基于LS-SVM模型的白水河滑坡台阶状位移预测
|
摘要
滑坡位移是滑坡变形破坏最直观的表现,滑坡位移预测成功与否对于判别滑坡的演化趋势至关重要。滑坡位移曲线是受多种影响因素共同作用的非平稳时间序列,以三峡库区白水河滑坡为例,利用HP滤波分析方法提取滑坡位移的趋势项,趋势项位移主要是由滑坡自身特征决定的,具有较明显的非线性递增特性,采用多项式对其进行拟合预测;周期项受多种诱发因子(滑坡演化阶段、季节性降雨、库水位升降等)影响,利用最小二乘支持向量机模型(LS-SVM)对其进行训练与预测。将趋势项和周期项拟合预测结果叠加即为累计位移预测值,结果表明在监测点ZG93和XD-04的预测中,LS-SVM模型均具备较高的评价精度,在台阶状位移特征的滑坡位移预测中具有较好的适应性。
Landslide displacement is the most intuitive manifestation of landslide deformation, and the prediction of displacement plays a very important role in judging the evolution trend of landslide. Landslide displacement curve is a non-stationary time series affected by various factors. In this paper the trend displacement of Baishuihe landslide in the Three Gorges Reservoir is extracted by the HP filter method. Because of the nonlinear increasing characteristics, the trend displacement which is determined by the characteristics of the landslide is fitted and predicted by polynomial. In the meantime, induced by various factors such as evolution stages, seasonal rainfall, and water level fluctuation, the periodic displacement is trained and predicted by the model of the least squares support vector machine model(LS-SVM). The prediction result of the cumulative displacement is the superposition of the trend term and the periodic term. The results show that the LS-SVM model has high precision in the prediction of monitoring point ZG93 and XD-04, implying that LS-SVM model is of good adaptability in predicting step-like landslide.
Landslide displacement is the most intuitive manifestation of landslide deformation, and the prediction of displacement plays a very important role in judging the evolution trend of landslide. Landslide displacement curve is a non-stationary time series affected by various factors. In this paper the trend displacement of Baishuihe landslide in the Three Gorges Reservoir is extracted by the HP filter method. Because of the nonlinear increasing characteristics, the trend displacement which is determined by the characteristics of the landslide is fitted and predicted by polynomial. In the meantime, induced by various factors such as evolution stages, seasonal rainfall, and water level fluctuation, the periodic displacement is trained and predicted by the model of the least squares support vector machine model(LS-SVM). The prediction result of the cumulative displacement is the superposition of the trend term and the periodic term. The results show that the LS-SVM model has high precision in the prediction of monitoring point ZG93 and XD-04, implying that LS-SVM model is of good adaptability in predicting step-like landslide.
引文
[1] 贺可强, 阳吉宝, 王思敬. 堆积层滑坡位移动力学理论及其应用:三峡库区典型堆积层滑坡例析[M]. 北京:科学出版社,2007.
[2] 李德营,殷坤龙,李远耀,等.三峡库区堆积层滑坡预测预报模型与判据研究[M].武汉:中国地质大学(武汉)出版社,2017.
[3] 徐峰, 汪洋, 杜娟,等. 基于时间序列分析的滑坡位移预测模型研究[J]. 岩石力学与工程学报, 2011, 30(4):746-751.
[4] 李德营, 殷坤龙. 基于影响因子的GM(1,1)-BP模型在八字门滑坡变形预测中的应用[J]. 长江科学院院报, 2013, 30(2):6-11.
[5] 石爱红, 牛瑞卿. 库水位响应滞后影响下的滑坡位移预测模型研究[J]. 安全与环境工程, 2013, 20(1):26-29.
[6] 徐南, 马符讯, 贾东振. 智能优化LSSVM算法的混沌时间序列边坡变形预测模型[J]. 测绘与空间地理信息, 2015,38(2):9-11.
[7] ZHU X, XU Q, TANG M, et al. Comparison of Two Optimized Machine Learning Models for Predicting Displacement of Rainfall-induced Landslide: A Case Study in Sichuan Province, China[J]. Engineering Geology, 2017, 218: 213-222.
[8] 刘天浩. 滑坡位移序列的支持向量机预测[D].沈阳:东北大学, 2005.
[9] SUYKENS J A K, GESTEL T V, BRABANTER J D, et al. Least Squares Support Vector Machines[J]. Euphytica, 2002, 2(2):1599-1604.
[10] SUYKENS J A K. Least Squares Support Vector Machines for Classification and Nonlinear Modelling[J]. Neural Network World, 2000, 10(1):29-47.
[11] 张俊, 殷坤龙, 王佳佳,等. 基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究[J]. 岩石力学与工程学报, 2015, 34(2):382-391.
[12] 张桂荣. 基于WebGIS的滑坡灾害预测预报与风险管理[D]. 武汉:中国地质大学(武汉), 2006.
[13] KEEFER D K, WILSON R C, MARK R K, et al. Real-time Landslide Warning During Heavy Rainfall[J]. Science, 1987, 238(4829):921-925.
[14] 汪洋, 殷坤龙, 安关峰. 滑坡敏感因子的灰色关联分析[J]. 岩土力学, 2004, 25(1):91-93.
[2] 李德营,殷坤龙,李远耀,等.三峡库区堆积层滑坡预测预报模型与判据研究[M].武汉:中国地质大学(武汉)出版社,2017.
[3] 徐峰, 汪洋, 杜娟,等. 基于时间序列分析的滑坡位移预测模型研究[J]. 岩石力学与工程学报, 2011, 30(4):746-751.
[4] 李德营, 殷坤龙. 基于影响因子的GM(1,1)-BP模型在八字门滑坡变形预测中的应用[J]. 长江科学院院报, 2013, 30(2):6-11.
[5] 石爱红, 牛瑞卿. 库水位响应滞后影响下的滑坡位移预测模型研究[J]. 安全与环境工程, 2013, 20(1):26-29.
[6] 徐南, 马符讯, 贾东振. 智能优化LSSVM算法的混沌时间序列边坡变形预测模型[J]. 测绘与空间地理信息, 2015,38(2):9-11.
[7] ZHU X, XU Q, TANG M, et al. Comparison of Two Optimized Machine Learning Models for Predicting Displacement of Rainfall-induced Landslide: A Case Study in Sichuan Province, China[J]. Engineering Geology, 2017, 218: 213-222.
[8] 刘天浩. 滑坡位移序列的支持向量机预测[D].沈阳:东北大学, 2005.
[9] SUYKENS J A K, GESTEL T V, BRABANTER J D, et al. Least Squares Support Vector Machines[J]. Euphytica, 2002, 2(2):1599-1604.
[10] SUYKENS J A K. Least Squares Support Vector Machines for Classification and Nonlinear Modelling[J]. Neural Network World, 2000, 10(1):29-47.
[11] 张俊, 殷坤龙, 王佳佳,等. 基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究[J]. 岩石力学与工程学报, 2015, 34(2):382-391.
[12] 张桂荣. 基于WebGIS的滑坡灾害预测预报与风险管理[D]. 武汉:中国地质大学(武汉), 2006.
[13] KEEFER D K, WILSON R C, MARK R K, et al. Real-time Landslide Warning During Heavy Rainfall[J]. Science, 1987, 238(4829):921-925.
[14] 汪洋, 殷坤龙, 安关峰. 滑坡敏感因子的灰色关联分析[J]. 岩土力学, 2004, 25(1):91-93.