• 中国科技核心期刊
  • 《中国科学引用文数据库》来源期刊
  • Caj-cd规范获奖期刊
欢迎扫码关注“i环境微平台”

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于数据挖掘技术的白水河滑坡多场信息关联准则分析

陈锐 范小光 吴益平

陈锐, 范小光, 吴益平. 基于数据挖掘技术的白水河滑坡多场信息关联准则分析[J]. 中国地质灾害与防治学报. doi: 10.16031/j.cnki.issn.1003-8035.2021.0000-00
引用本文: 陈锐, 范小光, 吴益平. 基于数据挖掘技术的白水河滑坡多场信息关联准则分析[J]. 中国地质灾害与防治学报. doi: 10.16031/j.cnki.issn.1003-8035.2021.0000-00
Rui CHEN, Xiaoguang FAN, Yiping WU. Analysis on association rules of multi-field information of Baishuihe landslide based on the data mining[J]. The Chinese Journal of Geological Hazard and Control. doi: 10.16031/j.cnki.issn.1003-8035.2021.0000-00
Citation: Rui CHEN, Xiaoguang FAN, Yiping WU. Analysis on association rules of multi-field information of Baishuihe landslide based on the data mining[J]. The Chinese Journal of Geological Hazard and Control. doi: 10.16031/j.cnki.issn.1003-8035.2021.0000-00

基于数据挖掘技术的白水河滑坡多场信息关联准则分析

doi: 10.16031/j.cnki.issn.1003-8035.2021.0000-00
基金项目: 国家自然科学基金资助项目(41977244,42007267);
详细信息
    作者简介:

    陈锐(1996-),男,硕士研究生,主要从事地质灾害预测预报研究

    通讯作者:

    吴益平(1971-),女,教授,博士生导师,从事地质灾害预测预报与风险评价研究;E-mail:ypwu@cug.edu.cn

Analysis on association rules of multi-field information of Baishuihe landslide based on the data mining

  • 摘要: 为探究滑坡多场监测数据间的关联准则,采用数据挖掘技术中的两步聚类法与Apriori算法,开展滑坡多场信息关联准则研究。以三峡库区白水河滑坡为例,分析ZG93监测点于2003年6月~2016年12月期间的监测数据,选取影响滑坡变形的主要诱发因子,采用两步聚类法对不同的影响因子进行预聚类和聚类,将数值型变量转化为离散型变量后,应用Apriori算法进行处理,生成满足最小置信度的关联准则,建立白水河滑坡多场耦合作用模式下的影响因子与滑坡位移变形关联准则判据。研究表明,关联准则对于滑坡灾害的变形分析具有重要的意义,数据挖掘技术可较好地应用于三峡库区地质灾害位移预测预报中。
  • 图  1  白水河滑坡工程地质平面图

    Figure  1.  Engineering geological plan of Baishuihe Landslide

    图  2  白水河滑坡工程地质剖面图

    Figure  2.  Engineering geological section of Baishuihe Landslide

    图  3  白水河滑坡监测数据曲线

    Figure  3.  Monitoring data curve of Baishuihe landslide

    图  4  滑坡多维信息时序关联判据数据挖掘流程图

    Figure  4.  Data mining flow chart of multi-dimensional landslide information time series Association criterion

    图  5  两步聚类法示意图

    Figure  5.  Schematic diagram of two-step clustering method

    图  6  Apriori算法示意图

    Figure  6.  Schematic diagram of Apriori algorithm

    表  1  白水河滑坡月累计降雨量定性化成果

    Table  1.   Qualitative results of monthly accumulated rainfall of Baishuihe landslide

    月累计降雨量$ ({\sum q^{month}/mm})$定性化值
    (183.5,517.6)Heavy_Rainfall
    (69.9,179.8)Moderate_Rainfall
    (3.1,66.1)Light_Rainfall
    下载: 导出CSV

    表  2  白水河滑坡日降雨量月度最大值定性化成果

    Table  2.   Qualitative results of monthly maximum rainfall of Baishuihe landslide

    日降雨量月度最大值$ (q_{max}^{day}/mm)$定性化值
    (55.9,160.7)Heavy_Rain_Shower
    (26.5,55.2)Medium_Rain_Shower
    (1.3,25.6)Light_Rain_Shower
    下载: 导出CSV

    表  3  白水河滑坡库水位月度平均值定性化成果

    Table  3.   Qualitative results of monthly average water level of Baishuihe landslide reservoir

    库水位月度平均值$ (\bar{h}/m)$定性化值
    (160.14,174.74)High_Water_Level
    (144.21,158.47)Medium_Water_Level
    (135.13,138.95)Low_Water_Level
    下载: 导出CSV

    表  4  白水河滑坡月库水位波动速率定性化成果

    Table  4.   Qualitative results of water level fluctuation rate of Baishuihe landslide monthly reservoir

    月库水位波动速率$ (\Delta h/m/month)$定性化值
    (13.26,17.35)Sharply_Rise
    (7.23,11.36)Medium_Rise
    (1.57,5.89)Slowly_Rise
    (-1.56,1.31)Smooth Fluctuation
    (-7.09,-3.41)Medium_Drop
    (-13.02,-8.59)Sharply_Drop
    下载: 导出CSV

    表  5  白水河滑坡单月最大有效连续降雨量定性化成果

    Table  5.   Qualitative results of maximum effective continuous rainfall in a single month of Baishuihe landslide

    单月最大有效连续降雨量$ (q_{continuous}^{effective}/{\rm{month/mm}})$定性化值
    (110.5,239.4)High_Effective Rainfall
    (36.6,109.8)Medium_Effective Rainfall
    (1.5,36.1)Low_Effective Rainfall
    下载: 导出CSV

    表  6  白水河滑坡单月库水位日浮动最大值定性化成果

    Table  6.   Qualitative results of the maximum daily fluctuation of the water level in a single month of Baishuihe landslide

    单月库水位日浮动最大值
    ($ h_{\max}^{\rm{float}}$/day/m)
    定性化值
    (1.66,3.223)Sharply_Rise_Water
    (0.744,1.513)Medium_Rise_Water
    (0.063,0.63)Slowly_Rise_Water
    (−0.414,0)Slowly_Drop_Water
    (−1.697,−0.49)Medium_Drop_Water
    下载: 导出CSV

    表  7  白水河滑坡月位移速率定性化成果

    Table  7.   Qualitative results of monthly displacement rate of Baishuihe landslide

    月位移速率(v/mm/day)定性化值
    (1.042,10.669)
    (0.092,0.939)
    (−0.195,0.078)
    下载: 导出CSV

    表  8  白水河滑坡多场信息关联准则

    Table  8.   Multi field information association criterion of Baishuihe landslide

    规则 ID规则支持度(%)置信度
    (%)
    提升度
    1$ \stackrel{-}{\mathrm{h}} $= High_Water_Level &$ {q}_{continuous}^{effective} $ =Low_Effective Rainfall$ \Rightarrow $Ⅰ25.7785.712.02
    2$ \stackrel{-}{\mathrm{h}} $=High_Water_Leve &$ \sum {q}^{month} $=Light_Rainfall &$ {q}_{max}^{day} $=Light_Rain_Shower$ \Rightarrow $Ⅰ25.1585.372.02
    3$ \stackrel{-}{\mathrm{h}} $= High_Water_Level &$ {q}_{max}^{day} $=Light_Rain_Shower$ \Rightarrow $Ⅰ28.2286.962.05
    4 $ {q}_{continuous}^{effective} $= Low_Effective Rainfall &$ {h}_{max}^{float} $ = Slowly_Rise_Water &$ \stackrel{-}{\mathrm{h}} $= Low_Water_Level $ \Rightarrow $Ⅱ8.42100.004.13
    5$ {q}_{continuous}^{effective} $= Low_Effective Rainfall &$ \sum {\mathrm{q}}^{month} $= Moderate_Rainfall& $ \Delta \mathrm{h} $=Slowly_Rise &$ {h}_{max}^{float} $ =Slowly_Rise_Water$ \Rightarrow $Ⅱ7.56100.004.58
    6$ {q}_{continuous}^{effective}=\mathrm{ }\mathrm{M}\mathrm{e}\mathrm{d}\mathrm{i}\mathrm{u}\mathrm{m}\_\mathrm{E}\mathrm{f}\mathrm{f}\mathrm{e}\mathrm{c}\mathrm{t}\mathrm{i}\mathrm{v}\mathrm{e}\mathrm{ }\mathrm{R}\mathrm{a}\mathrm{i}\mathrm{n}\mathrm{f}\mathrm{a}\mathrm{l}\mathrm{l}\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\&\stackrel{-}{\mathrm{h}} $= Low_Water_Level &$ \Delta \mathrm{h} $=Slowly_Rise$ \Rightarrow $Ⅱ7.56100.004.58
    7$ {q}_{continuous}^{effective} $= High_Effective Rainfall & $ \stackrel{-}{\mathrm{h}} $= Medium_Water_Level$ \Rightarrow $Ⅲ6.1390.005.24
    8$ {q}_{continuous}^{effective} $= High_Effective Rainfall & $ \sum {\mathrm{q}}^{month} $= Heavy_Rainfall & $ \stackrel{-}{\mathrm{h}} $= Medium_Water_Level$ \Rightarrow $Ⅲ5.5288.895.17
    9$ {q}_{continuous}^{effective} $= High_Effective Rainfall &$ {q}_{max}^{day} $=Heavy_Rain_Shower & $ \sum {\mathrm{q}}^{month} $= Heavy_Rainfall & $ \stackrel{-}{\mathrm{h}} $= Medium_Water_Level$ \Rightarrow $Ⅲ5.5288.895.17
    10$ {q}_{max}^{day} $= Heavy_Rain_Shower & $ \sum {\mathrm{q}}^{month} $= Heavy_Rainfall & $ \stackrel{-}{\mathrm{h}} $ = Medium_Water_Level$ \Rightarrow $Ⅲ6.1380.004.66
    下载: 导出CSV
  • [1] 王树良, 王新洲, 曾旭平, 等. 滑坡监测数据挖掘视角[J]. 武汉大学学报·信息科学版,2004,29(7):608 − 610. [WANG Shuliang, WANG Xinzhou, ZENG Xuping, et al. View angle of landslide-monitoring data mining[J]. Geomatics and Information Science of Wuhan University,2004,29(7):608 − 610. (in Chinese with English abstract)
    [2] 张纯志. 滑坡监测数据处理回归模型分析及探讨[J]. 测绘与空间地理信息,2016,39(8):214 − 217. [ZHANG Chunzhi. Landslide monitoring data processing regression model analysis and discussion[J]. Geomatics & Spatial Information Technology,2016,39(8):214 − 217. (in Chinese with English abstract) doi: 10.3969/j.issn.1672-5867.2016.08.064
    [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. [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):746 − 751. (in Chinese with English abstract)
    [4] MA Junwei, TANG Huiming, LIU Xiao, et al. 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,2017,14(3):1275 − 1281. doi: 10.1007/s10346-017-0804-0
    [5] MA Junwei, TANG Huiming, HU Xinli, et al. Identification of causal factors for the Majiagou landslide using modern data mining methods[J]. Landslides,2017,14(1):311 − 322. doi: 10.1007/s10346-016-0693-7
    [6] 亓呈明, 崔守梅, 陈辉, 等. 滑坡成因决策树挖掘[J]. 中国地质灾害与防治学报,2006,17(1):73 − 76. [QI Chengming, CUI Shoumei, CHEN Hui, et al. Decision-making tree for analysis of landslide causes[J]. The Chinese Journal of Geological Hazard and Control,2006,17(1):73 − 76. (in Chinese with English abstract) doi: 10.3969/j.issn.1003-8035.2006.01.017
    [7] 何少其, 刘元雪, 梁叶, 等. “阶跃式”滑坡突变预测与核心因子提取的平衡集成树模型[J]. 中国地质灾害与防治学报,2019,30(5):27 − 36. [HE Shaoqi, LIU Yuanxue, LIANG Ye, et al. Balanced decision tree ensemble model for catastrophe prediction and key factors' extraction of step-like landslides[J]. The Chinese Journal of Geological Hazard and Control,2019,30(5):27 − 36. (in Chinese with English abstract)
    [8] 马水山, 王志旺, 张漫. 基于关联规则挖掘的滑坡监测资料分析[J]. 长江科学院院报,2004,21(5):48 − 51. [MA Shuishan, WANG Zhiwang, ZHANG Man. Analysis on monitoring data of landslide based on associative data mining[J]. Journal of Yangtze River Scientific Research Institute,2004,21(5):48 − 51. (in Chinese with English abstract) doi: 10.3969/j.issn.1001-5485.2004.05.014
    [9] 段功豪. 三峡库区堆积层滑坡预报判据的动态挖掘研究[D]. 武汉: 中国地质大学, 2013

    DUAN Gonghao. Study on prediction criteria of accumulated layer landslide in Three Gorges reservoir using dynamic data mining[D]. Wuhan: China University of Geosciences, 2013. (in Chinese with English abstract)
    [10] HUANG Haifeng, YI Wu, LU Shuqiang, et al. Use of monitoring data to interpret active landslide movements and hydrological triggers in Three Gorges reservoir[J]. Journal of Performance of Constructed Facilities,2016,30(1):C4014005. doi: 10.1061/(asce)cf.1943-5509.0000682
    [11] 孙义杰. 库岸边坡多场光纤监测技术与稳定性评价研究[D]. 南京: 南京大学, 2015

    SUN Yijie. Bank slope multi-fields monitoring based on fiber optic sensing technologies and stability evaluation study[D]. Nanjing: Nanjing University, 2015. (in Chinese with English abstract)
    [12] TSAI F, LAI J S, CHEN W W, et al. Analysis of topographic and vegetative factors with data mining for landslide verification[J]. Ecological Engineering,2013,61:669 − 677. doi: 10.1016/j.ecoleng.2013.07.070
    [13] 马俊伟. 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, 2016

    MA Junwei. Evolution characteristics of multiple physics-based parameters and data mining technology for progressive landslides[D]. Wuhan: China University of Geosciences, 2016. (in Chinese with English abstract)
    [14] SUN Guanhua, ZHENG Hong, HUANG Yaoying, et al. Parameter inversion and deformation mechanism of Sanmendong landslide in the Three Gorges Reservoir region under the combined effect of reservoir water level fluctuation and rainfall[J]. Engineering Geology,2016,205:133 − 145. doi: 10.1016/j.enggeo.2015.10.014
    [15] 李麟玮, 吴益平, 苗发盛, 等. 考虑变形状态动态切换的阶跃型滑坡位移区间预测方法[J]. 岩石力学与工程学报,2019,38(11):2272 − 2287. [LI Linwei, WU Yiping, MIAO Fasheng, et al. Displacement interval prediction method for step-like landslides considering deformation state dynamic switching[J]. Chinese Journal of Rock Mechanics and Engineering,2019,38(11):2272 − 2287. (in Chinese with English abstract)
    [16] 易庆林, 张明玉, 文凯, 等. 三峡库区白水河滑坡变形特征及影响因素的阶段分析[J]. 三峡大学学报(自然科学版),2017,39(1):38 − 42. [YI Qinglin, ZHANG Mingyu, WEN Kai, et al. Periodic analysis of deformation characteristics and influential factors of Baishuihe landslide in Three Gorges reservoir area[J]. Journal of China Three Gorges University (Natural Sciences),2017,39(1):38 − 42. (in Chinese with English abstract)
    [17] CHIU T, FANG Dongping, CHEN J, et al. A robust and scalable clustering algorithm for mixed type attributes in large database environment[C]//Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '01. August 26-29, 2001. San Francisco, California. New York: ACM Press, 2001.
    [18] AGRAWAL R, IMIELIŃSKI T, SWAMI A. Mining association rules between sets of items in large databases[C]//Proceedings of the 1993 ACM SIGMOD international conference on Management of data - SIGMOD '93. May 25-28, 1993. Washington, D. C. , USA. New York: ACM Press, 1993: 207-216.
    [19] WU Xueling, BENJAMIN ZHAN F, ZHANG Kaixiang, et al. Application of a two-step cluster analysis and the Apriori algorithm to classify the deformation states of two typical colluvial landslides in the Three Gorges, China[J]. Environmental Earth Sciences,2016,75(2):1 − 16.
    [20] LI Deying, SUN Yiqing, YIN Kunlong, et al. Displacement characteristics and prediction of Baishuihe landslide in the Three Gorges Reservoir[J]. Journal of Mountain Science,2019,16(9):2203 − 2214. doi: 10.1007/s11629-019-5470-3
  • 加载中
图(6) / 表(8)
计量
  • 文章访问数:  2
  • HTML全文浏览量:  2
  • PDF下载量:  0
  • 被引次数: 0
出版历程
  • 网络出版日期:  2021-10-22

目录

    /

    返回文章
    返回