岩石强度的可解释性预测：基于COA⁃LightGBM⁃SHAP框架

张岩; 杨奇来; 罗璟; 刘亚斌; 简怀磊; 曾鹏; 李天斌

doi:10.3799/dqkx.2026.261

您当前的位置：

首页 >

文章列表页 >

岩石强度的可解释性预测：基于COA⁃LightGBM⁃SHAP框架

更新时间：2026-10-15

- 岩石强度的可解释性预测：基于COA⁃LightGBM⁃SHAP框架
- Interpretable Prediction of Rock Strength: A Study Based on the COA⁃LightGBM⁃SHAP Framework
- 地球科学 2026年51卷第9期页码：3433-3444
- 作者机构：
  
  1.成都理工大学地质灾害防治与地质环境保护全国重点实验室，四川成都 610059
  2.陕西兴通监理咨询有限公司，陕西西安 710061
- 作者简介：
  
  张岩（1988—），男，研究员，主要从事地下工程地质灾害机理与防控研究.ORCID：0000⁃0002⁃4791⁃7081. E⁃mail：zhylr1988@126.com
  罗璟，ORCID: 0000⁃0001⁃6746⁃1520. E⁃mail：luoj@cdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(42130719);四川省自然科学基金项目(2025ZNSFSC0097)
- DOI：10.3799/dqkx.2026.261
  中图分类号： P642
- 收稿：2026-01-26，
  
  纸质出版：2026-09-30
- 稿件说明：
移动端阅览
张岩，杨奇来，罗璟，刘亚斌，简怀磊，曾鹏，李天斌，2026.岩石强度的可解释性预测：基于COA⁃LightGBM⁃SHAP框架.地球科学，51（9）：3433-3444.

Zhang Yan，Yang Qilai，Luo Jing，Liu Yabin，Jian Huailei，Zeng Peng，Li Tianbin，2026.Interpretable Prediction of Rock Strength： A Study Based on the COA⁃LightGBM⁃SHAP Framework.Earth Science，51（9）：3433-3444.
张岩，杨奇来，罗璟，刘亚斌，简怀磊，曾鹏，李天斌，2026.岩石强度的可解释性预测：基于COA⁃LightGBM⁃SHAP框架.地球科学，51（9）：3433-3444. DOI： 10.3799/dqkx.2026.261.

Zhang Yan，Yang Qilai，Luo Jing，Liu Yabin，Jian Huailei，Zeng Peng，Li Tianbin，2026.Interpretable Prediction of Rock Strength： A Study Based on the COA⁃LightGBM⁃SHAP Framework.Earth Science，51（9）：3433-3444. DOI： 10.3799/dqkx.2026.261.

摘要

岩石单轴抗压强度（UCS）是表征岩体力学特性的核心参数，在工程稳定性分析中具有重要作用.然而，由于岩石材料的复杂性，高效且精确地确定UCS仍是一项重大挑战.本研究通过将Light Gradient Boosting Machine（LightGBM）与Coati优化算法（COA）相结合，开发了一个稳健的预测框架.基于包含273组岩石样本的综合数据库，利用COA系统地优化了LightGBM模型的超参数.研究结果表明，COA-LightGBM模型在岩石单轴抗压强度预测中表现卓越，其RMSE、

R²

和MAE值分别为20.48、0.83和15.24.对比试验结果表明，COA-LightGBM模型在岩石单轴抗压强度预测上的性能显著优于最近邻（KNN）、决策树（DT）、随机森林（RF）等对比模型.此外，引入了Shapley Additive Explanations（SHAP）方法来阐明内部决策机制，并弥合“黑箱”模型与物理可解释性之间的差距.特征分析表明，孔隙率（

）是控制岩石强度的最关键因素.这项研究不仅证实了COA优越的优化能力，还为工程实践中岩石力学参数的快速评估提供了科学且可解释的解决方案.

Abstract

Uniaxial compressive strength (UCS) is a fundamental parameter for characterizing the mechanical behavior of rock masses which is essential for geotechnical stability analysis. However

the efficient and precise determination of UCS remains a significant challenge due to the complexity of rock materials. This study develops a robust predictive framework by integrating the Light Gradient Boosting Machine (LightGBM) with the Coati Optimization Algorithm (COA). Based on a comprehensive database of 273 rock samples

the COA is utilized to systematically optimize the hyperparameters of the LightGBM model. The results indicate that the proposed COA-LightGBM model exhibits exceptional predictive accuracy

achieving an RMSE of 20.48

of 0.83

and an MAE of 15.24. Comparative analyses demonstrate that the COA-LightGBM model significantly outperforms conventional models such as K-Nearest Neighbors

Decision Trees

and Random Forests. Furthermore

the Shapley Additive Explanations (SHAP) method is introduced to elucidate the internal decision-making mechanism and bridge the gap between “black-box” models and physical interpretability. Feature analysis reveals that porosity (

) is the most critical factor governing rock strength. This research not only validates the superior optimization capability of COA but al

so provides a scientific and interpretable solution for the rapid assessment of rock mechanical parameters in engineering practice.

关键词

Keywords

references

Armaghani, D. J., Tonnizam Mohamad, E., Momeni, E., et al., 2016. Prediction of the Strength and Elasticity Modulus of Granite through an Expert Artificial Neural Network. Arabian Journal of Geosciences , 9 (1): 48. https://doi.org/10.1007/s12517⁃015⁃2057⁃3

Chen, C., Seo, H., 2023. Prediction of Rock Mass Class Ahead of TBM Excavation Face by ML and DL Algorithms with Bayesian TPE Optimization and SHAP Feature Analysis. Acta Geotechnica , 18 ( 7 ): 3825 - 3848 . https://doi.org/10.1007/s11440⁃022⁃01779⁃z

Chen, J., Tang, H., Chen, W. K., et al., 2022. A Prediction Method of Ground Motion for Regions without Available Observation Data (LGB⁃FS) and Its Application to both Yangbi and Maduo Earthquakes in 2021. Journal of Earth Science , 33 ( 4 ): 869 - 884 . https://doi.org/10.1007/s12583⁃021⁃1560⁃6

Chen, Z. Y., Ren, T., Zhao, D., 2025. TPE⁃SVM Model and SHAP Analysis to Identify PB⁃ZN Deposit Types Based on Sphalerite Trace Elements. Earth Science , 50 ( 11 ): 4355 - 4369 (in Chinese with English abstract) .

Daniel, C., Gao, F., Yin, X., et al., 2025. Exploring the Interpretability of Mach ine Learning Approaches in Modelling the Uniaxial Compressive Strength of Rocks. Mining , Metallurgy & Exploration , 42 ( 4 ): 2471 - 2497 . https://doi.org/10.1007/s42461⁃025⁃01282⁃5

Daviran, M., Ghezelbash, R., 2026. Detecting Low⁃Risk Exploration Targets from Automated Tuned Machine Learning Algorithms: Hybrid Particle Swarm Optimization, Grid Search and Genetic Optimization Algorithms with Support Vector Machine. Journal of Earth Science , 37 ( 2 ): 843 - 869 . https://doi.org/10.1007/s12583⁃025⁃0276⁃4

Dehghan, S., Sattari, G., CHEHREH CHELGANI, S., et al., 2010. Prediction of Uniaxial Compressive Strength and Modulus of Elasticity for Travertine Samples Using Regression and Artificial Neural Networks. Mining Science and Technology ( China ), 20 ( 1 ): 41 - 46 . https://doi.org/10.1016/S1674⁃5264(09)60158⁃7

Dehghani, M., Montazeri, Z., Trojovská, E., et al., 2023. Coati Optimization Algorithm: A New Bio⁃Inspired Metaheuristic Algorithm for Solving Optimization Problems. Knowledge⁃Based Systems , 259 : 110011. https://doi.org/10.1016/j.knosys.2022.110011

Deng, Z. H., Zhang, L. M., Xu, X. H., et al., 2024. Evaluation for Broken Line Slope Stability Based on Ensemble Learning and LEM. Earth Science , 49 ( 11 ): 4216 - 4224 (in Chinese with English abstract) .

Fang, D. M., 2001. Main Problems and Determination of Foundation Strength of Pier of the Second Nanjing Bridge. Earth Science , 26 ( 4 ): 406 - 409 (in Chinese with English abstract) .

Kılıç, A., Teymen, A., 2008. Determination of Mechanical Properties of Rocks Using Simple Methods. Bulletin of Engineering Geology and the Environment , 67 ( 2 ): 237 - 244 . https://doi.org/10.1007/s10064⁃008⁃0128⁃3

Lei, Y., Zhou, S. T., Luo, X. D., et al., 2022. A Comparative Study of Six Hybrid Prediction Models for Uniaxial Compressive Strength of Rock Based on Swarm Intelligence Optimization Algorithms. Frontiers in Earth Science , 10 : 930130. https://doi.org/10.3389/feart.2022.930130

Li, H. B., Li, X., Wang, S. J., et al., 2024. Cross Project Conversion Relationship of Key Parameters of TBM Rock Breaking. Earth Science , 49 ( 5 ): 1722 - 1735 (in Chinese with English abstract) .

Li, W., Tan, Z. Y., 2016. Comparison on Rock Strength Prediction Models Based on MLR and LS⁃SVM. Mining Research and Development , 36 ( 11 ): 36 - 40 (in Chinese with English abstract) .

Li, W., Tan, Z. Y., 2017. Research on Rock Strength Prediction Based on Least Squares Support Vector Machine. Geotechnical and Geological Engineering , 35 ( 1 ): 385 - 393 . https://doi.org/10.1007/s10706⁃016⁃0114⁃7

Li, Z., Zhang, Z. X., Yang, J., et al., 2019. Research and Application of Formation Pressure Monitoring while Drilling in Deepwater with High Temperature and High Pressure. Earth Science , 44 ( 8 ): 2597 - 2602 (in Chinese with English abstract) .

Mahmoodzadeh, A., Mohammadi, M., Hashim Ibrahim, H., et al., 2021. Artificial Intelligence Forecasting Models of Uniaxial Compressive Strength. Transportation Geotechnics , 27 : 100499. https://doi.org/10.1016/j.trgeo.2020.100499

Matin, S. S., Farahzadi, L., Makaremi, S., et al., 2018. Variable Selection and Prediction of Uniaxial Compressive Strength and Modulus of Elasticity by Random Forest. Applied Soft Computing , 70 : 980 - 987 . https://doi.org/10.1016/j.asoc.2017.06.030

Mishra, D. A., Basu, A., 2013. Estimation of Uniaxial Compressive Strength of Rock Materials by Index Tests Using Regression Analysis and Fuzzy Inference System. Engineering Geology , 160 : 54 - 68 . https://doi.org/10.1016/j.enggeo.2013.04.004

Ng, I. T., Yuen, K. V., Lau, C. H., 2015. Predictive Model for Uniaxial Compressive Strength for Grade III Granitic Rocks from Macao. Engineering Geology , 199 : 28 - 37 . https://doi.org/10.1016/j.enggeo.2015.10.008

Wang, W., Li, Y. L., Wu, N. Y., 2026. Urgent Need of Submarine Landslide Risk Monitoring after 2025 Mega⁃Quake off Coast of Kamchatka. Journal of Earth Science , 37 ( 3 ): 1513 - 1518 . https://doi.org/10.1007/s12583⁃026⁃0047⁃x

Wei, M. D., Meng, W. Z., Dai, F., et al., 2022. Application of Machine Learning in Predicting the Rate⁃Dependent Compressive Strength of Rocks. Journal of Rock Mechanics and Geotechnical Engineering , 14 ( 5 ): 1356 - 1365 . https://doi.org/10.1016/j.jrmge.2022.01.008

Wu, L. Y., Li, J. H., Ma, D., et al., 2023. Prediction for Rock Compressive Strength Based on Ensemble Learning and Bayesian Optimization. Earth Science , 48 ( 5 ): 1686 - 1695 (in Chinese with English abstract) .

Wu, S. C., Wang, Y. C., Zhang, H. J., 2022. Study on Prediction Method of Uniaxial Co mpressive Strength of Rocks Based on Stacking Ensemble Algorithm. Mining Research and Development , 42 ( 6 ): 105 - 111 (in Chinese with English abstract) .

Xie, H. H., Lin, P., Kang, J. T., et al., 2024. Prediction Method of Rock Uniaxial Compressive Strength Based on Feature Optimization and SSA⁃XGBoost. Sustainability , 16 (19): 8460. https://doi.org/10.3390/su16198460

Yu, Y. L., Cai, H. C., Chen, C. W., et al., 2026. Reconstruction Modeling⁃Driven Analysis of Shale Oil Production Dynamics Using Explainable Machine Learning CatBoost⁃SHAP: A Case Study from the Bohai Bay Basin. Journal of Earth Science , 37 ( 2 ): 923 - 927 . https://doi.org/10.1007/s12583⁃026⁃0606⁃1

Zhang, Y., Ma, C. C., Zou, M. L., et al., 2025a. Thermomechanical Failure Analysis of Sandstone Subjected to High Ground Temperature. Journal of Rock Mechanics and Geotechnical Engineering , 17 ( 6 ): 3524 - 3545 . https://doi.org/10.1016/j.jrmge.2025.04.004

Zhang, Y., Meng, K., Fan, X. M., et al., 2025b. Advancements in Laboratory Studies of Layered Rock Masses for Deep Engineering: Insights and Future Perspectives. Journal of Earth Science , 36(3): 1334-1340. https://doi.org/10.1007/s12583⁃025⁃2032⁃1

Zhang, Y., Meng, K., Zhang, Z. L., et al., 2026a. Evolution of Characteristic Stresses in Deep Hard Rocks under True Triaxial Stresses: The TT⁃CVS Identification Approach. Rock Mechanics and Rock Engineering , Online. https://doi.org/10.1007/s00603⁃026⁃05364⁃8

Zhang, Y., Qiao, J., Li, T. B., et al., 2026b. An Improved LightGBM Model with ADASYN and Whale Optimization Algorithm for Rockburst Intelligent Prediction. Rock Mechanics and Rock Engineering , Online. https://doi.org/10.1007/s00603⁃026⁃05437⁃8

Zhang, Y., Zheng, X. S., Li, S. J., et al., 2026c. Instability Mechanisms of Deep Tunnels Induced by Stiff Discontinuities: Insights from Laboratory Comparative Tests and Numerical Simulation Analysis. Tunnelling and Underground Space Technology , 172 : 107554. https://doi.org/10.1016/j.tust.2026.107554

Zhang, Y., Zhu, G. Q., Qiao, J., et al., 2026d. Dual⁃ Modality Fusion with HRNet for High⁃Accuracy Surrounding Rock Classification in TBM Tunneling: Integrating Geological and Operational Parameters. Tunnelling and Underground Space Technology , 173 : 107619. https://doi.org/10.1016/j.tust.2026.107619

Zhang, Y., Zhou, B. F., Guo, W. X., et al., 2026. Spike Waveform Recognition for Strong⁃Motion Records Based on LightGBM⁃SVM Stacking Algorithm. Earth Science , 51 ( 1 ): 185 - 198 (in Chinese with English abstract) .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

多源遥感解译与物理模型反演协同优化样本的降雨滑坡易发性评价方法

考虑滑坡类型耦合方式的滑坡易发性预测建模与不确定性分析

基于AI技术的滑坡易发性制图研究进展

基于XGBoost的现地PGV预测模型

TBM破岩关键参数跨工程转换关系