«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《地球科学与环境学报》[ISSN:1672-6561/CN:61-1423/P]

卷:

第44卷

期数:

2022年第06期

页码:

1083-1095

栏目:

纪念刘国昌先生诞辰110周年专辑

出版日期:

2022-11-15

文章信息/Info

Title:

Slope Stability Analysis Method Based on Machine Learning—Taking 618 Slopes in China as Examples

文章编号:

1672-6561(2022)06-1083-13

作者:

张梦涵; 魏 进^*; 卞海丁

(长安大学 公路学院,陕西 西安 710064)

Author(s):

ZHANG Meng-han;  WEI Jin^*;  BIAN Hai-ding

(School of Highway, Chang'an University, Xi'an 710064, Shaanxi, China)

关键词:

边坡;  稳定性;  机器学习;  随机森林;  智能评估;  特征参数;  混淆矩阵;  防护措施

Keywords:

slope;  stability;  machine learning;  random forest;  intelligent evaluation;  characteristic parameter;  confusion matrix;  protection measure

分类号:

P642.2; TU457

DOI:

10.19814/j.jese.2022.09019

文献标志码:

A

摘要:

为快速精确预测边坡稳定性状态,提出了一种基于机器学习的边坡稳定性状态智能评估方法。基于边坡失稳特征,结合国内618个边坡案例,选取了6个典型边坡参数——重度(γ)、黏聚力(C)、内摩擦角(φ)、坡角(β)、坡高(H)和孔隙水压力(P),建立了边坡稳定性评价数据集。采用机器学习理论中的梯度提升机(GBM)、支持向量机(SVM)、人工神经网络(ANN)及随机森林(RF)算法分别建立边坡稳定性预测模型,利用训练集对模型训练学习,使用五折交叉验证和网格搜索法对模型进行参数调整,并开展精度评价。基于受试者工作特征曲线下面积(AUC)和F₁分数(F₁Score)可知,随机森林算法的AUC值为0.969,F₁分数为0.904,随机森林算法的评价指标最优,更适合用于分析边坡稳定性。基于随机森林算法分别删除不同特征变量建立的不同边坡稳定性预测模型,得到特征参数敏感程度从大到小为重度、坡角、坡高、内摩擦角、孔隙水压力、黏聚力,并基于特征参数敏感程度提出了针对不同敏感因素的边坡防护措施。

Abstract:

In order to quickly and accurately predict the slope stability, an intelligent evaluation method of slope stability based on machine learning was proposed. Based on the characteristics of 618 slopes in China, 6 typical slope parameters, including gravity(γ), cohesion(C), internal friction angle(φ), slope angle(β), slope height(H)and pore water pressure(P), were selected to establish the slope stability evaluation dataset. Slope stability prediction models were established using gradient boosting machine(GBM), support vector machine(SVM), artificial neural network(ANN)and random forest(RF)in the machine learning algorithm. The models were trained and learned using the training set. The model parameters were adjusted using the 5-fold cross validation and grid-search. The ability of the model to classify the slope stability was tested through the test set, and the optimal model was determined. The results show that by comparing the area under the receiver operating characteristic curve(AUC)and F₁Score of GBM, SVM, ANN and RF algorithms, the AUC value and F₁Score of RF algorithm are 0.969 and 0.904, respectively; RF algorithm has the best evaluation index and is more suitable for analyzing slope stability. Based on the different slope stability prediction models established by deleting different characteristic variables of RF algorithm, the characteristic parameters in descending order of sensitivity are γ, β, H, φ, P, C. According to the different sensitivity factors, the slope protection measures are proposed based on the sensitivity of the characteristic parameters.

参考文献/References:

[1] 刘汉龙,马彦彬,仉文岗.大数据技术在地质灾害防治中的应用综述[J].防灾减灾工程学报,2021,41(4):710-722.
LIU Han-long,MA Yan-bin,ZHANG Wen-gang.Application of Big Data Techniques in Geological Disaster Analysis and Prevention:A Systematic Review [J].Journal of Disaster Prevention and Mitigation Engineering,2021,41(4):710-722.
[2] LAN H X,TIAN N M,LI L P,et al.Kinematic-based Landslide Risk Management for the Sichuan-Tibet Grid Interconnection Project(STGIP)in China[J].Engineering Geology,2022,308:106823.
[3] 罗元斌.边坡工程稳定性分析及处治技术研究[D].长沙:中南大学,2006.
LUO Yuan-bin.The Study on Analysing Stability and Treating Technique for Slope Engineering[D].Chang-sha:Central South University,2006.
[4] 彭 海.边坡工程处治技术分析研究及工程应用[D].长沙:中南大学,2011.
PENG Hai.Research of Analysis and Application on Slope Treatment Technical[D].Changsha:Central South University,2011.
[5] 兰恒星,彭建兵,祝艳波,等.黄河流域地质地表过程与重大灾害效应研究与展望[J].中国科学:地球科学,2022,52(2):199-221.
LAN Heng-xing,PENG Jian-bing,ZHU Yan-bo,et al.Research on Geological and Surfacial Processes and Major Disaster Effects in the Yellow River Basin[J].Science China:Earth Sciences,2022,52(2):199-221.
[6] 李红蕊.基于机器学习的边坡稳定性评价及位移预测研究[D].重庆:重庆大学,2021.
LI Hong-rui.Slope Stability Evaluation and Displacement Prediction Based on Machine Learning[D].Chongqing:Chongqing University,2021.
[7] 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 Kai,ZHANG Ke.Prediction Study on Slope Stability Based on LightGBM Algorithm[J].China Safety Science Journal,2022,32(7):113-120.
[8] 王健伟,徐玉胜,李俊鑫.基于网格搜索支持向量机的边坡稳定性系数预测[J].铁道建筑,2019,59(5):94-97.
WANG Jian-wei,XU Yu-sheng,LI Jun-xin.Prediction of Slope Stability Coefficients Based on Grid Search Support Vector Machine[J].Railway Engineering,2019,59(5):94-97.
[9] 苏国韶,宋咏春,燕柳斌.高斯过程机器学习在边坡稳定性评价中的应用[J].岩土力学,2009,30(3):675-679.
SU Guo-shao,SONG Yong-chun,YAN Liu-bin.Application of Gaussian Process Machine Learning to Slope Stability Evaluation[J].Rock and Soil Mecha-nics,2009,30(3):675-679.
[10] KAYA A,MIDILLI U M.Slope Sability Evaluation and Monitoring of A Landslide:A Case Study from NE Turkey[J].Journal of Mountain Science,2020,17(11):2624-2635.
[11] LING Q,ZHANG Q,WEI Y M,et al.Slope Reliability Evaluation Based on Multi-objective Grey Wolf Optimization-multi-kernel-based Extreme Learning Machine Agent Model[J].Bulletin of Engineering Geology and the Environment,2021,80(3):2011-2024.
[12] 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.
[13] 兰恒星,周成虎,李焯芬,等.瞬时孔隙水压力作用下的降雨滑坡稳定性响应分析:以香港天然降雨滑坡为例[J].中国科学:E辑,技术科学,2003,33(增):119-136.
LAN Heng-xing,ZHOU Cheng-hu,LI Chao-fen,et al.Rainfall-induced Landslide Stability Analysis in Response to Transient Pore Pressure:A Case Study of Natural Terrain Landslide in Hong Kong[J].Science in China:Series E,Technological Sciences,2003,33(S):119-136.
[14] HE X Z,XU H D,SABETAMAL H,et al.Machine Learning Aided Stochastic Reliability Analysis of Spatially Variable Slopes[J].Computers and Geotechnics,2020,126:103711.
[15] 仉文岗,何昱苇,王鲁琦,等.基于水系分区的滑坡易发性机器学习分析方法:以重庆市奉节县为例[J].地球科学,2022,https://kns.cnki.net/kcms/detail/42.1874.P.20220907.1841.006.html.
ZHANG Wen-gang,HE Yu-wei,WANG Lu-qi,et al.Machine Learning Solution for Landslide Susceptibility Based on Hydrographic Division:Case Study of Fengjie County in Chongqing[J].Earth Science,2022,https:∥kns.cnki.net/kcms/detail/42.1874.P.202209-07.1841.006.html.
[16] DIEU T B,TSANGARATOS P,VIET-TIEN N,et al.Comparing the Prediction Performance of a Deep Learning Neural Network Model with Conventional Machine Learning Models in Landslide Susceptibility Assessment[J].Catena,2020,188:104426.
[17] ZHAO H B,YIN S D,RU Z L.Relevance Vector Machine Applied to Slope Stability Analysis[J].International Journal for Numerical and Analytical Methods in Geomechanics,2012,36(5):643-652.
[18] LIN Y,ZHOU K P,LI J L.Prediction of Slope Stabi-lity Using Four Supervised Learning Methods[J].IEEE Access,2018,6:31169-31179.
[19] 孙吉书,夏健超,王建平,等.相关向量机模型在边坡稳定性预测中的应用[J].科学技术与工程,2021,21(28):12234-12242.
SUN Ji-shu,XIA Jian-chao,WANG Jian-ping,et al.Application of Relevance Vector Machine Model in Slope Stability Prediction[J].Science Technology and Engineering,2021,21(28):12234-12242.
[20] 马彦彬,李红蕊,王 林,等.机器学习方法在滑坡易发性评价中的应用[J].土木与环境工程学报,2022,44(1):53-67.
MA Yan-bin,LI Hong-rui,WANG Lin,et al.Machine Learning Algorithms and Techniques for Landslide Susceptibility Investigation:A Literature Review[J].Journal of Civil and Environmental Engineering,2022,44(1):53-67.
[21] FOONG L K,MOAYEDI H.Slope Stability Evaluation Using Neural Network Optimized by Equilibrium Optimization and Vortex Search Algorithm[J].Engineering with Computers,2022,38(S2):1269-1283.
[22] 黄发明,殷坤龙,蒋水华,等.基于聚类分析和支持向量机的滑坡易发性评价[J].岩石力学与工程学报,2018,37(1):156-167.
HUANG Fa-ming,YIN Kun-long,JIANG Shui-hua,et al.Landslide Susceptibility Assessment Based on Clustering Analysis and Support Vector Machine[J].Chinese Journal of Rock Mechanics and Engineering,2018,37(1):156-167.
[23] 温廷新,张 波.露天煤矿边坡稳定性的随机森林预测模型[J].科技导报,2014,32(4/5):105-109.
WEN Ting-xin,ZHANG Bo.Prediction Model for Open-pit Coal Mine Slope Stability Based on Random Forest[J].Science & Technology Review,2014,32(4/5):105-109.
[24] 石菊松.基于遥感和地理信息系统的滑坡风险评估关键技术研究[D].北京:中国地质科学院,2008.
SHI Ju-song.Key Techniques Study of Remote Sensing and Geographic Information System Based Landslide Risk Assessment[D].Beijing:Chinese Academy of Geological Sciences,2008.
[25] 李广信.岩土工程安全系数法稳定分析中的荷载与抗力[J].岩土工程学报,2021,43(5):918-925.
LI Guang-xin.Load and Resistance in Stability Analysis of Geotechnical Engineering with Safety Factor Method[J].Chinese Journal of Geotechnical Engineering,2021,43(5):918-925.
[26] 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.
[27] 赵洪波,冯夏庭.支持向量机函数拟合在边坡稳定性估计中的应用[J].岩石力学与工程学报,2003,21(2):241-245.
ZHAO Hong-bo,FENG Xia-ting.Application of Support Vector Machines Function Fitting in Slope Stability Evalution[J].Chinese Journal of Rock Mecha-nics and Engineering,2003,21(2):241-245.
[28] 邹义怀,江成玉,李春辉.人工神经网络在边坡稳定性预测中的应用[J].矿冶,2011,20(4):38-41.
ZOU Yi-huai,JIANG Cheng-yu,LI Chun-hui.Application of Artificial Neural Network in Stability Prediction of Slope[J].Mining and Metallurgy,2011,20(4):38-41.
[29] 匡 野.基于逐类组合支持向量机的边坡稳定性预测研究[J].路基工程,2013(5):73-76.
KUANG Ye.Research on Slope Stability Prediction Based on Class-by-class Combination Support Vector Machine[J].Subgrade Engineering,2013(5):73-76.
[30] 王 佳.基于支持向量机的边坡随机模糊可靠度分析[D].武汉:华中科技大学,2016.
WANG Jia.Slope Fuzzy-random Reliability Analysis Based on Support Vector Machine[D].Wuhan:Huazhong University of Science and Technology,2016.
[31] 张 研,吴哲康,王鹏鹏,等.基于PCA-RVM的露天矿边坡稳定性预测模型[J].矿业研究与开发,2021,41(3):13-18.
ZHANG Yan,WU Zhe-kang,WANG Peng-peng,et al.Prediction Model of Slope Stability of Open Pit Mine Based on PCA-RVM[J].Mining Research and Deve-lopment,2021,41(3):13-18.
[32] 孙伟超,韩 冰.基于PCA-PSO-SVM的边坡稳定性预测[J].河北地质大学学报,2018,41(1):60-64.
SUN Wei-chao,HAN Bing.Slope Stability Prediction Based on PCA-PSO-SVM[J].Journal of Hebei GEO University,2018,41(1):60-64.
[33] 张云雁.基于GS-SVM的边坡稳定性预测模型[J].水利水电技术,2020,51(11):205-209.
ZHANG Yun-yan.GS-SVM-based Prediction Model for Slope Stability[J].Water Resources and Hydropower Engineering,2020,51(11):205-209.
[34] 黄 俊,刘小生.基于GS-PSO-SVM模型的边坡稳定性预测模型[J].中国矿业,2020,29(6):87-91.
HUANG Jun,LIU Xiao-sheng.Slope Stability Prediction Model Based on GS-PSO-SVM Model[J].China Mining Magazine,2020,29(6):87-91.
[35] 王鹏飞.基于GM-RBF组合模型的高路堑边坡稳定性预测研究[J].建筑结构,2021,51(20):140-145.
WANG Peng-fei.Study on Stability Prediction of High Cutting Slope Based on GM-RBF Combination Model[J].Building Structure,2021,51(20):140-145.
[36] 史秀志,周 健,郑 纬,等.边坡稳定性预测的Bayes判别分析方法及应用[J].四川大学学报(工程科学版),2010,42(3):63-68.
SHI Xiu-zhi,ZHOU Jian,ZHENG Wei,et al.Bayes Discriminant Analysis Method and Its Application for Prediction of Slope Stability[J].Journal of Sichuan University(Engineering Science Edition),2010,42(3):63-68.
[37] 付义祥,刘世凯,刘大鹏.RBF神经网络在边坡岩体稳定性中的预测研究[J].武汉理工大学学报(交通科学与工程版),2003,27(2):170-173.
FU Yi-xiang,LIU Shi-kai,LIU Da-peng.Prediction of RBF Neural Network in Slope Rock Stability[J].Journal of Wuhan University of Technology(Tran-sportation Science & Engineering),2003,27(2):170-173.
[38] 乔 朋,梁志强,徐 凯,等.基于机器学习的中小跨径桥梁技术状况评估[J].长安大学学报(自然科学版),2021,41(6):39-52.
QIAO Peng,LIANG Zhi-qiang,XU Kai,et al.Evaluation of Technical Condition of Medium and Small Span Bridge Based on Machine Learning[J].Journal of Chang'an University(Natural Science Edition),2021,41(6):39-52.
[39] 刘 玮,王智伟,袁照旺,等.人工神经网络在商场建筑物冷负荷预测中的应用[J].长安大学学报(建筑与环境科学版),2004,21(4):58-61.
LIU Wei,WANG Zhi-wei,YUAN Zhao-wang,et al.Application of Artificial Neural Network to Predict Building's Cooling Load[J].Journal of Chang'an University(Architecture and Environment Science Edition),2004,21(4):58-61.
[40] 邵 勇,陈从新,鲁祖德,等.基于机器学习的深基坑人字形支护变形预测分析[J].岩土力学,2020,41(增2):1-9.
SHAO Yong,CHEN Cong-xin,LU Zu-de,et al.Prediction and Analysis of Deformation of Deep Foundation Pit Herringbone Retaining Support(HRS)Based on Machine Learning[J].Rock and Soil Mechanics,2020,41(S2):1-9.
[41] 李 龙,刘造保,周宏源,等.基于TBM岩机信息的隧洞断层超前智能感知加权投票模型研究[J].岩石力学与工程学报,2020,39(增2):3403-3411.
LI Long,LIU Zao-bao,ZHOU Hong-yuan,et al.Wei-ghted Voting Model for Advanced Intelligent Perception of Tunnel Faults Based on TBM Rock-machine Information[J].Chinese Journal of Rock Mechanics and Engineering,2020,39(S2):3403-3411.
[42] 黄发明,曹 昱,范宣梅,等.不同滑坡边界及其空间形状对滑坡易发性预测不确定性的影响规律[J].岩石力学与工程学报,2021,40(增2):3227-3240.
HUANG Fa-ming,CAO Yu,FAN Xuan-mei,et al.Effects of Different Landslide Boundaries and Their Spatial Shapes on the Uncertainty of Landslide Susceptibility Prediction[J].Chinese Journal of Rock Mechanics and Engineering,2021,40(S2):3227-3240.
[43] DU J,GLADE T,WOLDAI T,et al.Landslide Susceptibility Assessment Based on an Incomplete Landslide Inventory in the Jilong Valley,Tibet,Chinese Himalayas[J].Engineering Geology,2020,270:105572.
[44] 王 伟,袁雯宇,邹丽芳,等.基于滑坡敏感性评价的库区水动力型滑坡区域综合预警研究[J].岩石力学与工程学报,2022,41(3):479-491.
WANG Wei,YUAN Wen-yu,ZOU Li-fang,et al.Comprehensive Regional-scale Early Warning of Water-induced Landslides in Reservoir Areas Based on Landslide Susceptibility Assessment[J].Chinese Journal of Rock Mechanics and Engineering,2022,41(3):479-491.
[45] 张开放,苏华友,窦 勇.一种基于混淆矩阵的多分类任务准确率评估新方法[J].计算机工程与科学,2021,43(11):1910-1919.
ZHANG Kai-fang,SU Hua-you,DOU Yong.A New Multi-classification Task Accuracy Evaluation Method Based on Confusion Matrix[J].Computer Engineering & Science,2021,43(11):1910-1919.
[46] 武梦婷,陈秋松,齐冲冲.基于机器学习的边坡安全稳定性评价及防护措施[J].工程科学学报,2022,44(2):180-188.
WU Meng-ting,CHEN Qiu-song,QI Chong-chong.Slope Safety,Stability Evaluation,and Protective Measures Based on Machine Learning[J].Chinese Journal of Engineering,2022,44(2):180-188.
[47] 叶为民,孔令伟,胡瑞林,等.膨胀土滑坡与工程边坡新型防治技术与工程示范研究[J].岩土工程学报,2022,44(7):1295-1309.
YE Wei-min,KONG Ling-wei,HU Rui-lin,et al.New Prevention and Treatment Techniques and Their Applications to Landslides and Engineering Slopes of Expansive Soils[J].Chinese Journal of Geotechnical Engineering,2022,44(7):1295-1309.
[48] 徐永福,程 岩,肖 杰,等.膨胀土滑坡和工程边坡新型防治技术研究[J].岩土工程学报,2022,44(7):1281-1294.
XU Yong-fu,CHENG Yan,XIAO Jie,et al.New Prevention and Control Technology for Expansive Soil Slopes[J].Chinese Journal of Geotechnical Engineering,2022,44(7):1281-1294.
[49] 李庶林,赵睿鸣,彭府华,等.基于强度折减法的高陡边坡滑坡治理稳定性分析[J].建筑科学与工程学报,2020,37(1):120-126.
LI Shu-lin,ZHAO Rui-ming,PENG Fu-hua,et al.Stability Analysis of Treatment of High-steep Slope Landslide Based on Strength Reduction Method[J].Journal of Architecture and Civil Engineering,2020,37(1):120-126.

相似文献/References:

[1]田述军,孔纪名,陈泽富.基于公路功能的边坡灾害易损性评价[J].地球科学与环境学报,2013,35(03):119.
　TIAN Shu-jun,KONG Ji-ming,CHEN Ze-fu.Vulnerability Assessment of Slope Hazard Based on Function of Highway[J].Journal of Earth Sciences and Environment,2013,35(06):119.
[2]介玉新,柏永亮,张彬.基于加速度的边坡和挡土墙稳定性分析[J].地球科学与环境学报,2015,37(06):120.
　JIE Yu-xin,BAI Yong-liang,ZHANG Bin.Stability Analysis of Slopes and Retaining Walls Based on Acceleration[J].Journal of Earth Sciences and Environment,2015,37(06):120.
[3]李萍,张波,李同录.黄土高原边坡特征与破坏规律的分区研究[J].地球科学与环境学报,2012,34(03):89.
　LI Ping,ZHANG Bo,LI Tong-lu.Study on Regionalization for Characteristic and Destruction Rule of Slope in Loess Plateau[J].Journal of Earth Sciences and Environment,2012,34(06):89.
[4]李同录,王刘华,张常亮,等.土质边坡空间临界滑动面搜索的优化算法[J].地球科学与环境学报,2011,33(03):300.
　LI Tong-lu,WANG Liu-hua,ZHANG Chang-liang,et al.Optimistic Method for Searching the Spatial Critical Slip Surface of Earth Slopes[J].Journal of Earth Sciences and Environment,2011,33(06):300.
[5]刘悦,黄强兵.模拟堆载作用的黄土边坡土体变形机理试验[J].地球科学与环境学报,2007,29(02):183.
　LIU Yue,HUANG Qiang-bing.Test Study for Simulating Soil Deformation Mechanism of Loess Slope Under Load Condition[J].Journal of Earth Sciences and Environment,2007,29(06):183.
[6]陈文玲,赵法锁.基于模糊一致矩阵理论的边坡稳定性评价[J].地球科学与环境学报,2007,29(04):408.
　CHEN Wen-ling,ZHAO Fa-suo.Stability Evaluation of Slope in Geological Hazard Survey Based on Fuzzy Consistent Matrix Theory[J].Journal of Earth Sciences and Environment,2007,29(06):408.
[7]牛富俊,程国栋,石亚亚,等.泛北极多年冻土及重大线性工程稳定性状况[J].地球科学与环境学报,2021,43(03):587.[doi:10.19814/j.jese.2021.01034]
　NIU Fu-jun,CHENG Guo-dong,SHI Ya-ya,et al.Permafrost and Stability of the Major Linear Engineering in the Pan-Arctic Region[J].Journal of Earth Sciences and Environment,2021,43(06):587.[doi:10.19814/j.jese.2021.01034]
[8]邓通发,桂勇,罗嗣海,等.降雨条件下花岗岩残坡积土路堑边坡稳定性研究[J].地球科学与环境学报,2012,34(04):88.
　DENG Tong-fa,GUI Yong,LUO Si-hai,et al.Study on Slope Stability of Granite Residual Soil Cutting Excavation with Rainfall[J].Journal of Earth Sciences and Environment,2012,34(06):88.

备注/Memo

备注/Memo:

收稿日期:2022-09-08
基金项目:陕西省交通厅科技项目(22-24K); 西安市建设科技计划项目(SZJJ2021-10); 中央高校基本科研业务费专项资金项目(310821173701); 国家自然科学基金项目(52178310)
作者简介:张梦涵(1998-),女,河南许昌人,工学硕士研究生,E-mail:1498014549@qq.com。
*通讯作者:魏 进(1972-),男,陕西西安人,副教授,工学博士,E-mail:weijin@chd.edu.cn。

常用功能

更新日期/Last Update: 2022-11-25