SpringerLink
Log in

Prediction on compression indicators of clay soils using XGBoost with Bayesian optimization

基于贝叶斯优化XGBoost 模型的黏土压缩指标预测

  • Published:
Journal of Central South University Aims and scope Submit manuscript

Abstract

The determination of the compressibility of clay soils is a major concern during the design and construction of geotechnical engineering projects. Directly acquiring precise values of compression indicators from consolidation tests are cumbersome and time-consuming. Based on experimental results from a series of index tests, this study presents a hybrid method that combines the XGBoost model with the Bayesian optimization strategy to show the potential for achieving higher accuracy in predicting the compressibility indicators of clay soils. The results show that the proposed XGBoost model selected by Bayesian optimization can predict compression indicators more accurately and reliably than the artificial neural network (ANN) and support vector machine (SVM) models. In addition to the lowest prediction error, the proposed XGBoost-based method enhances the interpretability by feature importance analysis, which indicates that the void ratio is the most important factor when predicting the compressibility of clay soils. This paper highlights the promising prospect of the XGBoost model with Bayesian optimization for predicting unknown property parameters of clay soils and its capability to benefit the entire life cycle of engineering projects.

摘要

在岩土工程的设计和实践中, 准确评估黏土的压缩性是一个至关重要问题。鉴于直接从固结试 验中获取压缩指标繁琐耗时, 提出了一种将XGBoost 模型与贝叶斯优化策略耦合的机器学**模型对黏 土的主要性能指标进行预测。结果表明, 贝叶斯优化的XGBoost 模型通过特征重要性分析增**了机器 学**模型的可解释性, 揭示出孔隙率是预测黏土压缩性能时最为关键的特征量;与传统的人工神经网 络(ANN)和支持向量机(SVM)模型相比, 贝叶斯优化的XGBoost 模型预测误差最小, 能实现对黏土压 缩指标更为准确和可靠的预测。

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. JIAO Chen-jiang, YOU Shuang, JI Hong-guang. Numerical analysis of building structures response under effect of continuous and stepped non-uniform settlement [J]. Journal of Central South University, 2023, 30(12): 4066–4081. DOI: https://doi.org/10.1007/s11771-023-5519-x.

    Article  Google Scholar 

  2. GONG Chen-jie, XIE Chao-ran, LIN Zan-quan, et al. Ground deformation prediction induced by shield tunnelling considering existing multi-story buildings [J]. Journal of Central South University, 2023, 30(4): 1373–1387. DOI: https://doi.org/10.1007/s11771-023-5307-7.

    Article  Google Scholar 

  3. TERZAGHI K, PECK R B, MESRI G. Soil mechanics in engineering practice [M]. John Wiley & Sons, 1956.

  4. AZZOUZ A S, KRIZEK R J, COROTIS R B. Regression analysis of soil compressibility [J]. Soils and Foundations, 1976, 16(2): 19–29. DOI: https://doi.org/10.3208/sandf1972.16.2_19.

    Article  Google Scholar 

  5. YOON G L, KIM B T, JEON S S. Empirical correlations of compression index for marine clay from regression analysis [J]. Canadian Geotechnical Journal, 2004, 41(6): 1213–1221. DOI: https://doi.org/10.1139/T04-057.

    Article  Google Scholar 

  6. SHIMOBE S, SPAGNOLI G. A general overview on the correlation of compression Index of clays with some geotechnical index properties [J]. Geotechnical and Geological Engineering, 2022, 40(1): 311–324. DOI: https://doi.org/10.1007/s10706-021-01888-8.

    Article  Google Scholar 

  7. LECUN Y, BENGIO Y, HINTON G. Deep learning [J]. Nature, 2015, 521(7553): 436–444. DOI: https://doi.org/10.1038/nature14539.

    Article  Google Scholar 

  8. ZHANG Wen-gang, ZHANG Run-hong, WU Chong-zhi, et al. State-of-the-art review of soft computing applications in underground excavations [J]. Geoscience Frontiers, 2020, 11(4): 1095–1106. DOI: https://doi.org/10.1016/j.gsf.2019.12.003.

    Article  Google Scholar 

  9. ZHANG Wen-gang, LI Hong-rui, LI Yong-qin, et al. Application of deep learning algorithms in geotechnical engineering: A short critical review [J]. Artificial Intelligence Review, 2021: 1–41. DOI: https://doi.org/10.1007/s10462-021-09967-1.

  10. ZHANG Zi-long, PAN Qiu-**g, YANG Zi-han, et al. Physics-informed deep learning method for predicting tunnelling-induced ground deformations [J]. Acta Geotechnica, 2023: 1–16. DOI: https://doi.org/10.1007/s11440-023-01874-9.

  11. PARK H I, LEE S R. Evaluation of the compression index of soils using an artificial neural network [J]. Computers and Geotechnics, 2011, 38(4): 472–481. DOI: https://doi.org/10.1016/j.compgeo.2011.02.011.

    Article  Google Scholar 

  12. ALADAG C H, KAYABASI A, GOKCEOGLU C. Estimation of pressuremeter modulus and limit pressure of clayey soils by various artificial neural network models [J]. Neural Computing and Applications, 2013, 23: 333–339. DOI: https://doi.org/10.1007/s00521-012-0900-y.

    Article  Google Scholar 

  13. BENBOURAS M A, KETTAB M R, ZEDIRA H, et al. A new approach to predict the compression index using artificial intelligence methods [J]. Marine Georesources & Geotechnology, 2019, 37(6): 704–720. DOI: https://doi.org/10.1080/1064119X.2018.1484533.

    Article  Google Scholar 

  14. PHAM B T, NGUYEN M D, van DAO D, et al. Development of artificial intelligence models for the prediction of compression coefficient of soil: An application of Monte Carlo sensitivity analysis [J]. Science of the Total Environment, 2019, 679: 172–184. DOI: https://doi.org/10.1016/j.scitotenv.2019.05.061.

    Article  Google Scholar 

  15. ZHANG Dong-ming, ZHANG **-zhang, HUANG Hong-wei, et al. Machine learning-based prediction of soil compression modulus with application of 1D settlement [J]. Journal of Zhejiang University-Science A (Applied Physics & Engineering), 2020, 21(6): 430–444. DOI: https://doi.org/10.1631/jzus.A1900515.

    Article  Google Scholar 

  16. BUI D T, NHU V H, HOANG N D. Prediction of soil compression coefficient for urban housing project using novel integration machine learning approach of swarm intelligence and multi-layer perceptron neural network [J]. Advanced Engineering Informatics, 2018, 38: 593–604. DOI: https://doi.org/10.1016/j.aei.2018.09.005.

    Article  Google Scholar 

  17. ASTERIS P G, MAMOU A, FERENTINOU M, et al. Predicting clay compressibility using a novel Manta ray foraging optimization-based extreme learning machine model [J]. Transportation Geotechnics, 2022, 37: 100861. DOI: https://doi.org/10.1016/j.trgeo.2022.100861.

    Article  Google Scholar 

  18. ZHANG Zi-long, ZHANG Ting-ting, LI **ao-zhou, et al. Bayesian ensemble methods for predicting ground deformation due to tunnelling with sparse monitoring data [J]. Underground Space, 2024, 16: 79–93. DOI: https://doi.org/10.1016/j.undsp.2023.09.001.

    Article  Google Scholar 

  19. ZHANG Pin, YIN Zhen-yu, JIN Yin-fu, et al. Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms [J]. Geoscience Frontiers, 2021, 12(1): 441–452. DOI: https://doi.org/10.1016/j.gsf.2020.02.014.

    Article  Google Scholar 

  20. ZHU **ng, CHU Jian, WANG Kang-daet al. Prediction of rockhead using a hybrid N-XGBoost machine learning framework [J]. Journal of Rock Mechanics and Geotechnical Engineering, 2021, 13(6): 1231–1245. DOI: https://doi.org/10.1016/j.jrmge.2021.06.012.

    Article  Google Scholar 

  21. ZHANG Bao-yi, LI Man-yi, LI Wei-xia, et al. Machine learning strategies for lithostratigraphic classification based on geochemical sampling data: A case study in area of Chahanwusu River, Qinghai Province, China [J]. Journal of Central South University, 2021, 28(5): 1422–1447. DOI: https://doi.org/10.1007/s11771-021-4707-9.

    Article  Google Scholar 

  22. ZHANG Wen-gang, WU Chong-zhi, ZHONG Hai-yi, et al. Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization [J]. Geoscience Frontiers, 2021, 12(1): 469–477. DOI: https://doi.org/10.1016/j.gsf.2020.03.007.

    Article  Google Scholar 

  23. SHAHANI N M, ZHENG ** an XGBoost regression model for predicting young’s modulus of intact sedimentary rocks for the stability of surface and subsurface structures [J]. Frontiers in Earth Science, 2021, 9: 761990. DOI: https://doi.org/10.3389/feart.2021.761990.

    Article  Google Scholar 

  24. MA Ke, SHEN Qing-qing, SUN **ng-ye, et al. Rockburst prediction model using machine learning based on microseismic parameters of Qinling water conveyance tunnel [J]. Journal of Central South University, 2023, 30(1): 289–305. DOI: https://doi.org/10.1007/s11771-023-5233-8.

    Article  Google Scholar 

  25. PHOON K K, KULHAWY F H. Characterization of geotechnical variability [J]. Canadian Geotechnical Journal, 1999, 36(4): 612–624. DOI: https://doi.org/10.1139/t99-038.

    Article  Google Scholar 

  26. PAN Qiu-**g, WU Hong-tao, SU Dong, et al. Multivariate probability distributions for index and mechanical clay parameters in Shenzhen [J]. Computers and Geotechnics, 2024, 165: 105934. DOI: https://doi.org/10.1016/j.compgeo.2023.105934.

    Article  Google Scholar 

  27. LIN Pei-yuan, CHEN ** shear strength and compressibility of soft soils with artificial neural networks [J]. Engineering Geology, 2022, 300: 106585. DOI: https://doi.org/10.1016/j.enggeo.2022.106585.

    Article  Google Scholar 

  28. LIU Hui-fen, LIN Pei-yuan, WANG Jian-qiang. Machine learning approaches to estimation of the compressibility of soft soils [J]. Frontiers in Earth Science, 2023, 11: 1147825. DOI: https://doi.org/10.3389/feart.2023.1147825.

    Article  Google Scholar 

  29. SMITI A. A critical overview of outlier detection methods [J]. Computer Science Review, 2020, 38: 100306. DOI: https://doi.org/10.1016/j.cosrev.2020.100306.

    Article  MathSciNet  Google Scholar 

  30. KAASTRA I, BOYD M. Designing a neural network for forecasting financial and economic time series [J]. Neurocomputing, 1996, 10(3): 215–236. DOI: https://doi.org/10.1016/0925-2312(95)00039-9.

    Article  Google Scholar 

  31. CHEN Tian-qi, GUESTRIN C. Xgboost: A scalable tree boosting system [C]// Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining. 2016: 785–794. DOI: https://doi.org/10.1145/2939672.2939785.

  32. ZHANG Wen-gang, LI Hong-rui, WU Chong-zhi, et al. Soft computing approach for prediction of surface settlement induced by earth pressure balance shield tunneling [J]. Underground Space, 2021, 6(4): 353–363. DOI: https://doi.org/10.1016/j.undsp.2019.12.003.

    Article  Google Scholar 

  33. TURNER R, ERIKSSON D, MCCOURT M, et al. Bayesian optimization is superior to random search for machine learning hyperparameter tuning: Analysis of the black-box optimization challenge 2020 [C]// NeurIPS 2020 Competition and Demonstration Track. PMLR, 2021: 3–26. DOI: https://doi.org/10.48550/ar**v.2104.10201.

  34. SU Jie, WANG Yu-zhe, NIU **ao-kai, et al. Prediction of ground surface settlement by shield tunneling using XGBoost and Bayesian Optimization [J]. Engineering Applications of Artificial Intelligence, 2022, 114: 105020. DOI: https://doi.org/10.1016/j.engappai.2022.105020.

    Article  Google Scholar 

  35. HUANG Chang-fu, LI Qun, WU Shun-chuan, et al. Assessment of empirical equations of the compression index of muddy clay: sensitivity to geographic locality [J]. Arabian Journal of Geosciences, 2019, 12: 1–13. DOI: https://doi.org/10.1007/s12517-019-4276-5.

    Article  Google Scholar 

  36. ALZABEEBEE S, ALSHKANE Y M, RASHED K A. Evolutionary computing of the compression index of finegrained soils [J]. Arabian Journal of Geosciences, 2021, 14(19): 2040. DOI: https://doi.org/10.1007/s12517-021-08319-1.

    Article  Google Scholar 

  37. ZHAO You-ming, JIANG Hui-huang, ZHANG Hui-ming. Deformation parameters of Shenzhen soft clay [J]. China Railway Science, 2004, 25(3): 40–43.

    Google Scholar 

  38. ZHANG Zhan-rong. Correlation analysis of soil parameters in the western coastal railway of Guangdong [J]. Urban Geology, 2012, 7(1): 31–34.

    Google Scholar 

  39. HERRERO O R. Closure to “universal compression index equation” by Oswald Rendon-Herrero (November, 1980) [J]. Journal of Geotechnical Engineering, 1983, 109(5): 755–761. DOI: https://doi.org/10.1061/(ASCE)0733-9410(1983)109:5(755).

    Article  Google Scholar 

  40. KALANTARY F, KORDNAEIJ A. Prediction of compression index using artificial neural network [J]. Scientific Research and Essays, 2012, 7(31): 2835–2848. DOI: https://doi.org/10.5897/SRE12.297.

    Google Scholar 

  41. MAYNE P W. Cam-clay predications of undrained strength [J]. Journal of the Geotechnical Engineering Division, 1980, 106(11): 1219–1242. DOI: https://doi.org/10.1061/AJGEB6.0001060.

    Article  Google Scholar 

  42. OBAJI N O, KOMOLAFE O O, OKE J A. Prediction of initial void ratio from the natural moisture content of cohesive soils [J]. Uniabuja J. Eng. Technol, 2020, 1: 1–13.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Civil Engineering, Central South University, Changsha, 410075, China

    Hong-tao Wu  (吴洪涛) & Zi-long Zhang  (张子龙)

  2. Laboratory 3SR, Grenoble Alpes University, CNRS UMR 5521, Grenoble, 38000, France

    Zi-long Zhang  (张子龙) & Daniel Dias

Authors
  1. Hong-tao Wu  (吴洪涛)
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zi-long Zhang  (张子龙)
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Daniel Dias
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

The overarching research goals were developed by WU Hong-tao, ZHANG Zi-long, and Daniel DIAS. WU Hong-tao and ZHANG Zi-long conducted the literature review, wrote the draft, and completed the modeling processing. Daniel DIAS aided in editing and polishing the original draft. All authors replied to reviewers’ comments and revised the final version.

Corresponding author

Correspondence to Zi-long Zhang  (张子龙).

Ethics declarations

WU Hong-tao, ZHANG Zi-long, and Daniel DIAS declare that they have no conflict of interest.

Additional information

Foundation item: Project(202206370130) supported by the China Scholarship Council; Project(2023ZZTS0034) supported by the Fundamental Research Funds for the Central Universities, China

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wu, Ht., Zhang, Zl. & Dias, D. Prediction on compression indicators of clay soils using XGBoost with Bayesian optimization. J. Cent. South Univ. (2024). https://doi.org/10.1007/s11771-024-5681-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11771-024-5681-9

Key words

关键词

Search

Navigation