DISPLACEMENT PREDICTION OF THE ZHUJIADIAN LANDSLIDE WITH OUTLIERS
-
摘要: 滑坡位移预测预报是滑坡防灾减灾的重要组成部分，提高滑坡位移预测的准确性与精确度是该项研究的重点与难点。本文在滑坡位移预测中考虑了监测样本的离群值，通过忽略、指定与修正离群值3种方式，研究滑坡位移预测样本离群值的最优处理方式。以三峡库区朱家店滑坡为例，基于ARIMA(p，d，q)模型，分别对累积位移与位移速率时间序列开展了预测研究。研究结果表明：修正离群值的预测结果介于忽略和指定离群值两者之间，更适用于存在监测离群值的滑坡位移预测；对于ARIMA模型，更适合采用位移速率进行预测预报；使用位移速率时间序列ARIMA(1，0，1)并修正离群值的预测结果为：2016年和2017年6月份滑坡前缘GP3“阶跃”位移分别为79.0mm和70.2mm，截止2017年8月，GP3累积位移将达1647.7mm。Abstract: Landslide displacement prediction is one of important parts of landslide disaster prevention and mitigation. To improve the accuracy and precision of landslide displacement prediction is emphasis and difficulty. Outliers from monitoring samples are took into account in this research. By ignoring, reserving or correcting outliers to study on which is the best of three ways of landslide displacement prediction with outliers. The Zhujiadian Landslide in Three Gorges Reservoir Region is chosen as the case study on displacement prediction. Based on ARIMA(p, d, q) model, predictions are carried out using the accumulated displacement and the displacement rate time series, respectively. The research results show that: (1) The landslide prediction result with correcting outliers is between ignoring and reserving ones. (2)For ARIMA model, it is more suitable for using the displacement rate time series. (3)The prediction results of "step-like" displacement rates based on ARIMA(1, 0, 1) model for the displacement rate time series with correcting outliers are 79.0mm and 70.2mm in Jun. 2016 and 2017, and accumulated displacement is 1647.7mm until Aug. 2017.
-
Key words:
- Landslides /
- Displacement prediction /
- Outliers /
- ARIMA model /
- The Three Gorges Reservoir Region
-
图 4 GPS监测点位移、库水位与降雨量曲线
Figure 4. Time series of displacement, rainfall and water level
图 5 GP3监测墩倾斜变形对比图
a. 2013年GP3变形情况；b. 2015年GP3变形情况
Figure 5. GP3 pier deformation between 2013 & 2015
图 7 累积位移与位移速率的ACF/PACF系数
a.累积位移(偏)自相关性系数柱状图；b.位移速率(偏)自相关性柱状图
Figure 7. ACF/PACF coefficients of accumulated displacement and displacement rate
图 8 3种离群值处理方式下累积位移预测结果
Figure 8. Accumulated displacement prediction results by three kinds outlier handing
图 9 3种离群值处理方式下位移速率预测结果
Figure 9. Displacement rate prediction results by three kinds outlier handing
表 1 自2015/6~2016/5累积位移预测结果
Table 1. Accumulated displacement prediction results from 2015/6 to 2016/5
预测时间 2015/6 2015/7 2015/8 2015/9 2015/10 2015/11 2015/12 2016/1 2016/2 2016/3 2016/4 2016/5 位移量
/mm1171.58 1188.12 1189.36 1266.37 1259.44 1266.92 1265.31 1280.52 1283.20 1272.31 1289.51 1307.34 
下载: 导出CSV
表 2 累积位移与位移速率拟合效果和预测“阶跃”位移量
Table 2. R2 and "step-like" results of accumulated displacement and displacement rate prediction
预测目标 累积位移 位移速率 离群值处理方案 忽略 指定 修正 忽略 指定 修正 R2 0.878 0.933 0.926 0.852 0.919 0.903 2015/6 2203.0 / 1307.4 1042.7 / 146.7 2016/6 2072.2 1335.8 1482.0 225.7 17.5 79.0 2017/6 2065.2 1478.1 1627.3 205.8 15.0 70.2
下载: 导出CSV
表 3 朱家店滑坡历年“阶跃”位移量
Table 3. "Step-like" displacement over the years of the Zhujiadian landslide
类型 时间(年/月) “阶跃”位移量/mm 实测值 2007/7 26.9 2009/6 144.9 2011/6 223.9 2012/6 229.7 2013/6 94.5 2014/9 62.9 修正值 2015/6 146.7 预测值 2016/6 79.0 2017/6 70.2
下载: 导出CSV
-
Dong D M, Liang Y, Wang L Q, et al. 2017. Displacement prediction method based on ensemble empirical mode decomposition and support vector machine regression—a case of landslides in Three Gorges Reservoir area[J]. Rock and Soil Mechanics, 38(12): 366-3669. Hu X L, Zhang M, Sun M J, et al. 2015. Deformation characteristics and failure mode of the Zhujiadian landslide in the Three Gorges Reservoir, China[J]. Bulletin of Engineering Geology and the Environment, 74(1): 1-12. doi: 10.1007/s10064-013-0552-x Lei D X, Yi W. 2018. Prediction and forecast of landslide displacement based on ARIMA model: case of Wangjiapo landslide in Three Gorges Reservoir area[J]. Yangtze River, 49 (21): 56-60, 83. http://d.old.wanfangdata.com.cn/Periodical/rmcj201821011 Li C D, Tang H M, Hu X L, et al. 2009. Landslide prediction based on wavelet analysis and cusp catastrophe[J]. Journal of Earth Science, 20(6): 971. doi: 10.1007/s12583-009-0082-4 Li J, Zhang Z J, Hiu R Q, et al. 2016. Prediction of landslide displacement based on ARIMA-MC model[J]. Computer Engineering and Applications, 52(7): 215-221. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjgcyyy201607040 Li S W, Li Y C. 2015. Landslide displacement prediction based on ARIMA model[J]. Journal of Chengdu University(Natural Science Edition), 34(4): 421-424. http://d.old.wanfangdata.com.cn/Periodical/whchkjdxxb201704016 Ma J W. 2016. Rvolution characteristics of multiple physics-based parameters and data mining technology for progressive landslides[J]. Wuhan: China University of Geosciences(Wuhan). Ma J W, Tang H M, Liu X, et al. 2017. Establishment of a deformation forecasting model for a step-like landslide based on decision tree C5.0 and two-step cluster algorithms: a case study in the Three Gorges Reservoir area, China[J]. Landslides, 14(3): 1275-1281. doi: 10.1007/s10346-017-0804-0 Miao F S, Wu Y P, Xie Y H, et al. 2017. Prediction of landslide displacement with step-like behavior based on multialgorithm optimization and a support vector regression model[J]. Landslides, 15(3): 1-14. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=04ecaca2e44c7cf99ebf484dc17fa242 Miao F S, Wu Y P, Xie Y H, et al. 2016. Displacement prediction of baishuihe landslide based on multi algorithm optimization and SVR model[J]. Journal of Engineering Geology, 24(6): 1136-1144. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gcdzxb201606016 Tan F L, Hu X L, He C C, et al. 2018. Identifying the main control factors for different deformation stages of landslide[J]. Geotechnical and Geological Engineering, 36(1): 469-482. doi: 10.1007/s10706-017-0340-7 Tan F L. 2018. Evaluation method for dynamic stability of landslide stabilizing pile system with different evolution modes[J]. Wuhan: China University of Geosciences(Wuhan). Xu F, Wang Y, Du J, et al. 2011. Study of displacement prediction model of landslide based on time series analysis[J]. Chinese Journal of Rock Mechanics and Engineering, 30(4): 746-751. Yan H, Li S H, Wu L Z. 2019. Landslide displacement prediction based on multiple data-driven model methods[J]. Journal of Engineering Geology, 27(2): 459-465. http://d.old.wanfangdata.com.cn/Periodical/gcdzxb201902028 Zhao H, Shao S H, Xie D P. 2004. Examination method for qutlier of analytical data[J]. Journal of Zhoukou Teachers College, 21(5): 70-71. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zksfgdzkxxxb200405021 Zhou C, Yin K L, Cao Y, et al. 2016. Application of time series analysis and PSO-SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir, China[J]. Engineering Geology, 204 : 108-120. doi: 10.1016/j.enggeo.2016.02.009 Zhu J X, Bao Y T, Li Z. 2018. Discussion on the method for testing and treating outliers[J]. University Chemistry, 33(8): 58-65. http://d.old.wanfangdata.com.cn/Periodical/dxhx201808012 邓冬梅, 梁烨, 王亮清, 等. 2017.基于集合经验模态分解与支持向量机回归的位移预测方法:以三峡库区滑坡为例[J].岩土力学, 38(12): 3660-3669. http://d.old.wanfangdata.com.cn/Periodical/ytlx201712035 雷德鑫, 易武. 2018.基于ARIMA时间序列模型的滑坡位移预测预报——以三峡库区王家坡滑坡为例[J].人民长江, 49 (21): 60-64, 87. http://www.cnki.com.cn/Article/CJFDTotal-RIVE201821011.htm 李炯, 张志军, 牛瑞卿, 等. 2016.基于ARIMA-MC模型的滑坡位移预测[J].计算机工程与应用, 52(7): 215-221. doi: 10.3778/j.issn.1002-8331.1404-0187 李首位, 李益陈. 2015.基于ARIMA模型的滑坡位移预测[J].成都大学学报(自然科学版), 34(4): 421-424. doi: 10.3969/j.issn.1004-5422.2015.04.026 马俊伟. 2016.渐进式滑坡多场信息演化特征与数据挖掘研究[D].武汉: 中国地质大学(武汉). http://cdmd.cnki.com.cn/Article/CDMD-10491-1016312151.htm 苗发盛, 吴益平, 谢媛华, 等. 2016.基于多算法参数优化与SVR模型的白水河滑坡位移预测[J].工程地质学报, 24(6): 1136-1144. doi: 10.13544/j.cnki.jeg.2016.06.013 谭福林. 2018.基于不同演化模式的滑坡-抗滑桩体系动态稳定性评价方法研究[D].武汉: 中国地质大学(武汉). http://cdmd.cnki.com.cn/Article/CDMD-10491-1018817136.htm 王玉荣. 2004. ARIMA模型在我国出口贸易预测中的应用[J].统计与决策, (4): 33-34. doi: 10.3969/j.issn.1002-6487.2004.04.019 徐峰, 汪洋, 杜娟, 等. 2011.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, 30(4): 746-751. http://d.old.wanfangdata.com.cn/Periodical/yslxygcxb201104012 鄢好, 李绍红, 吴礼舟. 2019.联合多种数据驱动建模方法的滑坡位移预测研究[J].工程地质学报, 27(2): 459-465. doi: 10.13544/j.cnki.jeg.2017-485 赵辉, 邵素华, 谢东坡. 2004.分析数据中离群值的处理方法[J].周口师范学院学报, 21(5): 70-71. doi: 10.3969/j.issn.1671-9476.2004.05.021 中华人民共和国行业标准编写组. 2008.数据的统计处理和解释正态样本离群值的判断和处理(GB/T 4883-2008)[S].北京: 中国标准出版社. 朱嘉欣, 包雨恬, 黎朝. 2018.数据离群值的检验及处理方法讨论[J].大学化学, 33 (8): 58-65. http://d.old.wanfangdata.com.cn/Periodical/dxhx201808012 -
下载:
点击查看大图
图(10) / 表(3)
计量
- 文章访问数: 156
- HTML全文浏览量: 76
- PDF下载量: 0
- 被引次数: 0
京公网安备 11010502036328号 京ICP备17033152号