,且分类精度良好。

References

  1. Eslami A, Fellenius BH, 1997. Pile capacity by direct CPT and CPTu methods applied to 102 case histories. Canadian Geotechnical Journal, 34(6):886–904. https://doi.org/10.1139/t97-056

    Article  Google Scholar 

  2. Gylland AS, Sandven R, Montafia A, et al., 2017. CPTU classification diagrams for identification of sensitive clays. In: Thakur V, L’Heureux JS, Locat A (Eds.), Landslides in Sensitive Clays. Springer, Cham, Switzerland, p.57–66. https://doi.org/10.1007/978-3-319-56487-6_5

    Google Scholar 

  3. hmmlearn, 2010. hmmlearn: Unsupervised Learning and Inference of Hidden Markov Models. hmmlearn. https://hmmlearn.readthedocs.io

  4. L’Heureux J, Lindgård A, Emdal A, 2019. The Tiller-Flotten Research Site: Geotechnical Characterization of a Very Sensitive Clay Deposit. Technical Report No. 20160154-20-R. Norwegian Geotechnical Institute, Norway.

    Google Scholar 

  5. Lunne T, Robertson PK, Powell JJM, 1997. Cone Penetration Testing in Geotechnical Practice. Blackie Academic and Professional, London, UK.

    Google Scholar 

  6. NGI (Norwegian Geotechnical Institute), 2019. NGTS-Norwegian Geo-test Sites. NGI. https://www.ngi.no/eng/Projects/NGTS-Norwegian-Geo-Test-Sites

  7. Pedregosa F, Varoquaux G, Gramfort A, et al., 2011. Scikitlearn: machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.

    MathSciNet  MATH  Google Scholar 

  8. Robertson PK, 1990. Soil classification using the cone penetration test. Canadian Geotechnical Journal, 27(1):151–158. https://doi.org/10.1139/t90-014

    MathSciNet  Article  Google Scholar 

  9. Robertson PK, 2016. Cone penetration test (CPT)-based soil behaviour type (SBT) classification system-an update. Canadian Geotechnical Journal, 53(12):1910–1927. https://doi.org/10.1139/cgj-2016-0044

    Article  Google Scholar 

  10. Schneider JA, Randolph MF, Mayne PW, et al., 2008. Analysis of factors influencing soil classification using normalized piezocone tip resistance and pore pressure parameters. Journal of Geotechnical and Geoenvironmental Engineering, 134(11):1569–1586. https://doi.org/10.1061/(ASCE)1090-0241(2008)134:11(1569)

    Article  Google Scholar 

  11. Scikit-learn, 2019. Scikit-learn User Guide. Release 0.21.2.Scikit-learn. https://scikit-learn.org/dev/versions.html

  12. Statens Vegvesen, 2013. County Road 715 Keiserås-Olsøy, Parcel: Leksvik Border-Olsøy. Data Report Nr. 2012039995-009/Ud925Ar09. Rissa, Norway (in Norwegian).

  13. Valsson SM, 2016. Detecting quick clay with CPTu. Proceedings of the 17th Nordic Geotechnical Meeting: Challenges in Nordic Geotechnics.

  14. vanRossum G, 1995. Python Reference Manual. Technical Report No. CS-R9525. Centrum Wiskunde & Informatica, Amsterdam, The Netherlands.

    Google Scholar 

  15. Wickremesinghe DS, 1989. Statistical Characterization of Soil Profiles Using in Situ Tests. PhD Thesis, University of British Columbia, Vancouver, Canada. https://doi.org/10.14288/1.0062495

    Google Scholar 

Download references

Acknowledgments

The authors acknowledge NGI and Statens Vegvesen, Norway for the data support.

Funding

Open access funding provided by NTNU Norwegian University of Science and Technology (incl St. Olavs Hospital - Trondheim University Hospital)

Author information

Affiliations

Authors

Contributions

Vikas THAKUR and Ivan DEPINA designed the research. Cristian GODOY processed the corresponding data and wrote the first draft of the manuscript. Ivan DEPINA helped to organize the manuscript. Cristian GODOY and Ivan DEPINA revised and edited the final version.

Corresponding author

Correspondence to Cristian Godoy.

Additional information

Conflict of interest

Cristian GODOY, Ivan DEPINA, and Vikas THAKUR declare that they have no conflict of interest.

Project supported by the CONICYT Programa Formacion de Capital Humano Avanzado/Master Becas Chile (No. 2017-73180687)

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, duplication, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made..

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Godoy, C., Depina, I. & Thakur, V. Application of machine learning to the identification of quick and highly sensitive clays from cone penetration tests. J. Zhejiang Univ. Sci. A 21, 445–461 (2020). https://doi.org/10.1631/jzus.A1900556

Download citation

Key words

  • Machine learning
  • Classification
  • Quick clays
  • Sensitive clays

CLC number

  • TU19

关键词

  • 机器学习
  • 分类
  • 快黏土
  • 高灵敏度黏土