Stratigraphic classification prediction method for static cone penetrate test based on XGBoost and Bayesian optimization

Xian Tianlang; Li Xiaohu; Zhang Yun; Huang Jinlong; Chen Gan

doi:10.20265/j.cnki.issn.1007-2993.2024-0165

Volume 39 Issue 5

Oct. 2025

Turn off MathJax

Article Contents

Article Navigation > GEOTECHNICAL ENGINEERING TECHNIQUE > 2025 > 39(5): 656-666

Xian Tianlang, Li Xiaohu, Zhang Yun, Huang Jinlong, Chen Gan. Stratigraphic classification prediction method for static cone penetrate test based on XGBoost and Bayesian optimization[J]. GEOTECHNICAL ENGINEERING TECHNIQUE, 2025, 39(5): 656-666. doi: 10.20265/j.cnki.issn.1007-2993.2024-0165

Citation:

Xian Tianlang, Li Xiaohu, Zhang Yun, Huang Jinlong, Chen Gan. Stratigraphic classification prediction method for static cone penetrate test based on XGBoost and Bayesian optimization[J]. GEOTECHNICAL ENGINEERING TECHNIQUE, 2025, 39(5): 656-666. doi: 10.20265/j.cnki.issn.1007-2993.2024-0165

Citation:

Xian Tianlang, Li Xiaohu, Zhang Yun, Huang Jinlong, Chen Gan. Stratigraphic classification prediction method for static cone penetrate test based on XGBoost and Bayesian optimization[J]. GEOTECHNICAL ENGINEERING TECHNIQUE, 2025, 39(5): 656-666. doi: 10.20265/j.cnki.issn.1007-2993.2024-0165

PDF( 2251 KB)

Stratigraphic classification prediction method for static cone penetrate test based on XGBoost and Bayesian optimization

doi: 10.20265/j.cnki.issn.1007-2993.2024-0165

Guangzhou Design Institute Group Co., Ltd., Guangzhou 510620, Guangdong, China

Received Date: 2024-04-15
Accepted Date: 2024-08-29
Rev Recd Date: 2024-07-11
Publish Date: 2025-10-10

Abstract

Abstract

Stratigraphic classification and soil type identification are the basis for the application of static cone penetrate test results. To achieve accurate stratigraphic classification based on static cone penetrate test data, a prediction method based on eXtreme Gradient Boosting (XGBoost) and Bayesian optimization (BO) was proposed. Using the XGBoost method, a dataset is constructed based on the static cone penetrate test data of a project in South China, the hyperparameters of the XGBoost model were optimised using Bayesian optimisation, and the optimal XGBoost model was constructed to classify and predict the stratigraphic categories. The classification prediction accuracies of the constructed XGBoost model on the training set and the test set are 100% and 96.46%, respectively. The prediction accuracies of the Bayesian-optimised support vector machine (SVM), k-nearest neighbor (KNN) and random forest (RF) models on the test set are 93.34%, 92.99% and 95.89%, respectively, which are lower than those of the XGBoost, proving the superior prediction performances of the XGBoost model. The constructed XGBoost model was used to predict the stratigraphic classification of two boreholes in a geotechnical engineering exploration project in South China, and the prediction accuracy reaches more than 95%, which indicates that the model has a very reliable application value for the stratigraphic classification of static cone penetrate test in the actual geotechnical engineering exploration practice.
- static cone penetrate test,
- stratigraphic classification,
- XGBoost,
- Bayesian optimisation,
- feature importance

FullText(HTML)

References(24)

References

[1]	吴波鸿, 王贵和, 刘宝林, 等. 静力触探在海底土层工程性质评价中的应用研究[J]. 科学技术与工程, 2016, 16(23): 123-128. (WU B H, WANG G H, LIU B L, et al. The application of cone penetration test in subsea soil geotechnical properties evaluation[J]. Science Technology and Engineering, 2016, 16(23): 123-128. (in Chinese) doi: 10.3969/j.issn.1671-1815.2016.23.023 WU B H, WANG G H, LIU B L, et al. The application of cone penetration test in subsea soil geotechnical properties evaluation[J]. Science Technology and Engineering, 2016, 16（23）: 123-128. (in Chinese) doi: 10.3969/j.issn.1671-1815.2016.23.023
[2]	王波, 李建强, 冯涛, 等. 超深孔压静力触探在工程勘察的应用[J]. 铁道工程学报, 2016, 33(8): 44-49. (WANG B, LI J Q, FENG T, et al. Application of super-deep piezocone penetration tests in engineering investigation[J]. Journal of Railway Engineering Society, 2016, 33(8): 44-49. (in Chinese) doi: 10.3969/j.issn.1006-2106.2016.08.010 WANG B, LI J Q, FENG T, et al. Application of super-deep piezocone penetration tests in engineering investigation[J]. Journal of Railway Engineering Society, 2016, 33（8）: 44-49. (in Chinese) doi: 10.3969/j.issn.1006-2106.2016.08.010
[3]	林军, 蔡国军, 刘松玉, 等. 基于孔压静力触探力学分层的土体边界识别方法研究[J]. 岩土力学, 2017, 38(5): 1413-1423. (LIN J, CAI G J, LIU S Y, et al. Identification of soil layer boundaries using mechanical layered method base on piezocone penetration test data[J]. Rock and Soil Mechanics, 2017, 38(5): 1413-1423. (in Chinese) LIN J, CAI G J, LIU S Y, et al. Identification of soil layer boundaries using mechanical layered method base on piezocone penetration test data[J]. Rock and Soil Mechanics, 2017, 38（5）: 1413-1423. (in Chinese)
[4]	曹子君, 郑硕, 李典庆, 等. 基于静力触探的土层自动划分方法与不确定性表征[J]. 岩土工程学报, 2018, 40(2): 336-345. (CAO Z J, ZHENG S, LI D Q, et al. Probabilistic characterization of underground stratigraphy and its uncertainty based on cone penetration test[J]. Chinese Journal of Geotechnical Engineering, 2018, 40(2): 336-345. (in Chinese) doi: 10.11779/CJGE201802015 CAO Z J, ZHENG S, LI D Q, et al. Probabilistic characterization of underground stratigraphy and its uncertainty based on cone penetration test[J]. Chinese Journal of Geotechnical Engineering, 2018, 40（2）: 336-345. (in Chinese) doi: 10.11779/CJGE201802015
[5]	苗永红, 柏国龙. 基于概率神经网络的孔压静力触探的土层界面识别[J]. 济南大学学报(自然科学版), 2017, 31(4): 279-284. (MIAO Y H, BAI G L. Soil layer interface identification using piezocone penetration test based on probabilistic neural network[J]. Journal of University of Jinan (Science and Technology), 2017, 31(4): 279-284. (in Chinese) MIAO Y H, BAI G L. Soil layer interface identification using piezocone penetration test based on probabilistic neural network[J]. Journal of University of Jinan (Science and Technology), 2017, 31（4）: 279-284. (in Chinese)
[6]	吕树胜, 陈培帅, 邱敏, 等. 基于层次聚类算法的静力触探试验土体分类方法及试验研究[J]. 科学技术与工程, 2021, 21(7): 2609-2615. (LÜ S S, CHEN P S, QIU M, et al. Soil classification method and experimental research from CPT based on hierarchical clustering algorithm[J]. Science Technology and Engineering, 2021, 21(7): 2609-2615. (in Chinese) doi: 10.3969/j.issn.1671-1815.2021.07.007 LÜ S S, CHEN P S, QIU M, et al. Soil classification method and experimental research from CPT based on hierarchical clustering algorithm[J]. Science Technology and Engineering, 2021, 21（7）: 2609-2615. (in Chinese) doi: 10.3969/j.issn.1671-1815.2021.07.007
[7]	刘松玉, 蔡国军, 邹海峰. 基于CPTU的中国实用土分类方法研究[J]. 岩土工程学报, 2013, 35(10): 1765-1776. (LIU S Y, CAI G J, ZOU H F. Practical soil classification methods in China based on piezocone penetration tests[J]. Chinese Journal of Geotechnical Engineering, 2013, 35(10): 1765-1776. (in Chinese) LIU S Y, CAI G J, ZOU H F. Practical soil classification methods in China based on piezocone penetration tests[J]. Chinese Journal of Geotechnical Engineering, 2013, 35（10）: 1765-1776. (in Chinese)
[8]	蔡国军, 刘松玉, 童立元, 等. 基于聚类分析理论的CPTU土分类方法研究[J]. 岩土工程学报, 2009, 31(3): 416-424. (CAI G J, LIU S Y, TONG L Y, et al. Soil classification using CPTU data based upon cluster analysis theory[J]. Chinese Journal of Geotechnical Engineering, 2009, 31(3): 416-424. (in Chinese) doi: 10.3321/j.issn:1000-4548.2009.03.018 CAI G J, LIU S Y, TONG L Y, et al. Soil classification using CPTU data based upon cluster analysis theory[J]. Chinese Journal of Geotechnical Engineering, 2009, 31（3）: 416-424. (in Chinese) doi: 10.3321/j.issn:1000-4548.2009.03.018
[9]	ZHU W Y, SONG T R, WANG M C, et al. Stratigraphic subdivision-based logging curves generation using neural random forests[J]. Journal of Petroleum Science and Engineering, 2022, 219: 111086. doi: 10.1016/j.petrol.2022.111086
[10]	ZHANG W G, PHOON K K. Editorial for advances and applications of deep learning and soft computing in geotechnical underground engineering[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(3): 671-673. doi: 10.1016/j.jrmge.2022.01.001
[11]	邱敏, 宋友建, 丛璐, 等. 基于层次聚类算法的孔压静力触探土体分类方法及试验研究[J]. 水文地质工程地质, 2019, 46(3): 117-123. (QIU M, SONG Y J, CONG L, et al. Soil classification method and experimental research on CPTU based on the hierarchical clustering algorithm[J]. Hydrogeology & Engineering Geology, 2019, 46(3): 117-123. (in Chinese) QIU M, SONG Y J, CONG L, et al. Soil classification method and experimental research on CPTU based on the hierarchical clustering algorithm[J]. Hydrogeology & Engineering Geology, 2019, 46（3）: 117-123. (in Chinese)
[12]	徐黎明. 基于支持向量机的双桥静力触探地层自动划分方法[J]. 铁道勘察, 2023, 49(4): 90-95. (XU L M. Automatic method of soil layers division using double bridge static cone penetration test data based on support vector machine[J]. Railway Investigation and Surveying, 2023, 49(4): 90-95. (in Chinese) XU L M. Automatic method of soil layers division using double bridge static cone penetration test data based on support vector machine[J]. Railway Investigation and Surveying, 2023, 49（4）: 90-95. (in Chinese)
[13]	陈振新, 何旭涛, 袁舟龙, 等. 基于自编码神经网络的孔压静力触探海底土层划分方法改进[J]. 工程勘察, 2019, 47(6): 23-28. (CHEN Z X, HE X T, YUAN Z L, et al. Improvement of division method for seabed strata base on piezocone penetration test data with autoencoders[J]. Geotechnical Investigation & Surveying, 2019, 47(6): 23-28. (in Chinese) CHEN Z X, HE X T, YUAN Z L, et al. Improvement of division method for seabed strata base on piezocone penetration test data with autoencoders[J]. Geotechnical Investigation & Surveying, 2019, 47（6）: 23-28. (in Chinese)
[14]	WOOD D A. Predicting porosity, permeability and water saturation applying an optimized nearest-neighbour, machine-learning and data-mining network of well-log data[J]. Journal of Petroleum Science and Engineering, 2020, 184: 106587. doi: 10.1016/j.petrol.2019.106587
[15]	LI S L, ZHANG X J. Research on orthopedic auxiliary classification and prediction model based on XGBoost algorithm[J]. Neural Computing and Applications, 2020, 32(7): 1971-1979. doi: 10.1007/s00521-019-04378-4
[16]	CHEN T Q, GUESTRIN C. XGBoost: a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: Association for Computing Machinery, 2016: 785-794.
[17]	WANG T T, BIAN Y J, ZHANG Y X, et al. Classification of earthquakes, explosions and mining-induced earthquakes based on XGBoost algorithm[J]. Computers & Geosciences, 2023, 170: 105242.
[18]	GENG X J, WU S C, ZHANG Y J, et al. Developing hybrid XGBoost model integrated with entropy weight and Bayesian optimization for predicting tunnel squeezing intensity[J]. Natural Hazards, 2023, 119(1): 751-771. doi: 10.1007/s11069-023-06137-0
[19]	ZHANG W G, WU C Z, ZHONG H Y, 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: 10.1016/j.gsf.2020.03.007
[20]	PANTELEEV A V, LOBANOV A V. Mini-batch adaptive random search method for the parametric identification of dynamic systems[J]. Automation and Remote Control, 2020, 81(11): 2026-2045. doi: 10.1134/S0005117920110065
[21]	BHAT P C, PROSPER H B, SEKMEN S, et al. Optimizing event selection with the random grid search[J]. Computer Physics Communications, 2018, 228: 245-257. doi: 10.1016/j.cpc.2018.02.018
[22]	GHAHRAMANI Z. Probabilistic machine learning and artificial intelligence[J]. Nature, 2015, 521(7553): 452-459. doi: 10.1038/nature14541
[23]	XIA Y F, LIU C Z, LI Y Y, et al. A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring[J]. Expert Systems with Applications, 2017, 78: 225-241. doi: 10.1016/j.eswa.2017.02.017
[24]	QIU Y G, ZHOU J, KHANDELWAL M, et al. Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration[J]. Engineering with Computers, 2022, 38(S5): 4145-4162. doi: 10.1007/s00366-021-01393-9

Relative Articles

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(13) / Tables(5)

Get Citation

PDF

XML

Article Metrics

Article views (25) PDF downloads(6)

Stratigraphic classification prediction method for static cone penetrate test based on XGBoost and Bayesian optimization

doi: 10.20265/j.cnki.issn.1007-2993.2024-0165

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Stratigraphic classification prediction method for static cone penetrate test based on XGBoost and Bayesian optimization

doi: 10.20265/j.cnki.issn.1007-2993.2024-0165

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Export File

Citation

Format

Content