Evaluation for Broken Line Slope Stability Based on Ensemble Learning and LEM
-
摘要: 传统边坡稳定性力学分析方法计算效率有限且往往需要借助专业软件，不利于推广.机器学习作为一种高效分析手段可应用于边坡稳定性评价.基于随机生成的大量折线型边坡样本，通过极限平衡法（LEM）求解安全系数，从而构建边坡安全系数数据库，通过集成神经网络模型建立LEM代理模型.分别采用Bagging和AdaBoost.R2两种算法构建集成神经网络，建立折线型边坡安全系数预测模型，通过实际边坡工程案例进行了验证，并与单神经网络进行了对比.通过ROC曲线分析法评价各个模型性能，确定合理的安全系数阈值.结果表明两种集成模型性能显著优于单神经网络模型，其中单神经网络模型的AUC值为0.826，AdaBoost.R2模型为0.893，Bagging模型为0.929，更能准确辨别边坡的稳定性情况.提出的方法能快速、准确地评价折线型边坡稳定性，为区域性大量边坡的稳定性快速评价提供工具.Abstract: Conventional mechanical analysis methods for slope stability have limited computational efficiency and need professional software. Machine learning, as an efficient analysis method, can be applied to slope stability evaluation. Abundant broken line slope samples are randomly generated and the corresponding factors of safety are solved by the limit equilibrium method (LEM) in this paper, so as to build a slope factor of safety database, and the LEM surrogate model is established by integrating neural network models. Two ensemble algorithms, Bagging and AdaBoost.R2, are used to establish a neural network ensemble model to predict factor of safety, which is verified by practical slope engineering cases, contrasting with single neural network model. The performances are evaluated by ROC curve analysis method, and reasonable threshold of factor of safety is determined. Results show that two ensemble models are significantly better than the single neural network model. While the AUC value of the single neural network model is 0.826, the AdaBoost. R2 model is 0.893, and the Bagging model can recognize slope stability situation better with value of 0.929. The proposed method can evaluate broken line slope stability quickly and accurately, providing a tool for rapid stability evaluation of a large number of regional slopes.
-
图 1 边坡稳定性预测模型的BP网络拓扑结构
Fig. 1. Topological structure of BP network of slope stability prediction model
图 2 Bagging集成算法示意
Fig. 2. Schematic diagram of ensemble method using Bagging algorithm
图 5 2 000个样本的安全系数分布直方图
Fig. 5. Distribution histogram of factor of safety of 2 000 samples
图 6 不同结构模型的10次10折交叉验证结果
Fig. 6. The results of 10 times 10-fold cross-validation on models with different structures
图 7 不同模型在测试集上的相对误差箱线图
Fig. 7. Box diagram of relative error of different models on the test set
图 8 边坡案例安全系数预测结果
蓝线代表最优安全系数阈值
Fig. 8. Prediction results of safety factor for slope cases
图 9 不同模型预测实际边坡稳定性的ROC曲线
Fig. 9. ROC curves of different models predicting stability of actual slopes
表 1 边坡各参数取值范围
Table 1. Value range of slope parameters
参数 坡高H1(m) 坡高H2(m) 坡角α(°) 坡角β(°) 最小值 0 0 15 15 最大值 200 200 75 75 参数 重度$ \gamma $(kN·m-3) 粘聚力c (kPa) 内摩擦角$ \phi $(°) 孔隙水压力比ru 最小值 15 0 5 0 最大值 30 150 45 0.6 
下载: 导出CSV
-
Ahour, M., Hataf, N., Azar, E., 2020. A Mathematical Model Based on Artificial Neural Networks to Predict the Stability of Rock Slopes Using the Generalized Hoek-Brown Failure Criterion. Geotechnical and Geological Engineering, 38(1): 587-604. https://doi.org/10.1007/s10706-019-01049-y Bishop, A. W., Morgenstern, N., 1960. Stability Coefficients for Earth Slopes. Géotechnique, 10(4): 129-153. https://doi.org/10.1680/geot.1960.10.4.129 Breiman, L., 1996. Bagging Predictors. Machine Learning, 24(2): 123-140. https://doi.org/10.1007/BF00058655 Cao, W., Li, W. J., Zhang, H. F., 2018. Comparative Study of Safety Factor Calculation for Slope by Finite Element Method. Highway, 63(6): 19-23 (in Chinese with English abstract). doi: 10.3969/j.issn.1671-2668.2018.06.006 Chen, C. Y., Wang, S. J., Shen, X. K., 2001. Predicting Models to Estimate Stability of Rock Slope Based on Artificial Neural Network. Chinese Journal of Geotechnical Engineering, 23(2): 157-161 (in Chinese with English abstract). doi: 10.3321/j.issn:1000-4548.2001.02.006 Chen, J. P., Wang, C. L., Wang, X. D., 2021. Coal Mine Floor Water Inrush Prediction Based on CNN Neural Network. The Chinese Journal of Geological Hazard and Control, 32(1): 50-57 (in Chinese with English abstract). Chen, L., Huang, X. Q., Shi, R. R., et al., 2009. Regionalizing Forecasting Disquisition of the Landslide in Zhejiang Province. Bulletin of Science and Technology, 25(5): 577-581 (in Chinese with English abstract). Chen, L. L., Zhang, W. G., Gao, X. C., et al., 2022. Design Charts for Reliability Assessment of Rock Bedding Slopes Stability against Bi-Planar Sliding: SRLEM and BPNN Approaches. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, 16(2): 360-375. https://doi.org/10.1080/17499518.2020.1815215 Chen, X. M., Luo, G. Y., 1999. Grey System Analysis and Evaluation of Slope Stability Based on Experience. Chinese Journal of Geotechnical Engineering, 21(5): 638-641 (in Chinese with English abstract). doi: 10.3321/j.issn:1000-4548.1999.05.026 Di Napoli, M., Carotenuto, F., Cevasco, A., et al., 2020. Machine Learning Ensemble Modelling as a Tool to Improve Landslide Susceptibility Mapping Reliability. Landslides, 17(8): 1897-1914. https://doi.org/10.1007/s10346-020-01392-9 Dou, J., Yunus, A. P., Bui, D. T., et al., 2020. Improved Landslide Assessment Using Support Vector Machine with Bagging, Boosting, and Stacking Ensemble Machine Learning Framework in a Mountainous Watershed, Japan. Landslides, 17(3): 641-658. https://doi.org/10.1007/s10346-019-01286-5 Drucker, H., 1997. Improving Regressors Using Boosting Techniques. Proceedings the Fourteenth International Conference on Machine Learning, Nashville, 97: 107-115. Jiang, Y. H., Wang, W., Zou, L. F., et al., 2022. Research on Dynamic Prediction Model of Landslide Displacement Based on Particle Swarm Optimization-Variational Mode Decomposition, Nonlinear Autoregressive Neural Network with Exogenous Inputs and Gated Recurrent Unit. Rock and Soil Mechanics, 43(S1): 601-612 (in Chinese with English abstract). Li, F., Zhang, H. Y., 2021. Stability Evaluation of Rock Slope in Hydraulic Engineering Based on Improved Support Vector Machine Algorithm. Complexity, (1): 1-13. https://doi.org/10.1155/2021/8516525 Li, W. B., Fan, X. M., Huang, F. M., et al., 2021. Uncertainties of Landslide Susceptibility Modeling under Different Environmental Factor Connections and Prediction Models. Earth Science, 46(10): 3777-3795 (in Chinese with English abstract). Li, Z. H., Zhang, C. L., Chen, B., et al., 2022. A Technical Framework of Landslide Prevention Based on Multi-Source Remote Sensing and Its Engineering Application. Earth Science, 47(6): 1901-1916 (in Chinese with English abstract). Liang, H. N., Zhang, H. Q., 2010. Identification of Slope Stability Based on the Contrast of BP Neural Network and SVM. 2010 3rd International Conference on Computer Science and Information Technology, Chengdu, 347-350. https://doi.org/10.1109/ICCSIT.2010.5564502 Lü, Q., Chan, C. L., Low, B. K., 2012. Probabilistic Evaluation of Ground-Support Interaction for Deep Rock Excavation Using Artificial Neural Network and Uniform Design. Tunnelling and Underground Space Technology, 32: 1-18. https://doi.org/10.1016/j.tust.2012.04.014 Ma, T. H., Sun, L. L., Li, W., et al., 2010. Landslide Types and Causal Factors in Zhejiang Region, China. The Chinese Journal of Geological Hazard and Control, 21(3): 17-23, 42 (in Chinese with English abstract). doi: 10.3969/j.issn.1003-8035.2010.03.004 Pham, B. T., Tien Bui, D., Prakash, I., et al., 2017. Hybrid Integration of Multilayer Perceptron Neural Networks and Machine Learning Ensembles for Landslide Susceptibility Assessment at Himalayan Area (India) Using GIS. CATENA, 149: 52-63. https://doi.org/10.1016/j.catena.2016.09.007 Pham, K., Kim, D., Le, C. V., et al., 2022. Dual Tree-Boosting Framework for Estimating Warning Levels of Rainfall-Induced Landslides. Landslides, 19(9): 2249-2262. https://doi.org/10.1007/s10346-022-01894-8 Sakellariou, M. G., Ferentinou, M. D., 2005. A Study of Slope Stability Prediction Using Neural Networks. Geotechnical & Geological Engineering, 23(4): 419-445. https://doi.org/10.1007/s10706-004-8680-5 Sun, F. Q., 2009. New Rock Burst Prediction Modeling Based on Ensemble Neural Network. Journal of Jilin University (Information Science Edition), 27(1): 79-84 (in Chinese with English abstract). doi: 10.3969/j.issn.1671-5896.2009.01.015 Wu, R. Z., Hu, X. D., Mei, H. B., et al., 2021. Spatial Susceptibility Assessment of Landslides Based on Random Forest: A Case Study from Hubei Section in the Three Gorges Reservoir Area. Earth Science, 46(1): 321-330 (in Chinese with English abstract). Zhang, F. Y., Huang, X. W., 2018. Trend and Spatiotemporal Distribution of Fatal Landslides Triggered by Non-Seismic Effects in China. Landslides, 15(8): 1663-1674. https://doi.org/10.1007/s10346-018-1007-z Zhang, T. L., Zhou, A. G., Sun, Q., et al., 2017. Characteristics of the Groundwater Seepage and Failure Mechanisms of Landslide Induced by Typhoon Rainstorm. Earth Science, 42(12): 2354-2362 (in Chinese with English abstract). Zhang, W. L., 2020. Research on Slope Stability Analysis Based on Machine Learning (Dissertation). Taiyuan University of Technology, Taiyuan (in Chinese with English abstract). Zhou, C., Yin, K. L., Cao, Y., et al., 2020. Landslide Susceptibility Assessment by Applying the Coupling Method of Radial Basis Neural Network and Adaboost: A Case Study from the Three Gorges Reservoir Area. Earth Science, 45(6): 1865-1876 (in Chinese with English abstract). Zhou, Z. H., Chen, S. F., 2002. Neural Network Ensemble. Chinese Journal of Computers, 25(1): 1-8 (in Chinese with English abstract). doi: 10.3321/j.issn:0254-4164.2002.01.001 Zhou, Z. H., Wu, J. X., Tang, W., 2002. Ensembling Neural Networks: Many could be Better Than All. Artificial Intelligence, 137(1-2): 239-263. https://doi.org/10.1016/S0004-3702(02)00190-X 曹伟, 李文静, 张红芬, 2018. 边坡安全系数的有限元计算方法对比研究. 公路, 63(6): 19-23. doi: 10.3969/j.issn.1671-2668.2018.06.006 陈昌彦, 王思敬, 沈小克, 2001. 边坡岩体稳定性的人工神经网络预测模型. 岩土工程学报, 23(2): 157-161. doi: 10.3321/j.issn:1000-4548.2001.02.006 陈建平, 王春雷, 王雪冬, 2021. 基于CNN神经网络的煤层底板突水预测. 中国地质灾害与防治学报, 32(1): 50-57. 陈列, 黄新晴, 石蓉蓉, 等, 2009. 浙江省滑坡分区预报研究. 科技通报, 25(5): 577-581. 陈新民, 罗国煜, 1999. 基于经验的边坡稳定性灰色系统分析与评价. 岩土工程学报, 21(5): 638-641. doi: 10.3321/j.issn:1000-4548.1999.05.026 姜宇航, 王伟, 邹丽芳, 等, 2022. 基于粒子群‒变分模态分解、非线性自回归神经网络与门控循环单元的滑坡位移动态预测模型研究. 岩土力学, 43(S1): 601-612. 李文彬, 范宣梅, 黄发明, 等, 2021. 不同环境因子联接和预测模型的滑坡易发性建模不确定性. 地球科学, 46(10): 3777-3795. doi: 10.3799/dqkx.2021.042 李振洪, 张成龙, 陈博, 等, 2022. 一种基于多源遥感的滑坡防灾技术框架及其工程应用. 地球科学, 47(6): 1901-1916. doi: 10.3799/dqkx.2022.205 麻土华, 孙乐玲, 李炜, 等, 2010. 浙江滑坡类型、成因和环境控制因素与影响因素. 中国地质灾害与防治学报, 21(3): 17-23, 42. 孙凤琪, 2009. AdaBoost集成神经网络在冲击地压预报中的应用. 吉林大学学报(信息科学版), 27(1): 79-84. 吴润泽, 胡旭东, 梅红波, 等, 2021. 基于随机森林的滑坡空间易发性评价: 以三峡库区湖北段为例. 地球科学, 46(1): 321-330. doi: 10.3799/dqkx.2020.032 张泰丽, 周爱国, 孙强, 等, 2017. 台风暴雨条件下滑坡地下水渗流特征及成因机制. 地球科学, 42(12): 2354-2362. doi: 10.3799/dqkx.2017.570 张伟龙, 2020. 基于机器学习的边坡稳定性分析研究(硕士学位论文). 太原: 太原理工大学. 周超, 殷坤龙, 曹颖, 等, 2020. 基于集成学习与径向基神经网络耦合模型的三峡库区滑坡易发性评价. 地球科学, 45(6): 1865-1876. doi: 10.3799/dqkx.2020.071 周志华, 陈世福, 2002. 神经网络集成. 计算机学报, 25(1): 1-8. -
点击查看大图
图(9) / 表(1)
计量
- 文章访问数: 441
- HTML全文浏览量: 101
- PDF下载量: 36
- 被引次数: 0
