1.安徽建筑大学土木工程学院,安徽 合肥 230601
2.安徽省岩土工程智能建造与灾变防控重点实验室,安徽 合肥 230601
张仕杰(2002—),男,硕士研究生。主要从事边坡工程灾害预警与防治研究。E-mail: zsj020131@163.com
张宁(1985—),男,教授,博导,博士。主要从事岩土工程地震研究。E-mail: ningzhanghhu@163.com
收稿:2025-04-01,
修回:2025-05-15,
纸质出版:2025-10-28
移动端阅览
张仕杰,张煜,张宁.基于PSO‑LightGBM模型的边坡稳定性预测研究[J].防灾减灾工程学报,2025,45(05):1233-1240.
ZHANG Shijie,ZHANG Yu,ZHANG Ning.Research on Slope Stability Prediction Based on PSO‑LightGBM Model[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(05):1233-1240.
张仕杰,张煜,张宁.基于PSO‑LightGBM模型的边坡稳定性预测研究[J].防灾减灾工程学报,2025,45(05):1233-1240. DOI: 10.13409/j.cnki.jdpme.20250401001.
ZHANG Shijie,ZHANG Yu,ZHANG Ning.Research on Slope Stability Prediction Based on PSO‑LightGBM Model[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(05):1233-1240. DOI: 10.13409/j.cnki.jdpme.20250401001.
边坡稳定性的准确预测对降低边坡失稳风险具有重要意义。为高效且准确地预测边坡稳定性,提出了一种基于粒子群(PSO)优化轻量级梯度提升机(LightGBM)的边坡稳定性预测模型,即PSO‑LightGBM模型。该模型首先采用粒子群算法优化LightGBM模型中的重要参数,在实际工程应用中,降低了LightGBM模型参数所产生的影响。然后采用优化后的LightGBM模型对边坡稳定性进行分类预测。选取K近邻(KNN)、支持向量机(SVM)、LightGBM、网格搜索优化LightGBM(GS‑LightGBM)以及遗传优化LightGBM(GA‑LightGBM)作为对比模型,并采用准确率、精确率、召回率与F1 分数作为各模型预测性能的评价指标,并通过混淆矩阵可视化各模型的分类结果。基于PSO‑LightGBM模型的特征重要性分析,量化了各因素在边坡稳定性预测中的相对重要性。研究结果表明,在测试集上PSO‑LightGBM模型的各项评价指标上均显著优于其他对比模型,表现出较强的分类预测性能与泛化能力。通过特征重要性分析,影响边坡稳定性的因素从大到小依次为:坡角、坡高、内聚力、内摩擦角、土体重度与孔隙水压力。本研究为边坡稳定性的准确预测提供了一种新方法,对边坡工程安全设计与风险评估具有重要参考意义。
The accurate prediction of slope stability is of great significance for reducing the risk of slope instability. To achieve efficient and accurate slope stability prediction
this study proposed a slope stability prediction model based on particle swarm optimization (PSO) for light gradient boosting machine (LightGBM)
namely the PSO-LightGBM model. This model first used the PSO algorithm to optimize key parameters of the LightGBM model
reducing the impact of parameters of the LightGBM model in practical engineering applications. Then
the optimized LightGBM model was adopted to classify and predict the slope stability. K-nearest neighbor (KNN)
support vector machine (SVM)
LightGBM
grid search-optimized LightGBM (GS-LightGBM)
and genetic algorithm-optimized LightGBM (GA-LightGBM) were selected as comparison models. Accuracy
precision
recall
and F1 score were used as evaluation indicators for the predictive performance of each model
and the classification results of each model were visualized through the confusion matrices. Based on the feature importance analysis of the PSO-LightGBM model
the relative importance of each factor in slope stability prediction was quantified. The results showed that the PSO-LightGBM model significantly outperformed all other comparison models across all evaluation indicators on the test set
demonstrating strong classification prediction performance and generalization ability. Through feature importance analysis
the factors affecting slope stability were ranked in descending order as follows: slope angle
slope height
cohesion
internal friction angle
soil unit weight
and pore water pressure. This study provides a new method for the accurate prediction of slope stability and offers an important reference for the safety design and risk assessment of slope engineering.
Suman S , Khan S Z , Das S K , et al . Slope stability analysis using artificial intelligence techniques [J]. Natural Hazards , 2016 , 84 ( 2 ): 727 - 748 .
章瑞环 , 叶帅华 , 陶晖 . 基于改进极限平衡法的多级均质黄土边坡稳定性分析 [J]. 岩土力学 , 2021 , 42 ( 3 ): 813 - 825 .
Zhang R H , Ye S H , Tao H . Stability analysis of multistage homogeneous loess slopes by improved limit equilibrium method [J]. Rock and Soil Mechanics , 2021 , 42 ( 3 ): 813 - 825 . (in Chinese)
Liu S Y , Shao L T , Li H J . Slope stability analysis using the limit equilibrium method and two finite element methods [J]. Computers and Geotechnics , 2015 , 63 : 291 - 298 .
曹兰柱 , 王珍 , 王东 , 等 . 软弱基底排土场堆载过程中稳定性数值模拟 [J]. 防灾减灾工程学报 , 2017 , 37 ( 5 ): 776 - 781 .
Cao L Z , Wang Z , Wang D , et al . Numerical simulation of stability in loading dump with weak basement [J]. Journal of Disaster Prevention and Mitigation Engineering , 2017 , 37 ( 5 ): 776 - 781 . (in Chinese)
Ding Q L , Peng Y Y , Cheng Z , et al . Numerical simulation of slope stability during underground excavation using the lagrange element strength reduction method [J]. Minerals , 2022 , 12 ( 8 ): 1054 .
Pei T , Qiu T , Shen C P . Applying knowledge-guided machine learning to slope stability prediction [J]. Journal of Geotechnical and Geoenvironmental Engineering , 2023 , 149 ( 10 ): 04023089 .
Zhang Y , Dai M L , Ju Z M . Preliminary discussion regarding SVM kernel function selection in the twofold rock slope prediction model [J]. Journal of Computing in Civil Engineering , 2016 , 30 ( 3 ): 04015031 .
胡军 , 董建华 , 王凯凯 , 等 . 边坡稳定性的CPSO-BP模型研究 [J]. 岩土力学 , 2016 , 37 ( 增1 ): 577 - 582, 590 .
Hu J , Dong J H , Wang K K , et al . Research on CPSO-BP model of slope stability [J]. Rock and Soil Mechanics , 2016 , 37 ( Sup1 ): 577 - 582, 590 . (in Chinese)
Huang S , Huang M M , Lyu Y J . An improved KNN-based slope stability prediction model [J]. Advances in Civil Engineering , 2020 , 2020 ( 1 ): 8894109 .
马文涛 . 基于PSO和LSSVM的边坡稳定性评价方法 [J]. 岩土力学 , 2009 , 30 ( 3 ): 845 - 848 .
Ma W T . Evaluation of rock slope stability based on PSO and LSSVM [J]. Rock and Soil Mechanics , 2009 , 30 ( 3 ): 845 - 848 . (in Chinese)
Cai Y , Yuan Y , Zhou A H . Predictive slope stability early warning model based on CatBoost [J]. Scientific Reports , 2024 , 14 : 25727 .
Yuan H P , Ji S J , Li H Z , et al . Classification forecasting research of rock burst intensity based on the BO-XGBoost-Cloud model [J]. Earth Science Informatics , 2024 , 18 ( 1 ): 95 .
Xu W H , Kang Y F , Chen L C , et al . Dynamic assessment of slope stability based on multi-source monitoring data and ensemble learning approaches: A case study of Jiuxianping landslide [J]. Geological Journal , 2023 , 58 ( 6 ): 2353 - 2371 .
Qiu Y G , Zhou J , He B , et al . Evaluation and interpretation of blasting-induced tunnel overbreak: Using heuristic-based ensemble learning and gene expression programming techniques [J]. Rock Mechanics and Rock Engineering , 2024 , 57 ( 9 ): 7535 - 7563 .
张凯 , 张科 . 基于LightGBM算法的边坡稳定性预测研究 [J]. 中国安全科学学报 , 2022 , 32 ( 7 ): 113 - 120 .
Zhang K , Zhang K . Research on slope stability prediction based on LightGBM algorithm [J]. China Safety Science Journal , 2022 , 32 ( 7 ): 113 - 120 . (in Chinese)
白龙发 , 李保珠 , 时鹏程 . 基于EO-LightGBM融合模型的边坡稳定性预测方法研究 [J]. 地质灾害与环境保护 , 2024 , 35 ( 4 ): 105 - 111 .
Bai L F , Li B Z , Shi P C . Study on slope stability prediction method based on eo-lightgbm fusion model [J]. Journal of Geological Hazards and Environment Preservation , 2024 , 35 ( 4 ): 105 - 111 . (in Chinese)
Kennedy J , Eberhart R . Particle swarm optimization [C]∥ Proceedings of ICNN'95-International Conference on Neural Networks . Perth, WA, Australia . New York : IEEE Press , 2002 : 1942 - 1948 .
Zhu J J , Li B T , Wang Z L . A poverty index prediction model for students based on PSO-LightGBM [J]. Annals of Operations Research , 2025 , 348 ( 1 ): 717 - 734 .
Luo H , Liu J , He D . GNSS signal labeling, classification, and positioning in urban scenes based on PSO-LGBM-WLS algorithm [J]. IEEE Transactions on Instrumentation and Measurement , 2023 , 72 : 2528213 .
胡少伟 , 李原昊 , 单常喜 , 等 . 基于改进的PSO-BP神经网络的边坡稳定性研究 [J]. 防灾减灾工程学报 , 2023 , 43 ( 4 ): 854 - 861 .
Hu S W , Li Y H , Shan C X , et al . Research on slope stability based on improved PSO-BP neural network [J]. Journal of Disaster Prevention and Mitigation Engineering , 2023 , 43 ( 4 ): 854 - 861 . (in Chinese)
董学超 , 郭明伟 , 王水林 . 基于LightGBM的超大沉井下沉状态预测及传感器优化布置 [J]. 岩土力学 , 2023 , 44 ( 6 ): 1789 - 1799 .
Dong X C , Guo M W , Wang S L . Sinking state prediction and optimal sensor placement of super large open caissons based on LightGBM [J]. Rock and Soil Mechanics , 2023 , 44 ( 6 ): 1789 - 1799 . (in Chinese)
Zhou J , Li E M , Yang S , et al . Slope stability prediction for circular mode failure using gradient boosting machine approach based on an updated database of case histories [J]. Safety Science , 2019 , 118 : 505 - 518 .
刘顺青 , 洪宝宁 , 徐奋强 , 等 . 高液限土边坡稳定性影响因素的敏感性研究 [J]. 防灾减灾工程学报 , 2014 , 34 ( 5 ): 589 - 596 .
Liu S Q , Hong B N , Xu F Q , et al . Sensitivity studies on factors influencing stability of high liquid limit soil slope [J]. Journal of Disaster Prevention and Mitigation Engineering , 2014 , 34 ( 5 ): 589 - 596 . (in Chinese)
Choo H , Min D H , Sung J H , et al . Sensitivities of input parameters for predicting stability of soil slope [J]. Bulletin of Engineering Geology and the Environment , 2019 , 78 ( 8 ): 5671 - 5685 .
Lu P , Rosenbaum M S . Artificial neural networks and grey systems for the prediction of slope stability [J]. Natural Hazards , 2003 , 30 ( 3 ): 383 - 398 .
Das S K , Biswal R K , Sivakugan N , et al . Classification of slopes and prediction of factor of safety using differential evolution neural networks [J]. Environmental Earth Sciences , 2011 , 64 ( 1 ): 201 - 210 .
Lin H J , Li L , Qiang Y , et al . Sensitivity analysis of slope stability based on eXtreme gradient boosting and SHapley Additive exPlanations: An exploratory study [J]. Heliyon , 2024 , 10 ( 16 ): e35871 .
Sah N K , Sheorey P R , Upadhyaya L N . Maximum likelihood estimation of slope stability [J]. International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts , 1994 , 31 ( 1 ): 47 - 53 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
苏公网安备32010202012147号
