Please wait a minute...
J4  2013, Vol. 47 Issue (9): 1672-1679    DOI: 10.3785/j.issn.1008-973X.2013.09.024
地球科学     
时间序列分析与支持向量机的滑坡位移预测
彭令1,2,牛瑞卿2,吴婷3
1.中国地质环境监测院,北京100081|2.中国地质大学 地球物理与空间信息学院,湖北 武汉430074|
3.湖南农林工业勘察设计研究总院,湖南 长沙410007
Time series analysis and support vector machine for landslide displacement prediction
PENG Ling1,2, NIU Rui-qing2, WU Ting3
1. China Institute of Geo-Environment Monitoring, Beijing 100081, China|
2. Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, China|
3. Hunan Provincial Institute of Agriculture, Forestry and Industry Inventory and Planning, Changsha 410007, China
 全文: PDF  HTML
摘要:

滑坡在变形演化过程中,遭受季节性外界影响因素的作用,变形位移时间曲线呈现出阶跃型特征.采用时间序列分析方法,将位移分解为趋势项和季节项.趋势项位移由坡体自身地质条件控制,利用多项式函数进行预测|季节项位移受降雨、库水位和地下水位等因素的季节性作用而变化.选取当月降雨量、累计前2个月降雨量、当月库水位高程、月库水位变化速率和当月地下水位高程作为影响因子,利用进化支持向量机耦合模型进行预测|通过时间序列加法模型得到滑坡总位移预测值.以三峡库区白家包滑坡为例,通过计算得到预测结果与实际监测值基本吻合,其中最大均方根误差为188,而最小相关系数为098.研究表明:基于时间序列分析与进化支持向量机的滑坡位移预测模型,有效反映了阶跃型滑坡位移变化规律与季节性影响因素之间的响应关系,是一种行之有效的滑坡位移预测方法.

Abstract:

For the deformation and evolution process of landslides, the displacement curve presents the step-type deformation pattern under the influence of seasonal external factors effect.The time series analysis method was used to separate the landslide displacement into trend term  and seasonal term. Trend term displacement was controlled by the geological conditions of the slope and to be predicted using displacement polynomial function. Seasonal term displacement was affected by the seasonal functioning of influential factors, such as rainfall, reservoir level fluctuation, underground water level and so on. The rainfall of current month, cumulative rainfall of anterior two months, reservoir level fluctuation of the current month, the month rate of change of water level and underground water level of the current month were selected as influential factors. The genetic algorithm and support vector regression were adopted to predict the seasonal term displacement. Then, the prediction total displacement was obtained by the time series additive model. The Baijiabao landslide in the Three Gorges reservoir area was selected for a case study. The predicted values of the model were consistent with the measured values. The maximum value of mean squared error was only 188, and the minimum value of correlation coefficient up to 0.98. The results show that the proposed method effectively reflects the relationship between  landslides deformation and the external influential factors. It is an effective method for prediction of the step type deformation landslides.

出版日期: 2013-09-01
:  P 642.22  
基金资助:

国家“973”重点基础研究发展规划资助项目(2011CB710601); 国家”863”高技术研究发展计划资助项目(2012AA121303);国土资源部三峡库区三期地质灾害防治重大科学研究资助项目(SXKY3-6-2).

通讯作者: 牛瑞卿,男,教授.     E-mail: rqniu@163.com
作者简介: 彭 令(1984-),男,博士后,从事地质灾害监测、评估方面的研究. E-mail:wuhanpengling@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

彭令,牛瑞卿,吴婷. 时间序列分析与支持向量机的滑坡位移预测[J]. J4, 2013, 47(9): 1672-1679.

PENG Ling, NIU Rui-qing, WU Ting. Time series analysis and support vector machine for landslide displacement prediction. J4, 2013, 47(9): 1672-1679.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2013.09.024        http://www.zjujournals.com/eng/CN/Y2013/V47/I9/1672

[1] 许强,汤明高,徐开祥,等. 滑坡时空演化规律及预警预报研究[J]. 岩石力学与工程学报,2008,27(6):1104-1112.
XU Qiang,TANG Ming-gao,XU Kai-xiang,et al. Research on space-time evolution laws and early warning-prediction of landslides[J]. Chinese Journal of Rock Mechanics and Engineering,2008,27(6):1104-1112.
[2] 徐冲,刘保国,刘开云,等. 基于粒子群—高斯过程回归耦合算法的滑坡位移时序分析预测智能模型[J]. 岩土力学,2011,32(6):1669-1675.
XU Chong,LIU Bao-guo,LIU Kai-yun,et al. Intelligent analysis model of landslide displacement time series based on coupling PSO-GPR[J]. Rock and Soil Mechanics,2011,32(6):1669-1675.
[3] 郝小员,郝小红,熊红梅,等. 滑坡时间预报的非平稳时间序列方法研究[J]. 工程地质学报,1999,7(3):279-283.
HAO Xiao-yuan,HAO Xiao-hong,XIONG Hong-mei,et al. Research on landslide time forecast by the unstable time series method[J]. Journal of Engineering Geology,1999,7(3):279-283.
[4] 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):746751.
XU Feng,WANG Yang,DU Juan,et al. Study of displacement prediction model of landslide based on time series analysis[J]. Chinese Journal of Rock Mechanics and Engineering,2011,30(4):746751.
[5] 杜娟,殷坤龙,柴波. 基于诱发因素响应分析的滑坡位移预测模型研究[J]. 岩石力学与工程学报,2009,28(9):1783-1789.
DU Juan,YIN Kun-long,CHAI Bo. Study of displacement prediction model of landslide based on response analysis of inducing factors[J]. Chinese Journal of Rock Mechanics and Engineering,2009,28(9):1783-1789.
[6] 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,2003,22(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 Mechanics and Engineering,2003,22(2):241-245.
[7] 彭令,牛瑞卿,赵艳南,等. 基于核主成分分析和粒子群优化支持向量机的滑坡位移预测[J]. 武汉大学学报:信息科学版,2013,38(2):148-152.
PENG Ling,NIU Rui-qing,ZHAO Yan-nan,et al. Prediction of landslide displacement based on KPCA and PSO-SVR[J].Geomatics and Information Science of Wuhan University,2013,38(2):148152.
[8] 彭令,牛瑞卿,叶润青,等. 基于进化支持向量机的滑坡地下水位动态预测[J]. 中南大学学报:自然科学版,2012,43(12):4788-4795.
PENG Ling, NIU Rui-qing, YE Run-qing, et al. Prediction of ground water level in landslides based on genetic-support vector machine[J]. Journal of Central South University:Science and Technology,2012,43(12):4788-4795.
[9] 王建锋. 滑坡发生时间预报分析[J]. 中国地质灾害与防治学报,2003,14(2):18.
WANG Jian-feng. Quantitative prediction of landslide using S-curve[J]. The Chinese Journal of Geological Hazard and Control,2003,14(2):18.
[10] 黄波林,陈小婷. 香溪河流域白家堡滑坡变形失稳机制分析[J]. 岩土工程学报,2007,29(6):938-942.
HUANG Bo-lin,CHEN Xiao-ting. Deformation failure mechanism of Baijiabao landslide in Xiangxi River Valley[J]. Chinese Journal of Geotechnical Engineering,2007,29(6):938-942.
[11] 彭令,牛瑞卿. 三峡库区白家包滑坡变形特征与影响因素分析[J]. 中国地质灾害与防治学报,2011,22(4):1-7.
PENG Ling,NIU Rui-qing. Analysis on deformation characteristics and influential factors of Baijiabao landslide in the Three Gorges Reservoir area[J]. The Chinese Journal of Geological Hazard and Control,2011,22(4):1-7.
[12] 张军,刘祖强,邓小川,等. 滑坡监测分析预报的非线性理论和方法[M]. 北京:中国水利水电出版社,2010:41-52.
[13] GUZZETTI F,PERUCCACCI S,ROSSI M,et al. The rainfall intensity–duration control of shallow landslides and debris flows: an update[J]. Landslides,2008,5(1):3-17.
[14] 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.
[15] 年廷凯,万少石,蒋景彩,等. 库水位下降过程中土坡稳定强度折减有限元分析[J]. 岩土力学,2010,31(7):2264-2269.
NIAN Ting-kai,WAN Shao-shi,JIANG Jing-cai, et al. Finite element analysis of slope stability under drawdown conditions by strength reduction technique[J]. Rock and Soil Mechanics,2010,31(7):2264-2269.
[16] SUN Hong-yue,WONG L,SHANG Yue-quan,et al. Evaluation of drainage tunnel effectiveness in landslide control[J].Landslides,2010,7(4):445-454.
[17] VAPNIK W N. 统计学习理论的本质[M]. 张学工,译. 北京:清华大学出版社,2000:96-101.
[18] HOLLAND J H. Adaptation in natural and artificial systems[M]. Ann Arbor, MI: University of Michigan Press, 1975:228-234.

[1] 赵权利, 孙红月, 尚岳全, 王智磊. 承压水孔压的时空变化对边坡稳定性影响[J]. J4, 2013, 47(8): 1366-1372.