ISSN 1000-3665 CN 11-2202/P
  • 中文核心期刊
  • Scopus 收录期刊
  • 中国科技核心期刊
  • DOAJ 收录期刊
  • CSCD 收录期刊
  • 《WJCI 报告》收录期刊
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SOM-I-SVM耦合模型的滑坡易发性评价

贾雨霏 魏文豪 陈稳 杨清卓 盛逸凡 徐光黎

贾雨霏,魏文豪,陈稳,等. 基于SOM-I-SVM耦合模型的滑坡易发性评价[J]. 水文地质工程地质,2022,50(0): 1-14 doi:  10.16030/j.cnki.issn.1000-3665.202206041
引用本文: 贾雨霏,魏文豪,陈稳,等. 基于SOM-I-SVM耦合模型的滑坡易发性评价[J]. 水文地质工程地质,2022,50(0): 1-14 doi:  10.16030/j.cnki.issn.1000-3665.202206041
JIA Yufei, WEI Wenhao, CHEN Wen, et al. Landslide susceptibility assessment based on the SOM-I-SVM model[J]. Hydrogeology & Engineering Geology, 2022, 50(0): 1-14 doi:  10.16030/j.cnki.issn.1000-3665.202206041
Citation: JIA Yufei, WEI Wenhao, CHEN Wen, et al. Landslide susceptibility assessment based on the SOM-I-SVM model[J]. Hydrogeology & Engineering Geology, 2022, 50(0): 1-14 doi:  10.16030/j.cnki.issn.1000-3665.202206041

基于SOM-I-SVM耦合模型的滑坡易发性评价

doi: 10.16030/j.cnki.issn.1000-3665.202206041
基金项目: 湖北省科技厅研发项目(2021BCA219);
详细信息
    作者简介:

    贾雨霏(1998-),女,硕士研究生,主要从事地质灾害分析与防治的研究。E-mail:jiayufei@cug.edu.cn

    通讯作者:

    徐光黎(1963-),男,教授,主要从事地质工程与地质灾害方面的教学研究工作。E-mail:xu1963@cug.edu.cn

  • 中图分类号: P642.22

Landslide susceptibility assessment based on the SOM-I-SVM model

  • 摘要: 在使用机器学习模型对滑坡进行易发性评价时,非滑坡样本点通常会在滑坡影响范围之外随机选取,具有一定的误差。为了提高滑坡易发性评价的精度,本文将自组织映射(Self-organizing map, SOM)神经网络、信息量模型(Information,I)以及支持向量机模型(Support Vector Machine,SVM)进行耦合,提出一种基于SOM-I-SVM模型的滑坡易发性评价方法,并将SOM神经网络与K均值聚类算法进行对比,验证模型的可靠性。以十堰市茅箭区为例,首先通过对环境因子的相关性及重要性分析筛选出距水系距离、坡度、降雨量、距构造距离、相对高差、距道路距离、地层岩性7个因子建立滑坡易发性评价指标体系,在此基础上计算出各因子的分级信息量值,并作为模型的输入变量进行滑坡易发性评价。分别采用SOM神经网络和K均值聚类算法选取非滑坡样本,然后将样本数据集代入I-SVM模型预测滑坡易发性。将SVM、I-SVM、KMeans-I-SVM、SOM-I-SVM四种模型预测精度进行对比,其ROC曲线下面积AUC值分别为0.819、0.882、0.901、0.917,说明SOM-I-SVM模型能有效提高滑坡易发性预测准确率。
  • 图  1  茅箭区地理位置示意图

    Figure  1.  Location of the Maojian District

    图  2  SOM神经网络

    Figure  2.  SOM Neural Network

    图  3  支持向量机模型

    Figure  3.  Support vector machine model

    图  4  SOM-I-SVM模型建模流程

    Figure  4.  Process of the SOM-I-SVM model

    图  5  研究区滑坡灾害易发性评价指标因子

    Figure  5.  Index factors of landslide hazard susceptibility evaluation in the study area

    图  6  影响因子相关性热力图

    注:“*”表示两个因子之间相关性显著

    Figure  6.  Correlation chart of impact factors

    图  7  评价因子重要性分布图

    Figure  7.  Importance chart of evaluation factors

    图  8  SVM模型滑坡易发性分区

    Figure  8.  Zoning map of landslide susceptibility based on the SVM model

    图  9  I-SVM模型滑坡易发性分区

    Figure  9.  Zoning map of landslide susceptibility based on the I-SVM model

    图  10  KMeans聚类模型易发性分区及样本选择

    Figure  10.  Landslide susceptibility zoning and sample selection of the KMeans model

    图  11  SOM神经网络易发性分区及样本选择

    Figure  11.  Landslide susceptibility zoning and sample selection of the SOM neural network

    图  12  KMeans-I-SVM模型滑坡易发性分区

    Figure  12.  Zoning map of landslide susceptibility based on the KMeans-I-SVM model

    图  13  SOM-I-SVM模型滑坡易发性分区

    Figure  13.  Zoning map of landslide susceptibility based on the SOM-I-SVM model

    图  14  各易发等级历史滑坡点个数

    Figure  14.  Number of historical landslide sites of each vulnerability level

    图  15  ROC曲线对比图

    Figure  15.  ROC curves of the four used models

    表  1  各评价因子分级信息量值

    Table  1.   Information values of each evaluation factor

    因子分段灾点数灾点
    栅格数
    信息量排序
    相对高差(m)≤10232890.08590514315
    11~30255930.2349294418
    31~50287920.09514958413
    >50375−1.36892057128
    坡度
    (°)
    ≤10273980.09001148714
    11~20112280.198677839
    21~30247330.4404129677
    31~4012322−0.46757624223
    41~50568−0.99524972727
    >5000.00001−14.8642348729
    工程地质岩组坚硬块状变辉绿岩岩组498−0.57308226525
    较坚硬中-厚层状变粒岩岩组511113.75−0.08793424318
    较坚硬—较软弱薄—厚层状变粒岩、石英片岩互层岩组24537.250.5180905026
    松散土体00.00001−15.1774206830
    距构造距离
    (m)
    ≤200143400.6481029114
    201~6009273−0.23211977621
    601~100015255−0.16879351819
    >100041881−0.04868440417
    距水系距离
    (m)
    ≤200437380.7836255763
    201~40012225−0.21430188920
    401~60062820.12734742710
    >60018504−0.56285975424
    降雨量
    (mm)
    785~8555109−0.6335326
    856~891275250.1094512
    892~92524526−0.0411316
    926~1010235890.1151011
    距道路距离
    (m)
    ≤503540.5554175
    51~10092791.058392
    101~150213511.366021
    >150451065−0.3633422
    下载: 导出CSV

    表  2  SVM、I-SVM模型参数表

    Table  2.   Parameters of the SVM and I-SVM models

    模型类型超参数调试范围最佳参数模型评分
    SVMC(0.1−10,0.1)1.10.773
    gamma(0.1−10,0.1)0.12328
    I-SVMC(0.1-10,0.1)0.80.848
    gamma(0.1-10,0.1)10.48113
    下载: 导出CSV

    表  3  SVM、I-SVM模型分区结果

    Table  3.   Results of the SVM and I-SVM models

    模型
    类型
    易发性
    等级
    分区面积
    (km2
    所占
    比例
    滑坡个数占滑坡总数比例
    SVM低易发区199.87540.73%1012.82%
    中易发区129.47626.39%1620.51%
    高易发区89.73718.29%2126.92%
    极高易发区71.62214.60%3139.74%
    I-SVM低易发区221.59445.16%1114.10%
    中易发区121.87224.84%1316.67%
    高易发区83.54917.03%1519.23%
    极高易发区63.69512.98%3950.00%
    下载: 导出CSV

    表  4  SOM-I-SVM、KMeans-I-SVM模型参数表

    Table  4.   Parameters of the SOM-I-SVM and KMeans-I-SVM models

    模型类型超参数调试范围最佳参数模型评分
    SOM-I-SVMC(0.1−10,0.1)0.70.879
    gamma(0.1−10,0.1)0.39442
    KMeans-I-SVMC(0.1−10,0.1)6.00.856
    gamma(0.1−10,0.1)0.76396
    下载: 导出CSV

    表  5  KMeans-I-SVM、SOM-I-SVM模型分区结果

    Table  5.   Results of the KMeans-I-SVM and SOM-I-SVM models

    模型
    类型
    易发性
    等级
    分区面积
    (km2
    所占
    比例
    滑坡个数占滑坡
    总数比例
    KMeans-
    I-SVM
    低易发区235.5448.00%1417.95%
    中易发区101.92920.77%1012.82%
    高易发区88.31418.00%1721.79%
    极高易发区64.92713.23%3747.44%
    SOM-I-SVM低易发区223.59445.57%911.54%
    中易发区121.10424.68%1012.82%
    高易发区83.53717.02%1417.95%
    极高易发区62.47512.73%4557.69%
    下载: 导出CSV
  • [1] GUZZETTI F,REICHENBACH P,CARDINALI M,et al. Probabilistic landslide hazard assessment at the basin scale[J]. Geomorphology,2005,72(1/2/3/4):272 − 299.
    [2] CUI K,LU D,LI W. Comparison of landslide susceptibility mapping based on statistical index,certainty factors,weights of evidence and evidential belief function models[J]. Geocarto International,2017,32(9):935 − 955. doi:  10.1080/10106049.2016.1195886
    [3] 许嘉慧,张虹,文海家,等. 基于逻辑回归的巫山县滑坡易发性区划研究[J]. 重庆师范大学学报(自然科学版),2021,38(2):48 − 56. [XU Jiahui,ZHANG Hong,WEN Haijia,et al. Landslide susceptibility mapping based on logistic regression in Wushan County[J]. Journal of Chongqing Normal University (Natural Science),2021,38(2):48 − 56. (in Chinese with English abstract)
    [4] 栗泽桐,王涛,周杨,等. 基于信息量、逻辑回归及其耦合模型的滑坡易发性评估研究:以青海沙塘川流域为例[J]. 现代地质,2019,33(1):235 − 245. [LI Zetong,WANG Tao,ZHOU Yang,et al. Landslide susceptibility assessment based on information value model,logistic regression model and their integrated model:a case in Shatang River Basin,Qinghai Province[J]. Geoscience,2019,33(1):235 − 245. (in Chinese with English abstract)
    [5] 盛逸凡,李远耀,徐勇,等. 基于有效降雨强度和逻辑回归的降雨型滑坡预测模型[J]. 水文地质工程地质,2019,46(1):156 − 162. [SHENG Yifan,LI Yuanyao,XU Yong,et al. Prediction of rainfall-type landslides based on effective rainfall intensity and logistic regression[J]. Hydrogeology & Engineering Geology,2019,46(1):156 − 162. (in Chinese with English abstract)
    [6] SCHICKER R,MOON V. Comparison of bivariate and multivariate statistical approaches in landslide susceptibility mapping at a regional scale[J]. Geomorphology,2012,161/162:40 − 57. doi:  10.1016/j.geomorph.2012.03.036
    [7] 金朝,费雯丽,丁卫,等. 基于信息量模型和Logistic回归模型的地质灾害易发性评价—以十堰市郧阳区为例[J]. 资源环境与工程,2021,35(6):845 − 850. [JIN Zhao,FEI Wenli,DING Wei,et al. Evaluation of geological disaster susceptibility based on information model and logistic regression model[J]. Resources Environment & Engineering,2021,35(6):845 − 850. (in Chinese with English abstract)
    [8] 李利峰,张晓虎,邓慧琳,等. 基于熵指数与逻辑回归耦合模型的滑坡灾害易发性评价—以蓝田县为例[J]. 科学技术与工程,2020,20(14):5536 − 5543. [LI Lifeng,ZHANG Xiaohu,DENG Huilin,et al. Assessment of landslide susceptibility based on coupling model of index of entropy and logistic regression:a case study of Lantian County[J]. Science Technology and Engineering,2020,20(14):5536 − 5543. (in Chinese with English abstract)
    [9] 覃乙根,杨根兰,江兴元,等. 基于确定性系数模型与逻辑回归模型耦合的地质灾害易发性评价—以贵州省开阳县为例[J]. 科学技术与工程,2020,20(1):96 − 103. [QIN Yigen,YANG Genlan,JIANG Xingyuan,et al. Geohazard susceptibility assessment based on integrated certainty factor model and logistic regression model for Kaiyang,China[J]. Science Technology and Engineering,2020,20(1):96 − 103. (in Chinese with English abstract)
    [10] 吴雨辰,周晗旭,车爱兰. 基于粗糙集-神经网络的IBURI地震滑坡易发性研究[J]. 岩石力学与工程学报,2021,40(6):1226 − 1235. [WU Yuchen,ZHOU Hanxu,CHE Ailan. Susceptibility of landslides caused by IBURI earthquake based on rough set-neural network[J]. Chinese Journal of Rock Mechanics and Engineering,2021,40(6):1226 − 1235. (in Chinese with English abstract)
    [11] 丁茜,赵晓东,吴鑫俊,等. 基于RBF核的多分类SVM滑塌易发性评价模型[J]. 中国安全科学学报,2022,32(3):194 − 200. [DING Xi,ZHAO Xiaodong,WU Xinjun,et al. Landslide susceptibility assessment model based on multi-class SVM with RBF kernel[J]. China Safety Science Journal,2022,32(3):194 − 200. (in Chinese with English abstract)
    [12] 刘坚,李树林,陈涛. 基于优化随机森林模型的滑坡易发性评价[J]. 武汉大学学报·信息科学版,2018,43(7):1085 − 1091. [LIU Jian,LI Shulin,CHEN Tao. Landslide susceptibility assesment based on optimized random forest model[J]. Geomatics and Information Science of Wuhan University,2018,43(7):1085 − 1091. (in Chinese with English abstract)
    [13] YESILNACAR E,TOPAL T. Landslide susceptibility mapping:a comparison of logistic regression and neural networks methods in a medium scale study,Hendek region (Turkey)[J]. Engineering Geology,2005,79(3/4):251 − 266.
    [14] 万洋,郭捷,马凤山,等. 基于最大熵模型的中尼交通廊道滑坡易发性分析[J]. 中国地质灾害与防治学报,2022,33(2):88 − 95. [WAN Yang,GUO Jie,MA Fengshan,et al. Landslide susceptibility assessment based on MaxEnt model of along Sino-Nepal traffic corridor[J]. The Chinese Journal of Geological Hazard and Control,2022,33(2):88 − 95. (in Chinese with English abstract)
    [15] 黄武彪, 丁明涛, 王栋, 等. 基于层数自适应加权卷积神经网络的川藏铁路沿线滑坡易发性评价[J/OL]. 地球科学, 2021: 1 − 28. (2021-12-29). https://kns.cnki.net/kcms/detail/42.1874.P.20211228.1644.022.html

    HUANG Wubiao, DING Mingtao, WANG Dong, et al. Evaluation of landslide susceptibility based on layer adaptive weighted convolutional neural network model along Sichuan-Tibet railway[J/OL]. Earth Science, 2021: 1 − 28. (2021-12-29). https://kns.cnki.net/kcms/detail/42.1874.P.20211228.1644.022.html. (in Chinese with English abstract)
    [16] 安凯强,牛瑞卿. 信息量支持下SVM模型滑坡灾害易发性评价[J]. 长江科学院院报,2016,33(8):47 − 51. [AN Kaiqiang,NIU Ruiqing. Landslide susceptibility assessment using support vector machine based on weighted-information model[J]. Journal of Yangtze River Scientific Research Institute,2016,33(8):47 − 51. (in Chinese with English abstract) doi:  10.11988/ckyyb.20150311
    [17] 杜国梁,张永双,吕文明,等. 基于加权信息量模型的藏东南地区滑坡易发性评价[J]. 灾害学,2016,31(2):226 − 234. [DU Guoliang,ZHANG Yongshuang,LYU Wenming,et al. Landslide susceptibility assessment based on weighted information value model in southeast Tibet[J]. Journal of Catastrophology,2016,31(2):226 − 234. (in Chinese with English abstract)
    [18] 陈飞, 蔡超, 李小双, 等. 基于信息量与神经网络模型的滑坡易发性评价[J]. 岩石力学与工程学报, 2020, 39(增刊1): 2859 − 2870

    CHEN Fei, CAI Chao, LI Xiaoshuang, et al. Evaluation of landslide susceptibility based on information volume and neural network model[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(Sup 1): 2859 − 2870. (in Chinese with English abstract)
    [19] 武雪玲,任福,牛瑞卿,等. 斜坡单元支持下的滑坡易发性评价支持向量机模型[J]. 武汉大学学报·信息科学版,2013,38(12):1499 − 1503. [WU Xueling,REN Fu,NIU Ruiqing,et al. Landslide spatial prediction based on slope units and support vector machines[J]. Geomatics and Information Science of Wuhan University,2013,38(12):1499 − 1503. (in Chinese with English abstract)
    [20] BALLABIO C,STERLACCHINI S. Support vector machines for landslide susceptibility mapping:the staffora river basin case study,Italy[J]. Mathematical Geosciences,2012,44(1):47 − 70. doi:  10.1007/s11004-011-9379-9
    [21] 徐胜华,刘纪平,王想红,等. 熵指数融入支持向量机的滑坡灾害易发性评价方法—以陕西省为例[J]. 武汉大学学报·信息科学版,2020,45(8):1214 − 1222. [XU Shenghua,LIU Jiping,WANG Xianghong,et al. Landslide susceptibility assessment method incorporating index of entropy based on support vector machine:a case study of Shaanxi Province[J]. Geomatics and Information Science of Wuhan University,2020,45(8):1214 − 1222. (in Chinese with English abstract)
    [22] 刘福臻,王灵,肖东升. 机器学习模型在滑坡易发性评价中的应用[J]. 中国地质灾害与防治学报,2021,32(6):98 − 106. [LIU Fuzhen,WANG Ling,XIAO Dongsheng. Application of machine learning model in landslide susceptibility evaluation[J]. The Chinese Journal of Geological Hazard and Control,2021,32(6):98 − 106. (in Chinese with English abstract)
    [23] 鲍帅,刘纪平,王亮. 联合DBSCAN聚类采样和SVM分类的滑坡易发性评价[J]. 震灾防御技术,2021,16(4):625 − 636. [BAO Shuai,LIU Jiping,WANG Liang. Landslide susceptibility evaluation based on combined DBSCAN cluster sampling and SVM classification[J]. Technology for Earthquake Disaster Prevention,2021,16(4):625 − 636. (in Chinese with English abstract) doi:  10.11899/j.issn.1673-5722.2021.4.zzfyjs202104003
    [24] 杜国梁,杨志华,袁颖,等. 基于逻辑回归-信息量的川藏交通廊道滑坡易发性评价[J]. 水文地质工程地质,2021,48(5):102 − 111. [DU Guoliang,YANG Zhihua,YUAN Ying,et al. Landslide susceptibility mapping in the Sichuan-Tibet traffic corridor using logistic regression-information value method[J]. Hydrogeology & Engineering Geology,2021,48(5):102 − 111. (in Chinese with English abstract)
    [25] 周天伦,曾超,范晨,等. 基于快速聚类-信息量模型的汶川及周边两县滑坡易发性评价[J]. 中国地质灾害与防治学报,2021,32(5):137 − 150. [ZHOU Tianlun,ZENG Chao,FAN Chen,et al. Landslide susceptibility assessment based on K-means cluster information model in Wenchuan and two neighboring counties,China[J]. The Chinese Journal of Geological Hazard and Control,2021,32(5):137 − 150. (in Chinese with English abstract)
    [26] 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 with English abstract)
    [27] 周超,殷坤龙,曹颖,等. 基于集成学习与径向基神经网络耦合模型的三峡库区滑坡易发性评价[J]. 地球科学,2020,45(6):1865 − 1876. [ZHOU Chao,YIN Kunlong,CAO Ying,et al. Landslide susceptibility assessment by applying the coupling method of radial basis neural network and adaboost:a case study from the Three Gorges Reservoir area[J]. Earth Science,2020,45(6):1865 − 1876. (in Chinese with English abstract)
    [28] WUBALEM A,METEN M. Landslide susceptibility mapping using information value and logistic regression models in Goncha Siso Eneses area,northwestern Ethiopia[J]. SN Applied Sciences,2020,2(5):1 − 19.
  • 加载中
图(15) / 表(5)
计量
  • 文章访问数:  103
  • HTML全文浏览量:  109
  • PDF下载量:  24
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-06-19
  • 录用日期:  2022-10-08
  • 修回日期:  2022-10-03

目录

    /

    返回文章
    返回