| 713 | 2 | 500 |
| 下载次数 | 被引频次 | 阅读次数 |
【目的】软土滑坡因其复杂的塑性变形和流变特性，破坏机理不同于硬质岩土中的普通滑坡，传统的滑坡研究方法难以有效捕捉其运动特性非线性和不确定性特征。【方法】为量化评估软土滑坡的运动特性，采用软土的黏塑性流体假设，利用理想黏塑性材料Carbopol作为试验材料开展物理模型试验，并选取滑坡到达指定距离的厚度和速度作为代表性参数，通过随机森林算法训练试验数据构建预测模型。【结果】结果显示：厚度训练数据和测试数据的决定系数分别为0.941和0.923,速度训练数据和测试数据的决定系数分别为0.936和0.917;厚度和速度残差主要分布范围分别为(-0.02,0.02)和(-0.1,0.075),且呈正态分布。此外，自变量重要性分析显示屈服应力为对模型影响最大的输入变量，其重要程度特征值为0.35。【结论】结果表明：该模型具有较高的预测精度和良好的泛化能力，在处理软土滑坡动力学的高维度数据和复杂非线性关系方面具有较好的表现，可为软土滑坡灾害防治提供科学依据。
Abstract：[Objective]Soft soil landslides, due to their complex plastic deformation and rheological properties, have failure mechanisms distinct from ordinary landslides in hard rock and soil. Traditional method of landslide research are ineffective at capturing the nonlinear and uncertain characteristics of their movement.[Methods]To quantitatively evaluate the movement characteristics of soft soil landslides, a viscoplastic fluid assumption of soft soil was adopted, using ideal viscoplastic material Carbopol as the test material in physical model experiments. Thickness and velocity at a specified distance were chosen as representative parameters, and a prediction model was built by training the experimental data with the random forest algorithm.[Results]The results show that the determination coefficients of the thickness training and testing data were 0.941 and 0.923, respectively, while those of the velocity training and testing data were 0.936 and 0.917, respectively. The residuals for thickness and velocity were mainly distributed within the ranges of(-0.02, 0.02) and(-0.1, 0.075), respectively, and showed a normal distribution. Furthermore, an analysis of feature importance indicated that yield stress had the most significant impact on the model, with an importance value of 0.35.[Conclusion]The results demonstrate that the model has high predictive accuracy and good generalization ability, and it performs well in handling high-dimensional data and complex nonlinear relationships in the dynamics of soft soil landslides. This provides a scientific basis for the prevention and control of soft soil landslide disasters.
[1] 肖玉兰.软土地区多井降水与回灌条件下的土层沉降特征研究[J].铁道勘察，2024,50(3):83-88.XIAO Yulan.Study on subsidence characteristics under multi-well dewatering and recharging conditions in soft clay[J].Railway Investigation and Surveying,2024,50(3):83-88.
[2] LIU S,WANG R,LI D,et al.Rheological properties and landslide mechanism of soft soils under seismic conditions[J].Engineering Geology,2020,276:105754.
[3] 陈海军，王智猛，何建平，等.坡麓相煤系地层斜坡软土滑坡分析与整治研究[J].铁道工程学报，2022,39(6):43-49.CHEN Haijun,WANG Zhimeng,HE Jianping,et al.Analysis and remediation study of soft soil landslides in the slope of the foothill coal series stratum[J].Journal of Railway Engineering,2022,39(6):43-49.
[4] LI P,ZHOU C,WU S,et al.Application of machine learning in soft soil landslide prediction:A case study in southern China[J].Environmental Earth Sciences,2021,80(6):249.
[5] 刘合寨，刘合伍.某软土地区基坑滑坡事故原因分析及修复措施研究[J].广东土木与建筑，2022,29(8):20-22.LIU Hezhai,LIU Hewu.Research on the causes and treatment measures of a foundation pit landslide in soft soil area[J].Guangdong Architecture Civil Engineering,2022,29(8):20-22.
[6] ZHANG L,XU Q,HUANG R,et al.Characteristics and mechanisms of large-scale soft soil landslides in the Three Gorges Reservoir,China[J].Landslides,2014,11(5):793-804.
[7] XIE J,WANG X,LI Y,et al.Stability analysis of soft soil landslides under different hydrological conditions[J].Geotechnical and Geological Engineering,2022,40(7):3021-3035.
[8] ZHANG Z Y,JIN X G,BI J.Development of an SPH-based method to simulate the progressive failure of cohesive soil slope[J].Environmental Earth Sciences,2019,78 (17):1-15.
[9] 平扬，蒋志坚.软土堤岸滑坡机理研究[J].中国农村水利水电，2013(1):122-124.PING Yang.Research on the mechanism of soft soil embankment landslides[J].Journal of Rural Water Conservancy and Hydropower in China,2013(1):122-124.
[10] SHI C,ZHANG Y L,XU W Y,et al.Risk analysis of building damage induced by landslide impact disaster[J].European Journal of Environmental and Civil Engineering,2013,17(12):126-143.
[11] LUO H,ZHANG L,ZHANG L.Progressive failure of buildings under landslide impact[J].Landslide,2019,16(7):1327-1340.
[12] CHEN X Y,ZHANG L L,CHEN L H,et al.Slope stability analysis based on the coupled Eulerian-Lagrangian finite element method[J].Bulletin of Engineering Geology and the Environment,2019,78 (6):4451-4463.
[13] YEGANEH B,MOHAMMADZADEH A,HAMEDINIA M,et al.Hybrid machine learning models for debris flow prediction[J].Natural Hazards,2021,105:1291-1309.
[14] LEUNG A K,KAMCHOOM V,NG C W W.Influences of root-induced soil suction and root geometry on slope stability:a centrifuge study[J].Canadian Geotechnical Journal,2017,54 (3):291-304.
[15] BERTI M,SIMONI A,ROSATTI G.Debris flow modeling and prediction using machine learning methods[J].Engineering Geology,2012,147/148:58-66.
[16] ASMAE K,PEDER M,ABDOULAYE F.Quick clay and landslides of clayey soils[J].Physical Review Letters,2009,103(18):1-4.
[17] 任克彬，郑文举，刘彭彭，等.粉砂土抗剪强度黏粒含量效应[J].科学技术与工程，2021,21(17):7286-7292.REN Kebin,ZHENG Wenju,LIU Pengpeng,et al.The effect of clay content on shear strength of silty sand[J].Science Technology and Engineering,2021,21(17):7286-7292.
[18] ZHANG X,LIU L,SUN W,et al.Hybrid deep learning and physical modeling for debris flow prediction under extreme weather conditions[J].Natural Hazards,2023,118:1625-1641.
[19] 龚琰，陈浩锋.红黏土研究现状综述[J].路基工程，2019(1):47-53.GONG Yan,CHEN Haofeng.Description on research status of red clay[J].Subgrade Engineering,2019(1):47-53.
[20] 池秋慧，董金玉.不同饱和度下黏粒含量对土体强度特性的影响[J].土工基础，2020,34(2):190-193.CHI Qiuhui,DONG Jinyu.Influence of clay content on soil strength properly under different degrees of saturation[J].Soil Engineering and Foundation,2020,34(2):190-193.
[21] 刘光华，袁鸿鹄，叶思源，等.温榆河公园堆山岩土工程问题分析研究[J].水利发展研究，2024,24(11):114-118.LIU Guanghua,YUAN Honghu,YE Siyuan,et al.Analysis and research on rock-soil engineering problems related to piled mountain in Wenyuhe Park[J].Water Resources Development Research,2024,24(11):114-118.
[22] MENG Z.Experimental study on impulse waves generated by a viscoplastic material at laboratory scale[J].Landslides,2018,15(6):1173-82.
[23] MENG Z,ANCEY C.The effects of slide cohesion on impulse-wave formation[J].Experiments in Fluids,2019,60(10):1-4.
[24] ANCEY C.Plasticity and geophysical flows:A review[J].Journal of Non-Newtonian Fluid Mechanics,2007,142,4-35.
[25] MENG Z,ZHANG J,HU Y,et al.Temporal prediction of landslide-generated waves using a theoretical-statistical combined method[J].Journal of Marine Science and Engineering,2023,11(6):1151.
[26] JORDAN M I,MITCHELL T M.Machine learning:Trends,perspectives,and prospects[J].Science,2015,349(6245):255-260.
[27] MENG Z,HU Y,ANCEY C.Using a data driven approach to predict waves generated by gravity driven mass flows[J].Water,2020,12(2):600.
[28] CUTLER D R,EDWARDS T C,BEARD K H,et al.Random forests for classification in ecology[J].Ecology,2007,88(11):2783-2792.
[29] SPEISER J L,MILLER M E,TOOZE J,et al.A comparison of random forest variable selection methods for classification prediction modeling[J].Expert Systems with Applications,2019,134:93-101.
[30] PROBST P,BOULESTEIX A L.To tune or not to tune the number of trees in random forest[J].Journal of Machine Learning Research,2018,18(181):1-18.
[31] RIGATTI S J.Random forest[J].Journal of Insurance Medicine,2017,47(1):31-39.
基本信息:
DOI：10.13928/j.cnki.wrahe.2025.07.018
中图分类号:P642.22;TU447
引用信息:
[1]周书东,丁其乐,王奕仁,等.基于随机森林算法和物理模型试验的软土滑坡运动特性预测研究[J].水利水电技术(中英文),2025,56(07):239-248.DOI:10.13928/j.cnki.wrahe.2025.07.018.
基金信息:
国家自然科学基金项目(42002274); 企业委托科研项目“滨海湾新区软土地基处理技术研究”(2439001092)
2024-12-13
2024-12-13
2024-12-13