作者：朱鸿鹄1,2，王佳1，李厚芝3，叶霄1，施斌1，张勤4
1南京大学地球科学与工程学院 南京 210023
2南京大学（苏州）高新技术研究院 苏州 215023
3中国地质调查局探矿工艺研究所，成都 611734
4长安大学地质工程与测绘学院，西安 710054
摘 要：从实测数据中分析滑坡灾害的成因机理，对于准确识别潜在危险区与及时制定防治措施十分重要。由于现场监测数据的数量庞大、来源多样，常规的数据处理方法难以从海量监测数据中提取出有用的信息，进而对滑坡变形演化趋势作出正确评价和预测。本文基于经典数据挖掘方法中的两步聚类法与关联规则分析，提出了滑坡变形行为的关联分析挖掘技术，并以长江三峡库区新铺滑坡为例，对库水位波动及降雨影响下的特大滑坡位移速率进行了关联分析。结果表明：该滑坡的变形受库水位高程水平、库水位波动速率与降雨强度等因素的多重影响，水位下降、强降雨与滑坡变形密切相关；滑坡不同空间位置处的变形影响因素存在差异，由坡脚至坡顶，库水位波动的影响水平依次降低，降雨强度的影响水平逐渐增强。本文提出的数据挖掘方法可定量分析滑坡变形的控制因素，并通过与实测数据的对比验证了相关规则的可靠性，这对于海量监测数据条件下滑坡灾害的成因分析有重要意义。
关键词：关联规则；滑坡变形；数据挖掘；库区滑坡
基金项目：国家自然科学基金（资助号：42225702，42077235），国家重点研发计划课题（资助号：2018YFC1505104）．
第一（通讯）作者简介：朱鸿鹄（1979-），男，博士，教授，博士生导师，主要从事岩土界面监测与评价方面的研究工作.
ASSOCIATION RULE ANALYSIS FOR GIANT LANDSLIDE DEFORMATION OF THE THREE GORGES RESERVOIR REGION BASED ON DATA MINING
ZHU Honghu①②，WANG Jia①，LI Houzhi，YE Xiao①，SHI Bin①，ZHANG Qin
（① School of Earth Sciences and Engineering, Nanjing University, Nanjing, Jiangsu 210023, China；
（② Nanjing University High-Tech Institute at Suzhou, Suzhou, Jiangsu 215123, China；
（③ Institute of Exploration Technology, China Geological Survey, Chengdu 611734, China；
（④ College of Geological Engineering and Geomatics，Chang’an University, Xi’an 710054，China）
Abstract：Understanding the causes of landslides from real-time monitoring data is important for identifying triggering mechanisms and potential hazard areas and formulating mitigation measures in a timely manner. However, due to the large amount and diverse sources of monitoring data, the conventional data processing methods can hardly extract useful information from huge monitoring data so as to make a correct evaluation of landslide deformation behaviors and evolution trends. This paper introduces the two-step clustering and association rule analysis methods in the classical data mining methods, proposes the data mining process of association analysis of slope deformation behavior, and takes the Xinpu landslide in the Three Gorges reservoir region of Yangtze River as an example, and carries out the association analysis of slope displacement rate under the influence of reservoir water level and rainfall. The results show that the landslide deformation in the reservoir area is influenced by multiple factors such as reservoir water level elevation level, reservoir water level fluctuation rate and rainfall intensity, etc., and water level decline and strong rainfall are closely related to landslide deformation; there are differences in deformation influencing factors at different spatial locations of the landslide, the influence level of reservoir water level fluctuation decreases and the influence level of rainfall intensity increases from front part to rear part; the data mining method can be used to analyze the influencing factors of landslide deformation The data mining method can be used to analyze the influencing factors of landslide deformation, and the comparison with the measured data verifies the reliability of the rules, which is important for the analysis of the causes of landslide disasters under the massive monitoring data.
Key words: association rule; slope deformation; data mining; reservoir landslide
参 考 文 献
Chen M S, Han J W, Yu P S. Data mining: an overview from a database perspective [J]. 1996. IEEE Transactions on Knowledge and Data Engineering, 8(6): 866-883.
Chen R, Fan X G, Wu Y P. 2021. 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, 32(6): 1-8.
Dong W W, Zhu H H, Sun Y J, et al. 2016. Current status and new progress on slope deformation monitoring technologies[J]. Journal of Engineering Geology, 24(6): 1088-1095.
Franceschini R, Rosi A, Catani F, et al. 2022. Exploring a landslide inventory created by automated web data mining: the case of Italy[J]. Landslides, 19: 841-853.
Huang G W, Wang J X, Du Y, et al. 2021. Time-delay analysis and prediction of landslide considering precipitation and reservoir water level[J]. Journal of Earth Science and Environment, 43(3): 621-631.
Jiang H W, Li Y Y, Zhou C, et al. 2020. Landslide displacement prediction combining LSTM and SVR algorithms: A case study of Shengjibao Landslide from the Three Gorges Reservoir Area[J]. Applied Sciences, 10(21): 7830.
Jie Q, Shi B, Luo W Q, et al. 2015. Analysis of DFOS based association rules on multi-fields data monitoring of slope[J]. Journal of Engineering Geology, 23(6): 1146-1152.
Lee S M, Lee M J, Jung H S. 2017. Data mining approaches for landslide susceptibility mapping in Umyeonsan, Seoul, South Korea[J]. Applied Sciences, 7(7): 683.
Li C D, Long J J, Jiang Q H, et al. 2020. Advance and progress of formation mechanism for reservoir landslide[J]. Bulletin of Geological Science and Technology, 39(1): 67-77.
Luo S L, Huang D. 2020. Deformation characteristics and reactivation mechanisms of the Outang ancient landslide in the Three Gorges Reservoir, China[J]. Bulletin of Engineering Geology and the Environment, 79: 3943–3958.
Ma J W. 2016. Evolution on characteristics of multiple physics-based parameters and data mining technology for progressive landslides[D]. China University of Geosciences (Wuhan).
Ma J W, Tang H M, Hu X L, et al. 2017. Identification of causal factors for the Majiagou landslide using modern data mining methods[J]. Landslides, 14: 311-322.
Ma J W, Tang H M, Zou Z X, et al. 2019. Intelligent Algorithm and Application Example of Landslide Displacement Prediction[M]. Wuhan: China University of Geosciences Press.
Ma S S, Wang Z W, Zhang M. 2002. Factor analysis on monitoring data of landslide[J]. Chinese Journal of Rock Mechanics and Engineering, 21(7): 1003-1006.
National Meteorological Center. 2012. Grade of precipitation(GB/T 28592-2012)[S]. Beijing, Standards Press of China.
Ouyang Y, Luo S M, Cui L H, et al. 2011. Estimation of real-time N load in surface water using dynamic data-driven application system[J]. Ecological Engineering, 37(4): 616-621.
Shang M, Liao F, Ma R, et al. 2021. Quantitative correlation analysis on deformation of Baijiabao landslide between rainfall and reservoir water level[J]. Journal of Engineering Geology, 29(3): 742-750.
Tan M J, Yin K L, Fu Z Y, et al. 2022. Analysis on groundwater response characteristics of Madiwan landslide under the influence of rainfall and reservoir water[J]. The Chinese Journal of Geological Hazard and Control, 33(1): 45-57.
Tang H M, Wasowski J, Juang C H. 2019. Geohazards in the three Gorges Reservoir Area, China – Lessons learned from decades of research[J]. Engineering Geology, 261: 105267.
Tsironi V, Ganas A, Karamitros I, et al. 2022. Kinematics of Active Landslides in Achaia (Peloponnese, Greece) through InSAR Time Series Analysis and Relation to Rainfall Patterns. Remote Sensing. 14(4):844.
Xu Q, Dong X J, Li W L. 2019. Integrated Space-Air-Ground Early Detection, Monitoring and Warning System for Potential Catastrophic Geohazards[J]. Geomatics and Information Science of Wuhan University, 44(7): 957-996.
Xu Q. 2020. Understanding the landslide monitoring and early warning：Consideration to practical issues[J]. Journal of Engineering Geology，28(2)：360-374.
Xue X. 2021. Study on hysteresis effect of reservoir colluvial landslide’s deformation-Taking a case of Baijiabao landslide[D]. China Three Gorges University.
Xue W, Chen H G. 2010. Clementine data mining method and application[M]. Electronic Industry Press.
Yang Z P, Li X Y, Zhao Q, et al. 2021. Key influencing factors based distribution regularity and deformation and failure response of colluvial landslides in Three Gorges Reservoir area[J]. Journal of Engineering Geology，29(3)：617-627.
Ye R Q, Fu X L, Guo F, et al. 2021. Deformation characteristics and mechanism analysis of geological hazards during operation period of Three Gorges Reservoir[J]. Journal of Engineering Geology，29(3)：680-692.
Ye X, Zhu H H, Wang J, et al. 2022. Subsurface multi-physical monitoring of a reservoir landslide with the fiber-optic nerve system[J]. Geophysical Research Letters, 49(11): e2022GL098211.
Yin Y P, Wu S R, Men Y M, et al. 2012. Study on landslide monitoring, early warning and emergency prevention technology[M]. Beijing: Science Press.
Yin Y P, Huang B L, Wang W P, et al. 2016. Reservoir-induced landslides and risk control in Three Gorges Project on Yangtze River, China[J]. Journal of Rock Mechanics and Geotechnical Engineering, 8(5): 577-595.
Zhang L, Shi B, Zhu H H, et al. 2021. PSO-SVM-based deep displacement prediction of Majiagou landslide considering the deformation hysteresis effect[J]. Landslides, 18: 179-193.
Zhang W, Xiao R, Shi B, et al. 2019. Forecasting slope deformation field using correlated grey model updated with time correction factor and background value optimization[J]. Engineering Geology, 260: 105215.
Zhu H H, Shi B, Yan J F, et al. 2014. Fiber Bragg grating-based performance monitoring of a slope model subjected to seepage. Smart Materials and Structures, 23: 095027.
Zhu S N, Yin Y P, Huang B L, et al. 2021. Deformation characteristics and instability mechanism of large monoclinal layered neogenic bedrock landslide in Three Gorges Reservoir area[J]. Journal of Engineering Geology，29(3)：657-667.
陈锐, 范小光, 吴益平. 2021. 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, 32(6): 1-8.
董文文, 朱鸿鹄, 孙义杰, 等. 2016. 边坡变形监测技术现状及新进展[J]. 工程地质学报, 24(6): 1088-1095.
国家气象中心. 2012. 降水量等级（GB/T 28592-2012）[S]. 北京：中国标准出版社.
黄观文, 王家兴, 杜源, 等. 2021. 顾及降雨及库水位因素的滑坡时滞分析与预测——以三峡库区新铺滑坡为例[J].地球科学与环境学报, 43(3): 621-631.
揭奇, 施斌, 罗文强, 等. 2015. 基于DFOS的边坡多场信息关联规则分析[J]. 工程地质学报, 23(6):1146-1152.
李长冬, 龙晶晶, 姜茜慧, 等. 2020. 水库滑坡成因机制研究进展与展望[J]. 地质科技通报, 39(1): 71-81.
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].中国地质大学.
马俊伟，唐辉明，邹宗兴, 等. 2019. 滑坡位移预测的智能算法与应用实例[M]. 武汉：中国地质大学出版社.
马水山, 王志旺, 张漫. 2002. 滑坡监测资料的因子分析[J]. 岩石力学与工程学报, 21(7): 1003-1006.
尚敏, 廖芬, 马锐, 等. 2021. 白家包滑坡变形与库水位、降雨相关性定量化分析研究[J]. 工程地质学报, 29(3): 742-750.
檀梦皎, 殷坤龙, 付智勇, 等. 2022. 降雨及库水位影响下麻地湾滑坡地下水响应特征分析[J]. 中国地质灾害与防治学报, 33(1): 45-57.
许强, 董秀军, 李为乐. 2019. 基于天-空-地一体化的重大地质灾害隐患早期识别与监测预警[J]. 武汉大学学报(信息科学版), 44(7): 957-966.
许强. 2020. 对滑坡监测预警相关问题的认识与思考[J]. 工程地质学报，28(2)：360-374.
薛欣. 2021. 库岸堆积层滑坡变形滞后效应研究[D]. 三峡大学.
薛薇, 陈欢歌. 2010. Clementine数据挖掘方法及应用[M]. 电子工业出版社.
杨忠平, 李绪勇, 赵茜, 等. 2021. 关键影响因子作用下三峡库区堆积层滑坡分布规律及变形破坏响应特征[J]. 工程地质学报, 29(3): 617-627.
叶润青, 付小林, 郭飞, 等. 2021. 三峡水库运行期地质灾害变形特征及机制分析[J]. 工程地质学报, 29(3): 680-692.
殷跃平, 吴树人, 门玉明, 等. 2012. 滑坡监测预警与应急防治技术研究[M]. 北京: 科学出版社.
朱赛楠, 殷跃平, 黄波林, 等. 2021. 三峡库区大型单斜顺层新生滑坡变形特征与失稳机理研究[J]. 工程地质学报, 29(3): 657-667.
引用格式：朱鸿鹄, 王佳, 李厚芝, 等. 2022. 基于数据挖掘的三峡库区特大滑坡变形关联规则研究[J]. 工程地质学报, 30(5): 1517-1527. doi: 10.13544/j.cnki.jeg.2022-0514
Citation: Zhu Honghu, Wang Jia, Li Houzhi, et al. 2022. Association rule analysis for giant landslide deformation of the Three Gorges Reservoir region based on data mining[J]. Journal of Engineering Geology, 30(5): 1517-1527. doi: 10.13544/j.cnki.jeg.2022-0514