九寨沟地震滑坡易发性评价因子组合选取研究

doi:10.13722/j.cnki.jrme.2021.0198

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (194347 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要滑坡易发性区域评价作为危险性和风险评价的基础，如何科学、合理地进行因子选取是已有研究的薄弱部分。以2017年8月8日九寨沟Mw 6.5地震重灾区——九寨沟国家地质公园内的1 022处地震滑坡点为样本数据，选取地震参数、地形地貌、地质条件、水文条件、人类工程活动等共16个滑坡控制和影响因素，在对指标因子进行共线性诊断的基础上，采用逻辑回归(Logistic Regression，LR)模型在斜坡单元下开展不同因素组合，建立30个评价模型，最后在软件R中采用10折交叉验证的数据采样方法和ROC曲线进行模型准确率与预测精度评价。结果表明：LR模型在九寨沟地区地震滑坡易发性区域评价中具有良好的适用性；地震滑坡主要受地震因素和地形地貌的控制影响作用，当剔除掉水文条件和人类工程活动等因子时，模型性能出现小幅度降低；交叉验证方法相比传统的数据取样方法，可以有效减少选择偏差和预测方差，更好地检测模型的稳定鲁棒性。研究成果可丰富地震滑坡区域评价理论研究内容，并为九寨沟地区震后快速评价和防灾减灾提供参考。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	罗路广
	裴向军
	崔圣华
	黄润秋
	朱凌
	何智浩

关键词 ：边坡工程, 地震滑坡, 滑坡易发性, 因子组合选取, 10折交叉验证, 逻辑回归模型

Abstract：The regional landslide susceptibility assessment is the basis of landslide hazards and risk assessments. However，how to scientifically select landslide conditioning factors is still a weak part of the previous researches. 1022 identified landslides induced by the Jiuzhaigou earthquake in the Jiuzhaigou National Geopark on August 8，2017 were taken as the sample dataset. A total of 16 landslide causative factors including seismic，topographic，geological，hydrological parameters and human engineering activities were selected. Based on the collinearity test of these continuous conditioning factors，the logistic regression(LR) model was used to generate 30 landslide assessment models by combining different covariates under the slope units，and then the 10-fold cross-validation and receiver operating characteristics(ROC) curve were adopted to assess success rate and prediction accuracy of the models in R statistic software. The results show that the LR model has good applicability in the earthquake-induced landslides(EQILs) susceptibility assessment for the study area，and EQILs are mainly controlled and affected by seismic and topographic parameters. Once hydrological conditions and human engineering activities are excluded out，the performance of the models decreases within a small range. Moreover，compared to the traditional data sampling methods，the cross-validation approach can effectively reduce selection bias and prediction variance，and can better test the robustness of the models. This research may enrich the theoretical research content of EQILs regional assessment and provide references for rapid post-earthquake assessment and disaster prevention and mitigation for the Jiuzhaigou area.

Key words： slope engineering earthquake-induced landslides(EQILs) landslide susceptibility factor combined selection 10-fold cross-validation logistic regression model

引用本文:

罗路广，裴向军，崔圣华，黄润秋，朱凌，何智浩. 九寨沟地震滑坡易发性评价因子组合选取研究[J]. 岩石力学与工程学报, 2021, 40(11): 2306-2319.
LUO Luguang，PEI Xiangjun，CUI Shenghua，HUANG Runqiu，ZHU Ling，HE Zhihao. Combined selection of susceptibility assessment factors for Jiuzhaigou earthquake-induced landslides. , 2021, 40(11): 2306-2319.

链接本文:

http://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2021.0198 或 http://rockmech.whrsm.ac.cn/CN/Y2021/V40/I11/2306

[24]	KEEFER D K. Landslides caused by earthquakes[J]. Geological Society of America Bulletin，1984，95(4)：406-421.
[5]	BUI D T，TUAN T A，KLEMPE H，et al. Spatial prediction models for shallow landslide hazards：a comparative assessment of the efficiency of support vector machines，artificial neural networks，kernel logistic regression，and logistic tree[J]. Landslides，2016，13(2)：361-378.
[8]	马思远，许冲，田颖颖，等. 基于逻辑回归模型的九寨沟地震滑坡危险性评估[J]. 地震地质，2019，41(1)：162-177.(MA Siyuan，XU Chong，TIAN Yingying，et al. Application of logistic regression model for hazard assessment of earthquake-triggered landslides：a case study of 2017 Jiuzhaigou(China) MS 7.0 event[J]. Seismology and Geology，2019，41(1)：162-177.(in Chinese))
[11]	YI Y，ZHANG Z，ZHANG W，et al. Landslide susceptibility mapping using multiscale sampling strategy and convolutional neural network：A case study in Jiuzhaigou region[J]. Catena，2020，195：104851.
[13]	ALEOTTI P，CHOWDHURY R. Landslide hazard assessment：summary review and new perspectives[J]. Bulletin of Engineering Geology and the Environment，1999，58(1)：21-44.
[15]	PRADHAN B，LEE S. Landslide susceptibility assessment and factor effect analysis：backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling[J]. Environmental Modelling and Software，2010，25(6)：747-759.
[18]	李雪平，唐辉明. 贝叶斯信息标准在滑坡因子敏感性分析中的应用[J]. 岩土力学，2006，27(8)：1 393-1 397.(LI Xueping，TANG Huiming. Application of Bayesian information criterion to sensitivity analysis of landslide factor[J]. Rock and Soil Mechanics，2006，27(8)：1 393-1 397.(in Chinese))
[21]	COSTANZO D，ROTIGLIANO E，IRIGARAY C，et al. Factors selection in landslide susceptibility modelling on large scale following the gis matrix method：application to the river Beiro basin(Spain)[J]. Natural Hazards and Earth System Sciences，2012，12(2)：327-340.
[23]	于宪煜，胡友健，牛瑞卿. 基于RS-SVM模型的滑坡易发性评价因子选择方法研究[J]. 地理与地理信息科学，2016，32(3)：23-28.(YU Xianyu，HU Youjian，NIU Ruiqing. Research on the method to select landslide susceptibility evaluation factors based on RS-SVM model[J]. Geography and Geo-Information Science，2016，32(3)：23-28.(in Chinese))
[28]	周德培，钟卫，杨涛. 基于坡体结构的岩质边坡稳定性分析[J]. 岩石力学与工程学报，2008，27(4)：687-695.(ZHOU Depei，ZHONG Wei，YANG Tao. Stability analysis of rocky slope based on slope structures[J]. Chinese Journal of Rock Mechanics and Engineering，2008，27(4)：687-695.(in Chinese))
[31]	GEISSER S. The predictive sample reuse method with applications[J]. Journal of the American statistical Association，1975，70(350)：320-328.
[6]	中国科学院科技战略咨询研究院，中国科学院文献情报中心. 2020研究前沿[EB/OL]. http：// www. dsac.cn/News/Detail/28422，2020-11-13/ 2020-11-16.(Institutes of Science and Development，National Science Library，Chinese Academy of Sciences. Research Fronts Report 2020[EB/OL]. http：//www. dsac.cn/News/Detail/ 28422，2020-11-13/2020-11-16.(in Chinese))
[16]	黄发明，殷坤龙，蒋水华，等. 基于聚类分析和支持向量机的滑坡易发性评价[J]. 岩石力学与工程学报，2018，37(1)：156-167. (HUANG Faming，YIN Kunlong，JIANG Shuihua，et al. Landslide susceptibility assessment based on clustering analysis and support vector machine[J]. Chinese Journal of Rock Mechanics and Engineering，2018，37(1)：156-167.(in Chinese))
[26]	李秀珍，孔纪名，崔云，等. 汶川地震滑坡与地震参数及地质地貌因素之间的相关关系[J]. 工程地质学报，2010，18(1)：8-14.(LI Xiuzhen，KONG Jiming，CUI Yun，et al. Statistical relations between landslides induced by Wenchuan earthquake and earthquake parameters，geological as well as geomorphological factors[J]. Journal of Engineering Geology，2010，18(1)：8-14.(in Chinese))
[2]	BRABB E. Innovative approaches for landslide hazard evaluation[C]// Proceedings of IVth International Conference and Field Workshop in Landslides. Tokyo，Japan：Japan Landslide Society，1984：307-323.
[4]	LEE C T，HUANG C C，LEE J F，et al. Statistical approach to earthquake-induced landslide susceptibility[J]. Engineering Geology，2008，100(1/2)：43-58.
[12]	CAO J，ZHANG Z，DU J，et al. Multi-geohazards susceptibility mapping based on machine learning—a case study in Jiuzhaigou，China[J]. Natural Hazards，2020，102(3)：851-871.
[22]	KAVZOGLU T，SAHIN E K，COLKESEN I. Selecting optimal conditioning factors in shallow translational landslide susceptibility mapping using genetic algorithm[J]. Engineering Geology，2015，192：101-112.
[32]	杨德旭. 云南省巧家县地震前后滑坡易发性评价及地震作用影响综合研究[硕士学位论文][D]. 昆明：昆明理工大学，2019.(YANG Dexu. Comprehensive study on landslide susceptibility evaluation and seismic effect before and after earthquake in Qiaojia County，Yunnan Province[M. S. Thesis][D]. Kunming：Kunming University of Science and Technology，2019.(in Chinese))
[9]	许冲，徐锡伟，周本刚，等. 同震滑坡发生概率研究——新一代地震滑坡危险性模型[J]. 工程地质学报，2019，27(5)：1 121-1 129. (XU Chong，XU Xiwei，ZHOU Bengang，et al. Probability of coseismic landslides：A new generation of earthquake-triggered landslide hazard model[J]. Journal of Engineering Geology，2019，27(5)：1 121-1 129. (in Chinese))
[14]	AMATO G，FIORUCCI M，MARTINO S，et al. Earthquake-triggered landslide susceptibility in Italy by means of Artificial Neural Network[EB/OL]. [2021-03-08]. https：//xueshu.baidu.com/usercenter/ paper/show?paperid=1x7a0a60x20m0tf0mv5d0c20rf749269&site=xueshu_se.
[10]	罗路广，裴向军，黄润秋. 强震山区地震滑坡发生概率研究——以九寨沟国家地质公园为例[J]. 岩石力学与工程学报，2020，39(10)：2 079-2 093.(LUO Luguang，PEI Xiangjun，HUANG Runqiu. Earthquake-triggered landslide occurrence probability in strong seismically mountainous areas：a case study of Jiuzhaigou National Geopark[J]. Chinese Journal of Rock Mechanics and Engineering，2020，39(10)：2 079-2 093.(in Chinese))
[19]	赵忠国，张峰，郑江华. 多元自适应回归样条法的滑坡敏感性评价[J]. 武汉大学学报：信息科学版，2021，46(3)：442-450.(ZHAO Zhongguo，ZHANG Feng，ZHENG Jianghua. Evaluation of landslide susceptibility by multiple adaptive regression spline method[J]. Geomatics and Information Science of Wuhan University：2021，46(3)：442-450.(in Chinese))
[29]	MOORE D S，NOTZ W I. Statistics：concepts and controversies[M]. Macmillan：[s. n.]，2006：234-236.
[17]	HUANG F，YIN K，HUANG J，et al. Landslide susceptibility mapping based on self-organizing-map network and extreme learning machine[J]. Engineering Geology，2017，223：11-22.
[20]	ROTIGLIANO E，CAPPADONIA C，CONOSCENTI C，et al. Slope units-based flow susceptibility model：using validation tests to select controlling factors[J]. Natural Hazards，2012，61(1)：143-153.
[30]	ALVIOLI M，MARCHESINI I，REICHENBACH P，et al. Automatic delineation of geomorphological slope units with r.slopeunits v1.0 and their optimization for landslide susceptibility modeling[J]. Geoscientific Model Development，2016，9(11)：3 975-3 991.
[27]	LOMBARDO L，SAIA S，SCHILLACI C，et al. Modeling soil organic carbon with quantile regression：Dissecting predictors' effects on carbon stocks[J]. Geoderma，2018，318：148-159.
[25]	HOSMER D W，LEMESHOW S. Applied logistic regression[M]. 2nd ed. New York：Wiley，2000：160-164.
[3]	REICHENBACH P，ROSSI M，MALAMUD B D，et al. A review of statistically-based landslide susceptibility models[J]. Earth-Science Reviews，2018，180：60-91.
[1]	VARNES D J. Landslide hazard zonation：a review of principles and practice[M]. Paris：United Nations Economic，Scientific and Cultural Organization，UNESCO 3，1984：63.
[7]	FAN X，SCARINGI G，XU Q，et al. Coseismic landslides triggered by the 8th August 2017 Ms 7.0 Jiuzhaigou earthquake(Sichuan，China)：factors controlling their spatial distribution and implications for the seismogenic blind fault identification[J]. Landslides，2018，15(5)：967-983.