Nonlinear Prediction of Landslide Stability Based on Machine Learning
-
摘要: 滑坡稳定性含有非线性特征，机器学习算法相对于传统算法在滑坡稳定性预测中准确性更高.因此，为了更加准确地分析顺层岩质边坡在循环地震荷载作用下的稳定性，结合室内物理模型试验和离散元数值模拟软件PFC3D相互对比的研究手段，得到了滑带土的应变软化过程；并利用滑坡变形的非线性特点，和数值模拟得到的滑坡稳定性系数数据，经过模式识别、拟合检验等提出了基于机器学习算法（Box-Jenkins随机模型）的滑坡稳定性预测模型.结果表明：（1）剪切应力的逐渐减小促进了滑带土应变的软化过程，滑带土的围压虽然能抑制滑带土裂缝的增加，但对应变软化的抑制作用有限；（2）本研究所建立的标准BIC值为8.160的ARIMA（1，1，0）（0，1，1）模型，可以对边坡稳定系数时间序列数据进行精准预测.基于边坡稳定系数和应力场的现场观测，进一步描述了两种可能的滑坡触发机制，同时时间序列的机器学习能准确预测循环荷载作用下边坡稳定系数的变化规律.Abstract: The prediction and stability analysis of landslide disaster have great engineering significance and application value. Machine learning algorithm is mainly used in landslide displacement prediction, but is limited in landslide stability analysis. Therefore, in order to more accurately analyze the stability of bedding rock slope under cyclic seismic load, the strain softening process of sliding zone soil was obtained by combining the research methods of indoor physical model test and the comparison of discrete element numerical simulation software. In addition, a landslide stability prediction model based on machine learning algorithm is proposed by taking advantage of the nonlinear characteristics of landslide deformation. The results show follows: (1) The gradual reduction of shear stress promotes the strain-softening process of soil in the sliding zone. Although confining pressure of soil in the sliding zone can inhibit the increase of cracks in the sliding zone, its inhibition effect on strain softening is limited. (2) The ARIMA(1, 1, 0)(0, 1, 1) model with the standard BIC value of 8.160 was established to accurately predict the time series data of the slope stability coefficient. Based on the field observation of the slope stability coefficient and stress field, two possible landslide-triggering mechanisms are described. Mechanical learning of time series can accurately predict the variation law of slope stability coefficient under cyclic load.
-
Key words:
- machine learning /
- landslide /
- stability calculation /
- time series /
- engineering geology
-
图 2 滑带土体数值模拟的概念
a.边坡；b.室内直剪试验；c.数值模型；d.数值墙体模型
Fig. 2. Concepts of numerical simulation of soil in the sliding zone
图 3 数值模型循环加载过程示意
Fig. 3. Schematic diagram of the cyclic loading process of numerical model
图 4 室内直剪试验与数值模拟的直剪应力应变曲线对比
Fig. 4. Comparison of strain curves between direct shear test and numerical simulation
图 5 表征滑带土软化过程的配位数变化
Fig. 5. Coordination number changes characterizing the softening process of sliding zone soil
a. 50 kPa; b. 100 kPa; c. 200 kPa
图 7 不同循环荷载作用下滑带土剪切应力的演化规律
a.围压= 200 kPa；b.围压= 100 kPa；c.围压= 50 kPa
Fig. 7. Evolution of soil shear stress under different cyclic loads
图 8 不同循环荷载作用下滑带土数值模型中裂缝的变化
a.V = 0.5 cm/s，围压= 200 kPa；b.V = 0.9 cm/s，围压= 200 kPa；c.V = 1.5 cm/s，围压= 200 kPa；d.V = 2.2 cm/s，围压= 200 kPa
Fig. 8. Variation of cracks in the numerical model of soil in sliding zone under different cyclic loads
图 11 基于机器学习的边坡稳定性预测时间序列分析
Fig. 11. Time series analysis of slope stability prediction based on mechanical learning
表 1 PFC3D颗粒的校准微观参数
Table 1. Calibration microscopic parameters of PFC3D particles
滑带土的微观参数 数值 滑带土的微观参数 数值 最小颗粒半径(mm) 1 颗粒摩擦系数 1 最大颗粒半径(mm) 2 平行粘结法向、切向刚度比 1.3 颗粒密度(g/cm3) 2.36 平行粘结切向强度(GPa) 0.01 颗粒接触模量(GPa) 0.03 平行粘结拉向强度(MPa) 16.5 
下载: 导出CSV
-
Alaei, E., Mahboubi, A., 2012. A Discrete Model for Simulating Shear Strength and Deformation Behaviour of Rockfill Material, Considering the Particle Breakage Phenomenon. Granular Matter, 14(6): 707-717. doi: 10.1007/s10035-012-0367-7 Balogun, A., Rezaie, F., Pham, Q. B., et al., 2021. Spatial Prediction of Landslide Susceptibility in Western Serbia Using Hybrid Support Vector Regression (SVR) with GWO, BAT and COA Algorithms. Geoscience Frontiers, 12(3): 384-398. http://doc.paperpass.com/journal/20210065dxqy-e.html Chen, W.X., 2021. Prediction of Roadbed Deformation of Qinghai-Tibet Railway Based on Time Series Model. Science Technology and Engineering, 21(35): 15203-15208 (in Chinese with English abstract). doi: 10.3969/j.issn.1671-1815.2021.35.042 Chen, Z. R., Song, D. Q., Liu, X. L., et al., 2022. Seismic Dynamic Response Characteristics of a Layered Slope at Tunnel Entrance Using Shaking Table Test. Earth Science, 47(6): 2069-2080 (in Chinese with English abstract). Chigira, M., Yagi, H., 2006. Geological and Geomorphological Characteristics of Landslides Triggered by the 2004 Mid Niigta Prefecture Earthquake in Japan. Engineering Geology, 82: 202-221. doi: 10.1016/j.enggeo.2005.10.006 Guo, Z., Chen, L., Gui, L., et al., 2019. Landslide Displacement Prediction Based on Variational Mode Decomposition and WA-GWO-BP Model. Landslides, 17(2): 567-583. Guo, Z.Z., Tian, B.X., Li, G.G., 2022. Using and Comparing Three Data-Driven Techniques to Generate Effective Regional Landslide Susceptibility Maps in the Loess Plateau of Northwest, China. Frontiers in Earth Science, 1-23. Hofmann, H., Babadagli, T., Zimmermann, G., 2015. A Grain Based Modeling Study of Fracture Branching during Compression Tests in Granites. Intertnational Journal of Rock Mechanics and Mining Sciences, 77: 152-162. doi: 10.1016/j.ijrmms.2015.04.008 Hu, F., Li, Z.Q., Hu, R. L., et al., 2018. Research on the Deformation Characteristics of Shear Band of Soil-Rock Mixture Based on Large Scale Direct Shear Test. Chinese Journal of Rock Mechanics and Engineering, 37(3): 766-778 (in Chinese with English abstract). Huang, F. M., Chen, J. W., Tang, Z. P., et al., 2021. Uncertainties of Landslide Susceptibility Prediction due to Different Spatial Resolutions and Different Proportions of Training and Testing Datasets. Chinese Journal of Rock Mechanics and Engineering, 40(6): 1155-1169 (in Chinese with English abstract). Huang, F. M., Yin, K. L., Jiang, S. H., et al., 2018. Landslide Susceptibility Assessment Based on Clustering Analysis and Support Vector Machine. Chinese Journal of Rock Mechanics and Engineering, 37(1): 156-167 (in Chinese with English abstract). http://search.cnki.net/down/default.aspx?filename=YSLX201801016&dbcode=CJFD&year=2018&dflag=pdfdown Itasca, 2014. Version 5.0. Itasca Consulting Group Inc., Minneapolis. Jiang, S. H., Liu, Y., Zhang, H. L., et al., 2020. Quantitatively Evaluating the Effects of Prior Probability Distribution and Likelihood Function Models on Slope Reliability Assessment. Rock and Soil Mechanics, 41(9): 3087-3097 (in Chinese with English abstract). http://en.cnki.com.cn/Article_en/CJFDTotal-YTLX202009027.htm Kirschbaum, D., Stanley, T., Zhou, Y., 2015. Spatial and Temporal Analysis of a Global Landslide Catalog. Geomorphology, 249: 4-15. doi: 10.1016/j.geomorph.2015.03.016 Peethambaran, B., Anbalagan, R., Kanungo, D.P., et al., 2020. A Comparative Evaluation of Supervised Machine Learning Algorithms for Township Level Landslide Susceptibility Zonation in Parts of Indian Himalayas. Catena, 195: 104751. doi: 10.1016/j.catena.2020.104751 Pinzón-Hassan, A.D., Tique-Ortiz, V., Zafra-Mejía, C.A., 2021. Box-Jenkins Stochastic Models for Studying Air Pollutants in a Latin American Megacity. Journal of Physics: Conference Series, 2139(1): 012003. doi: 10.1088/1742-6596/2139/1/012003 Potyondy, D.O., Cundall, P.A., 2004. A Bonded-Particle Model for Rock. International Journal of Rock Mechanics and Mining Sciences, 41(8): 1329-1364. doi: 10.1016/j.ijrmms.2004.09.011 Ratshefola-Lerefolo, L., Mpeta, K.N., 2023. Analysis and Forecasting of Final Household Expenditure in South Africa Using Box-Jenkins-ARIMA Model. In: International Conference on Intelligent Computing & Optimization. Springer, Cham. Samui, P., 2008. Slope Stability Analysis: A Support Vector Machine Approach. Environmental Geology, 56: 255-261. doi: 10.1007/s00254-007-1161-4 Shan, P., Lai, X., 2019. Mesoscopic Structure PFC2D Model of Soil Rock Mixture Based on Digital Image. Journal of Visual Communication and Image Representation, 58: 407-415. doi: 10.1016/j.jvcir.2018.12.015 Sun, C., Tang, C. S., Cheng, Q., et al., 2022. Stability of Soil Slope under Soil-Atmosphere Interaction. Earth Science, 47(10): 3701-3722 (in Chinese with English abstract). Thai Pham, B., Tien Bui, D., Prakash, I., 2018. Landslide Susceptibility Modelling Using Different Advanced Decision Trees Methods. Civil Engineering and Environmental Systems, 35(1/2/3/4): 139-157. https://doi.org/10.1080/10286608.2019.1568418 Vm, A., Mh, A., Zga, B., et al., 2021. Fast Physically-Based Model for Rainfall-Induced Landslide Susceptibility Assessment at Regional Scale-Science Direct. CATENA, 201: 105213. doi: 10.1016/j.catena.2021.105213 Wang, C., Dong, J.Y., Liu, H.D., et al., 2022. Shaking Table Model Test on Dynamic Response Characteristics and Failure Mechanism of Three Sections Locked Rock Slope. Earth Science, 47(12): 4428-4441 (in Chinese with English abstract). Wang, F., Fan, X., Yunus, A.P., et al., 2019. Coseismic Landslides Triggered by the 2018 Hokkaido, Japan (Mw 6.6), Earthquake: Spatial Distribution, Controlling Factors, and Possible Failure Mechanism. Landslides, 16: 1551-1566. doi: 10.1007/s10346-019-01187-7 Xiao, T., Segoni, S., Liang, X., et al., 2022. Generating Soil Thickness Maps by Means of Geomorphological-Empirical Approach and Random Forest Algorithm in Wanzhou County, Three Gorges Reservoir. Geoscience Frontiers, 1-23. http://www.mendeley.com/catalogue/661c9a95-3dbf-3f94-b4d4-6aef8d8d2fe7/ Yang, J., Yin, Z., Laouafa, F., et al., 2020. Hydromechanical Modeling of Granular Soils Considering Internal Erosion. Canadian Geotechnical Journal, 57(2): 157-172. https://doi.org/10.1139/cgj-2018-0653 Yu, B., Pan, W. Z., Song, J., et al., 2012. Risk Zonation and Evaluation of Landslide Geohazards in Hangzhou. Rock and Soil Mechanics, 33(S1): 193-199, 216 (in Chinese with English abstract). http://202.127.156.19/ytlx/CN/article/downloadArticleFile.do?attachType=PDF&id=11390 Zhang, Y., Wong, L. N. Y., Meng, F., 2021. Brittle Fracturing in Low-Porosity Rock and Implications to Fault Nucleation. Engineering Geology, 285: 106025. doi: 10.1016/j.enggeo.2021.106025 Zhang, Z., Zhang, X., Qiu, H., et al., 2016. Micro Parameters Sensitivity of Coarse Grained Material in Mechanics and Deformation Based on PFC3D. Materials Science Forum, 873: 115-119. doi: 10.4028/www.scientific.net/MSF.873.115 Zhang, Z.F., Huang, M., Tang, Z.C., 2022. Numerical Experimental Study on Shear Mechanical Properties of Particles in Rock Discontinuities. Chinese Journal of Geotechnical Engineering, 1-10 (in Chinese with English abstract). 陈卫雄, 2021. 基于时间序列模型的青藏铁路路基变形预测. 科学技术与工程, 21(35): 15203-15208. doi: 10.3969/j.issn.1671-1815.2021.35.042 陈志荣, 宋丹青, 刘晓丽, 等, 2022. 隧道口顺层斜坡地震动力响应特征振动台试验. 地球科学, 47(6): 2069-2080. doi: 10.3799/dqkx.2021.300 胡峰, 李志清, 胡瑞林, 等, 2018. 基于大型直剪试验的土石混合体剪切带变形特征试验研究. 岩石力学与工程学报, 37(3): 766-778. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201803025.htm 黄发明, 陈佳武, 唐志鹏, 等, 2021. 不同空间分辨率和训练测试集比例下的滑坡易发性预测不确定性. 岩石力学与工程学报, 40(6): 1155-1169. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX202106008.htm 黄发明, 殷坤龙, 蒋水华, 等, 2018. 基于聚类分析和支持向量机的滑坡易发性评价. 岩石力学与工程学报, 37(1): 156-167. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201801016.htm 蒋水华, 刘源, 章浩龙, 等, 2020. 先验概率分布及似然函数模型的选择对边坡可靠度评价影响的定量评估. 岩土力学, 41(9): 3087-3097. https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX202009027.htm 孙畅, 唐朝生, 程青, 等, 2022. 土体-大气相互作用下土质边坡稳定性研究. 地球科学, 47(10): 3701-3722. doi: 10.3799/dqkx.2022.275 王闯, 董金玉, 刘汉东, 等, 2022. 三段式锁固型岩质边坡动力响应特性及破坏机制振动台模型试验研究. 地球科学, 47(12): 4428-4441. doi: 10.3799/dqkx.2022.396 俞布, 潘文卓, 宋健, 等, 2012. 杭州市滑坡地质灾害危险性区划与评价. 岩土力学, 33(S1): 193-199, 216. https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX2012S1031.htm 张志飞, 黄曼, 唐志成, 2022. 岩石不连续面内颗粒剪切力学性质的数值试验研究. 岩土工程学报, 1-10. https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC202305011.htm -
点击查看大图
图(11) / 表(1)
计量
- 文章访问数: 924
- HTML全文浏览量: 613
- PDF下载量: 75
- 被引次数: 0
