Landslide susceptibility assessment based on multi-scale segmentation of remote sensing and geological factor evaluation
-
摘要:
区域滑坡易发性的研究是滑坡空间预测的核心内容之一。从影像多尺度分割和面向对象的分类理论出发，以研究区遥感影像的熵、能量、相关性、对比度共4个参数作为影像纹理因子提取易发性特征，利用滑坡所处区域的库水影响等级、坡度、斜坡结构、工程岩组4类地质因子分析地质背景，搭建C5.0决策树的易发性分类模型，实现了对研究区内4类滑坡易发性单元的预测。结果表明：高易发性单元的工程岩组通常发育为软岩岩组和软硬相间岩组，且坡度在15°～30°之间；模型显示该区域训练样本和测试样本平均正确率达91.64%，Kappa系数分别为0.84，0.51，因此这种基于影像多尺度分割与地质因子分级的滑坡易发性分类研究具有一定的适用性。
Abstract:The prediction and prevention of landslide is an important issue, and the study of regional landslide susceptibility is one of the core of landslide spatial prediction. Based on the multi-scale segmentation and object-oriented classification theory, four parameters including entropy, energy, correlation and contrast of remote sensing image are selected as the texture factor to extract the susceptibility features. the four types of geological factors including the reservoir water impact rating, slope, slope structure and engineering rock group were adopted to analyze the geological background, finally the C5.0 decision tree model was constructed to predict the four types of landslide-prone units in the study area. The results show that the engineering rock group of the high-susceptibility unit usually develops into soft rock group and soft-hard interphase group, and the slope was mostly between 15° to 30° in these units. The average correct rate of training samples and test samples is 91.64%, the Kappa coefficients are 0.84 and 0.51, respectively. Therefore, this kind of landslide susceptibility classification based on image multi-scale segmentation and geological factor rating has certain applicability.
-
Key words:
- landslide /
- susceptibility /
- remote sensing /
- multi-scale segmentation /
- C5.0 decision tree
-
-
表 1 秭归—巴东工程岩组分类标准[18]
Table 1. The classification standard of engineering rock group (Zigui-Badong)
大类 组别 岩性描述 碳酸盐岩岩类 坚硬中至厚层状强岩溶化碳酸盐岩岩组（Ⅰ） 灰岩、白云岩、白云质灰岩、灰质白云岩组 较坚硬中至厚层状强至中等岩溶化碳酸盐岩岩组（Ⅱ） 灰岩、泥质灰岩、白云岩为主 较坚硬薄至中厚层状弱岩溶化碳酸盐岩岩组（Ⅲ） 灰岩、白云岩、白云质灰岩为主 碎屑岩岩类 坚硬较坚硬中至厚层状砂岩、泥质粉砂岩夹页岩煤层与泥岩页岩互层岩组（Ⅰ） 砂岩、泥质粉砂岩为主，夹泥岩或互层发育 较坚硬至软质薄层至中厚层状页岩砂岩泥岩岩组（Ⅱ） 砂岩、砂质页岩为主 软质薄层至中厚层状泥质粉砂岩页岩岩组（Ⅲ） 泥岩、粉砂岩为主 碳酸盐岩、碎屑岩互层岩类 弱岩溶较坚硬层状泥灰岩、较软弱层状粉砂岩相间岩组 灰岩、泥灰岩与粉砂岩、泥质粉砂岩相间 
下载: 导出CSV
表 2 地质数据评级因子库
Table 2. Geological evaluation factors
评价因子 代号 分级情况 描述 库水影响等级 1 弱影响 >430 m 2 中级影响 320～430 m 3 强影响 175～320 m 4 主波动区 145～175 m 工程岩组 1 多硬质 泥盆系、石炭系地层，灰岩为主 2 多软质 侏罗系、志留系地层，泥页岩为主 3 软硬相间 巴东组、二叠系地层、砂岩为主 坡度类型 1 平缓坡 <15° 2 缓倾坡 15°～30° 3 中倾坡 30°～45° 4 陡倾坡 >45° 斜坡结构（坡度θ、
坡向σ、地层倾向α、
倾角β，Y = |σ–α|）1 飘倾坡 0°<Y<30°或330°<Y<360°，
β>10°且θ>β2 层面坡 0°<Y<30°或330°<Y<360°，
β>10°且θ = β3 伏倾坡 0°<Y<30°或330°<Y<360°，
β>10°且θ<β4 顺斜坡 30°<Y<60°或300°<Y<330° 5 横向坡 60°<Y<120°或240°<Y<300° 6 逆斜坡 120°<Y<150°或210°<Y<240° 7 逆向坡 150°<Y<180°或180°<Y<210° 8 块状岩体 α、β为空
下载: 导出CSV
表 3 训练集分类预测结果
Table 3. Result of training set classification
精度评判 实际结果与分类结果
混淆矩阵Kappa系数 正确 479 93.73% 0(非滑坡) 1(滑坡) 错误 32 6.27% 0(非滑坡) 381 21 0.84 总计 511 100.00% 1(滑坡) 11 98
下载: 导出CSV
表 4 测试集分类预测结果
Table 4. Result of testing set classification and prediction
精度评判 实际结果与分类结果
混淆矩阵Kappa系数 正确 190 86.76% 0(非滑坡) 1(滑坡) 错误 29 13.24% 0(非滑坡) 128 20 0.51 总计 219 100.00% 1(滑坡) 9 62
下载: 导出CSV
表 5 秭归—巴东段滑坡易发性分区总体结果
Table 5. Landslide susceptibility classification prediction (Zigui—Badong)
预测值 预测类别 对象个数 百分比% 离散型 0 稳定区 1977 86.75 1 危险区 302 13.25 连续型 [0，0.263) 不易发区 1865 81.83 [0.263，0.420) 低易发区 71 3.12 [0. 420，0.571) 中易发区 67 2.94 [0.571，1] 高易发区 276 12.11
下载: 导出CSV
-
[1] NEMČOK A, PAŠEK J, RYBÁŘ J. Classification of landslides and other mass movements[J]. Rock Mechanics,1972,4(2):71 − 78. doi: 10.1007/BF01239137
[2] 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)
[3] 牛瑞卿, 彭令, 叶润青, 等. 基于粗糙集的支持向量机滑坡易发性评价[J]. 吉林大学学报(地球科学版),2012,42(2):430 − 439. [NIU Ruiqing, PENG Ling, YE Runqing, et al. Landslide susceptibility assessment based on rough sets and support vector machine[J]. Journal of Jilin University (Earth Science Edition),2012,42(2):430 − 439. (in Chinese with English abstract)
[4] BALDO M, BICOCCHI C, CHIOCCHINI U, et al. LIDAR monitoring of mass wasting processes: The Radicofani landslide, Province of Siena, Central Italy[J]. Geomorphology,2009,105(3/4):193 − 201.
[5] DAI F C, LEE C F, NGAI Y Y. Landslide risk assessment and management: an overview[J]. Engineering Geology,2002,64(1):65 − 87. doi: 10.1016/S0013-7952(01)00093-X
[6] MANTOVANI F, SOETERS R, VAN WESTEN C J. Remote sensing techniques for landslide studies and hazard zonation in Europe[J]. Geomorphology,1996,15(3/4):213 − 225.
[7] GUZZETTI F, REICHENBACH P, ARDIZZONE F, et al. Estimating the quality of landslide susceptibility models[J]. Geomorphology,2006,81(1/2):166 − 184.
[8] EECKHAUT M, MARRE A, POESEN J. Comparison of two landslide susceptibility assessments in the Champagne–Ardenne region (France)[J]. Geomorphology,2010,115(1/2):141 − 155.
[9] NICHOL J E, SHAKER A, WONG M S. Application of high-resolution stereo satellite images to detailed landslide hazard assessment[J]. Geomorphology,2006,76(1/2):68 − 75.
[10] ZHOU G, ESAKI T, MITANI Y, et al. Spatial probabilistic modeling of slope failure using an integrated GIS Monte Carlo simulation approach[J]. Engineering Geology,2003,68(3/4):373 − 386.
[11] 段功豪, 牛瑞卿, 彭令, 等. 诱发因素影响下的滑坡参数优化预测模型研究[J]. 武汉大学学报(信息科学版),2017,42(4):531 − 536. [DUAN Gonghao, NIU Ruiqing, PENG Ling, et al. A landslide displacement prediction research based on optimization-parameter ARIMA model under the inducing factors[J]. Geomatics and Information Science of Wuhan University,2017,42(4):531 − 536. (in Chinese with English abstract)
[12] FALL M, AZZAM R, NOUBACTEP C. A multi-method approach to study the stability of natural slopes and landslide susceptibility mapping[J]. Engineering Geology,2006,82(4):241 − 263. doi: 10.1016/j.enggeo.2005.11.007
[13] 李明威, 唐川, 陈明, 等. 汶川震区北川县泥石流流域崩滑体时空演变特征[J]. 水文地质工程地质,2020,47(3):182 − 190. [LI Mingwei, TANG Chuan, CHEN Ming, et al. Spatio-temporal evolution characteristics of landslides in debris flow catchment in Beichuan County in the Wenchuan earthquake zone[J]. Hydrogeology & Engineering Geology,2020,47(3):182 − 190. (in Chinese with English abstract)
[14] 文广超, 张哲玮, 肖学军, 等. 基于遥感数据的灾后滑坡信息快速提取方法[J]. 中国地质灾害与防治学报,2020,31(2):80 − 86. [WEN Guangchao, ZHANG Zhewei, XIAO Xuejun, et al. Method for rapid extraction information for post-disaster landslide based on remote sensing images[J]. The Chinese Journal of Geological Hazard and Control,2020,31(2):80 − 86. (in Chinese with English abstract)
[15] 丁辉, 张茂省, 朱卫红, 等. 黄土滑坡高分辨率遥感影像识别—以陕西省延安市地区为例[J]. 西北地质,2019,52(3):231 − 239. [DING Hui, ZHANG Maosheng, ZHU Weihong, et al. High resolution remote sensing for the identification of loess landslides: example from Yan'an City[J]. Northwestern Geology,2019,52(3):231 − 239. (in Chinese with English abstract)
[16] 张森, 陈健飞, 龚建周. 面向对象分类的决策树方法探讨—以Landsat-8OLI为例[J]. 测绘科学,2016,41(6):117 − 121. [ZHANG Sen, CHEN Jianfei, GONG Jianzhou. Object-oriented classification based on C5.0 algorithm[J]. Science of Surveying and Mapping,2016,41(6):117 − 121. (in Chinese with English abstract)
[17] CARLEER A P, WOLFF E. Urban land cover multi-level region-based classification of VHR data by selecting relevant features[J]. International Journal of Remote Sensing,2006,27(6):1035 − 1051. doi: 10.1080/01431160500297956
[18] 谭建民, 常宏, 韩会卿, 等. 清江流域滑坡发育地质环境特征的统计分析[J]. 华南地质与矿产,2018,34(4):315 − 322. [TAN Jianmin, CHANG Hong, HAN Huiqing, et al. Statistical analysis of the geological environment characteristics of landslide development in Qingjiang River Basin[J]. Geology and Mineral Resources of South China,2018,34(4):315 − 322. (in Chinese with English abstract) doi: 10.3969/j.issn.1007-3701.2018.04.006
-
图(5)
表(5)
计量
- 文章访问数: 1449
- PDF下载数: 12
- 施引文献: 0