EN中文

地球信息科学学报 >

2015 , Vol. 17 >Issue 12: 1554 - 1562

DOI: https://doi.org/10.3724/SP.J.1047.2015.01554

遥感科学与应用技术

基于信息量模型的涪陵区地质灾害易发性评价

  • 谭玉敏 , 1, * ,
  • 郭栋 1 ,
  • 白冰心 1 ,
  • 许波 2
展开
  • 1. 北京航空航天大学交通科学与工程学院, 北京 100191
  • 2. 美国加州州立大学San Bernardino分校地理与环境系,CA 92407

作者简介：谭玉敏（1977-）,女,博士,副教授,研究方向为遥感与GIS应用。E-mail:

收稿日期: 2015-03-24

  要求修回日期: 2015-06-10

  网络出版日期: 2015-12-20

基金资助

2013国家卫星及应用高技术产业化专项“基于国产卫星应用技术的三峡库区生态环境动态监测与应急服务示范”

收起

Geological Hazard Risk Assessment Based on Information Quantity Model in Fuling District, Chongqing City, China

  • TAN Yumin , 1, * ,
  • GUO Dong 1 ,
  • BAI Bingxin 1 ,
  • XU Bo 2
Expand
  • 1. Department of Civil Engineering, Beihang University, Beijing 100191, China
  • 2. Department of Geography & Environmental Studies, California State University San Bernardino, CA 92407, USA
*Corresponding author: TAN Yumin, E-mail:

Received date: 2015-03-24

  Request revised date: 2015-06-10

  Online published: 2015-12-20

Copyright

《地球信息科学学报》编辑部 所有
Fold

摘要

本文以重庆涪陵区为研究区域,选取坡度、坡向、累计汇水面积、地层岩性、水域、降雨量、植被和土地利用分类8个影响因子,提取高分一号遥感数据（2013.12.24）动态影响因子,引入信息量模型,分别计算上述影响因子对应的信息量,对该时期示范区的地质灾害危险性进行评价,并引入ROC曲线和AUC评价指标,对得到的区域地质灾害易发性评价结果进行精度评估。结果显示,2013年12月研究区内高易发区面积占总面积的9.73%,该易发区内含有104个地质灾害点,占所有灾害点的52.7%,灾积比为5.42,明显大于其他易发等级类别。利用ROC评价方法,计算成功率曲线AUC为0.796,预测率曲线AUC为0.748（74.8%）,具有较高的可靠性,证明本文方法在该区域地质灾害易发性评价的适应性良好。

关键词： 地质灾害; 易发性评价; 信息量模型; 动态影响因子

本文引用格式

谭玉敏 , 郭栋 , 白冰心 , 许波 . 基于信息量模型的涪陵区地质灾害易发性评价[J]. 地球信息科学学报, 2015 , 17(12) : 1554 -1562 . DOI: 10.3724/SP.J.1047.2015.01554

Abstract

Using geospatial technologies to assess geological hazard risk has been proved feasible, effective and important in the southwest of China, which is featured by mountainous landscape and the population density is very large. The main objective of this study is to make the risk assessment of the geological hazards in Fuling district using information quantity model, and eight triggering factors are used, including slope, aspect, cumulative catchment area, formation lithology, distances to water, precipitation, vegetation, and land use/land cover type respectively. GaoFen-1 image of December 24, 2013 is used to extract two dynamic triggering factors, vegetation and land use, and precipitation is also taken as a dynamic triggering factor. All triggering factors were then used to construct an information model to assess and predict the geological hazards in the study area in December 2013, producing a geological hazard risk distribution map. Finally, ROC curve was used to validate the information model. The statistical results indicate that the areas with high risk zone is about 9.73% of the entire area and that the percentage of the geological hazards sites is about 52.7% of the entire geological hazards sites. And it shows a satisfactory consistency between the susceptibility map and the geological hazard locations. The AUC of success-rate ROC of 0.796 and the AUC of prediction-rate ROC of 0.748 demonstrate the robustness and relatively good reliability of the information quantity model. Above all, the model can be applied to interpret and predict the geological hazard occurrences in the study area.

Key words： Geological hazard; risk assessment; information quantity; dynamic triggering factors

1 引言

中国西部山区地质环境脆弱,地质灾害多发。地质灾害危及人类生命财产安全、破坏生态环境,特别是在人口密集的地区危害更大[1]。三峡大坝自修建以来,由于受到地形地貌,地质气象等因素影响,地质灾害频发,其主要的地质灾害有滑坡、泥石流、崩塌、高切坡失稳及库岸坍塌等。因此,对该区域进行地质灾害易发性评价具有重要意义。近年来,计算机技术和以遥感与GIS为代表的空间信息技术,已广泛应用于地质灾害易发性的评价,地质灾害定量评价方法主要有人工神经网络法[2-6]、信息量法[7-11]、多元回归分析[12]、逻辑回归分析[13-15]等方法[16]。在地质灾害评价中,人工神经网络法能取得精确度较高的效果,但该方法建模过程与评价过程均比较复杂,系统实现困难,因而实际应用较少;回归分析法与信息量法能取得相对一致效果,但后者原理简单,容易建模,实现方便快捷,因此该法常用于地质灾害评价。殷坤龙和柳源[17]把传统的滑坡单体稳定性分析延伸到以Monte-Carlo方法的概率模拟分析,信息论原理,建立了灾害信息分析系统,以及多因素分析的灾害预测分区方法;阮沈勇和黄润秋[18]将GIS与信息量模型结合应用于地质灾害危险性区划。
本文以重庆市涪陵区特殊的地质环境为研究区,采取改进的信息量模型[19],将滑坡危险评价方法扩大到整个区域地质灾害易发性的评价。首先,结合该地区地质灾害空间分布提取出地质灾害影响因子;其次,应用改进后的信息量模型,实时动态的对地质灾害易发性进行预测;最后,对该地质灾害信息量模型方法进行精度评价。

2 基于信息量模型的地质灾害易发性区域评价

2.1 信息量模型

信息量模型以信息论为基础,模型采用地质灾害发生过程中熵的减少来表征地质灾害事件产生的可能性,以影响地质灾害发生的因素为影响因子,通过计算各因子的信息量,进而将信息量单因素或加权叠加,建立易发性评价模型,对易发性做出评价。信息量用概率来计算,其公式如式（1）。
I y , x 1 x 2 … x n = lo g 2 P ( y | x 1 x 2 … x n ) P ( y ) （1）
式（1）可写成：
I y , x 1 x 2 … x n = I y , x 1 + I x 1 y , x 2 + … + I x 1 x 2 … x n ( y , x n ) （2）
式中, I y , x 1 x 2 … x n 为具体因子组合 x 1 x 2 … x n 对地质灾害提供的信息量; P ( y | x 1 x 2 … x n ) 为 因子 x 1 x 2 … x n 组合条件下地质灾害发生的概率;P(y)为地质灾害发生的概率; I x 1 y , x 2 为因子x1存在的条件下,因子x2对地质灾害所提供的信息量。
通常情况下,对区域地质灾害的发生有影响的因子很多。对各因子信息量进行单因素信息量叠加,可得到研究区多因子共同作用下的综合信息量。如果用Ii表示影响因子 x i 的信息量,则有式（3）：
I y , x 1 x 2 … x n = ∑ i = 1 n I i （3）
区域灾害易发性评价以对研究区进行评价单元的划分为基础,即为影响因子划分网格。格网划分过大会引起信息混淆,过小则影响效率。对于规则的正方形格网大小可选作与栅格数据分辨率相同,也可由经验公式得到,如李军[24]等以香港大屿山滑坡风险评估为例,分析影响适宜栅格单元的因子,给出网格大小选取的经验公式（式（4））：
G s = 7.49 + 0.0006 S - 2.0 × 10 - 9 S 2 + 2.9 × 10 - 15 S 3 （4）
式中,Gs为适宜网格的大小;S为原始等高线数据精度的分母。
实际计算时可用统计频率估计条件概率来估算（式（5））。
I y , x 1 x 2 … x n = lo g 2 N 0 N S 0 S （5）
式中,S为研究区评价单元总面积;N为研究区含有地质灾害分布的地质灾害点总数;S0为研究区内含有影响因子 x 1 x 2 … x n 组合的单元总面积;N0为具有相同因子组合 x 1 x 2 … x n 的特定类别内的地质灾害点总数。则得到式（6）。
I = ∑ i = 1 n I i = ∑ i = 1 n lo g 2 N i N S i S （6）
式中, I 为某评价单元信息量预测值; N i 为影响因子 x i 占有的评价单元中的地质灾害点总数; S i 为含有影响因子 x i 的评价单元的面积。

2.2 基于信息量模型的地质灾害易发性区域评价

本文提出的地质灾害易发性区域信息量模型的评价方法流程如下：
（1）提取地质灾害影响因子;
（2）将收集到的研究区所有地质灾害点随意分为二部分：一部分用于确定评价方法和验证该方法的准确性,另一部分用于评估其可靠性;
（3）根据计算规则计算各类因子的信息量,并进行矢量叠加,生成总信息量图;
（4）依据统计学方法对信息量进行重分类,得到地质灾害易发性评价方法;
（5）利用验证的地质灾害点对评价方法进行 验证。
Fig. 1 Methodology flow chart

图1 地质灾害易发性评价流程

3 涪陵地质灾害易发性区域评价

研究区地处重庆市中东部,居三峡库区腹地,扼长江、乌江交汇要冲,历来有川东南门户之称。地理范围介于 106 ° 5 6 ′ ~ 107 ° 4 3 ′ E , 29 ° 2 1 ′ ~ 30 ° 0 1 ′ N 之间,东西宽74.5 km,南北长70.8 km,幅员面积2941.46 km2（图2）。该区海拔最高1977 m,最低138 m,多在200~800 m之间。地势东南高西北低,地貌以低浅山丘为主。研究区位于中亚热带季风性湿润气候区域,四季分明,热量充足,雨量充沛,主要植被类型为亚热带常绿阔叶林。
Fig. 2 Study area

图2 研究区位置

3.1 地质灾害影响因子的提取计算

根据实地调查及综合分析各影响因子与地质灾害点分布空间位置关系,本文选取坡度、坡向、累积汇水面积、地层岩性、植被（NDVI）、水域、土地利用类型和降雨量8个地质灾害影响因子作为地质灾害易发性评价指标。
地貌是区域地质灾害易发性评价的重要因素,本文选择地貌的坡度和坡向2个因子,利用ArcMap10.2的Slope和Aspect工具以1：5万等高线数据生成坡度和坡向图,用标准差尽量大和符合正态分布2个指标为准则,分别对研究区坡度、坡向进行划分,得到坡度因子图（图3）和坡向因子图（图4）。
Fig. 3 Slope distribution

图3 坡度分布图

Fig. 4. Slope aspect distribution

图4 坡向分布图

累计汇水面积因子图（图5）通过Hydrology工具集,依格网数对其进行重分类得到。
Fig. 5 Cumulative catchment area

图5 累计汇水面积分布图

地层岩性信息从1：5万三峡库区地质图提取,依据涪陵区地质组成,将地层岩性分为14组,得到地层岩性因子图（图6）。
Fig. 6 Formation lithology

图6 地层岩性（地质因子）分布图

由1:2000地形图提取水系单线河和水系双线河,对提取出的水系单线河与水系双线河分布,通过Multiple Ring Buffer工具建立多重缓冲区,得到地表水域因子图（图7）。
Fig. 7 Multiple buffer zones of surface stream and river network

图7 水域缓冲（地表水因子）分布图

土地利用类型图（图8）由2013年12月获得高分一号2 m全色与8 m多光谱融合后分类而成,结合实地调查将研究区域土地利用类型分为7类：耕地、林地、园地、草地、交通运输用地、水域及水利设施用地和城镇村及工矿用地。
Fig. 8 Land use/Land cover map

图8 土地利用分类图

植被因子（图9）的提取基于ENVI 5.1对遥感影像进行归一化处理,用获得的归一化植被指数（Normalized Difference Vegetation Index,NDVI）作为度量植被覆盖的指标。
Fig. 9 Vegetation NDVI distribution map

图9 植被(NDVI)分布

降雨是地质灾害发生的强影响因素,降雨量数据由研究区各雨量站实际监测得到,本文使用的降雨量数据包括影像拍摄当日降雨量数据及拍摄前14日的过程降雨量数据,部分监测站点2013年12月的降雨量信息如表1所示。
Tab. 1 Example of precipitation in Fuling district

表1 涪陵区部分降雨量信息

站点 日降雨 rain5d rain4d rain3d rain2d rain1d
白涛 0 0 0.5 0 0 0
百胜 0 0 0.8 0 0.1 0.1
从林 0 0 1.7 0 0.1 0.5
大木 0.1 0 2.5 0.1 0 0.1
大溪 0 0 1.7 0 0 0.2
对比站 0 0 0 0 0 0
涪陵本站 0 0 1.7 0 0.5 0.4
明家 0.1 0 0.8 0.1 0.5 0.1

注：rain1d,…,rain5d分别表示相对0天前第1-5天日降雨量

3.2 各因子信息量计算及危险性分区

截止2013年底,研究区共有各类潜在地质灾害点和已发生地质灾害点280个,这些地质灾害点中有危岩体9个,变形体49个,塌岸33个,滑坡189个。当地质灾害信息量评价方法确定时,通常将已知地质灾害点分成2个数据集,一个数据集用于确定易发性评价方法,另一个用于验证易发性评价结果。目前,对地质灾害点数据集的分离还没有统一的分离标准,本文将地质灾害点随机分为2个数据集,70%（即约196个地灾点）用于确定评价方法,剩余30%（84个地灾点）用于验证和评估其可靠性。
根据基于信息量模型的地质灾害易发性评价方法,利用ArcMap 10.2分别计算各影响因子的信息量值,影响因子信息量计算如表2,并生成信息量图,对各因子信息量图叠加,得到研究区的综合信息量图。利用统计学自然断点法将综合信息量图,利用ArcMap 10.2的reclassify工具,重新划分为低易发区、较低易发区、易发区、较高易发区和高易发区5个易发性等级,得到地质灾害易发性评价分区图（图10）。
Tab. 2 Example information values for individual triggering factors

表2 影响因子信息量计算表

地质灾害因子 分段 地灾个数（个） 信息量 信息量主要排序
坡度（°） 0~5 18 -1.514609 -
5~10 31 -0.352688 -
10~15 87 0.530870 11
15~20 56 0.667521 8
20~25 4 -1.244959 -
坡向(°) 平坦 5 -2.08588 -
0~30 10 -0.326033 -
30~150 66 0.189856 19
150~200 21 -0.005354 -
200~250 30 0.372565 16
250~310 32 -0.020237 -
310~330 13 0.04228 -
330~360 19 0.357179 17
累积汇水面积
（格网）		 1~2 114 0.100335 21
2~4 31 0.437477 15
4~8 15 -0.550313 -
8~20 21 0.162117 20
>20 15 -0.793704 -
土地利用类型 耕地 76 0.503849 12
林地 61 -7.919041 -
园地 19 1.316537 2
草地 5 -0.589446 -
交通运输用地 2 0.743452 7
水域及水利设施用地 11 0.478293 13
城镇村及工矿用地 22 2.009376 1
离地表水距离
（m）		 0~150 97 1.218703 3
150~250 60 1.187452 4
250~400 21 -0.728606 -
>400 18 -2.39345 -
地层岩性 三叠系中统雷口坡组 0 0 -
三叠系下统嘉陵江组 12 -1.138709 -
三叠系上统须家河组 0 0 -
侏罗系下统珍珠冲组 0 0 -
侏罗系中统新田沟组 0 0 -
二迭系上统 0 0 -
侏罗系上统蓬莱镇组 2 -3.63999 -
侏罗系中统上沙溪庙组 106 0.783518 6
二迭系下统 0 0 -
三叠系下统飞仙关组 0 0 -
志留系下统罗惹坪组 0 0 -
侏罗系上统遂宁组 49 0.797644 5
侏罗系中统下沙溪庙组 22 -0.309074 -
侏罗系中下统自流井组 5 -0.961061 -
植被（NDVI） -1~0 176 0.132877 21
0~0.2 11 -1.164542 -
0.2~0.4 9 0.353476 18
0.4~1.0 0 0 -
降雨量（mm） 0.0~1.0 65 0.568849 10
1.0~2.0 43 0.453245 14
2.0~3.0 80 0.572047 9
>3.0 8 -0.003276 -
Fig. 10 Geological hazard risk distribution map

图10 地质灾害易发性评价分区图

4 区域地质灾害易发性评价结果分析

4.1 结果分析

由影响因子信息量计算表、易发性分区图及各影响因子分布图可知,地质灾害危险性较强的区域有如下特点：
(1)地质灾害主要发生在坡度为5~20o、坡向朝东北和西及地层为侏罗系中统上沙溪庙组和侏罗系中下统自流井组的地区范围内。
(2)大多数地质灾害发生在距离水域150 m范围内,并且越靠近地表水域,地质灾害发生的可能性越高。
(3)土地利用类型为园地、交通运输用地和城镇村及工矿用地的区域较易发生地质灾害,并且这些区域的NDVI主要在0.2-0.4,说明人为活动对地质灾害的影响较大。人类不合理的生产活动造成生态环境破坏,地质环境恶化,导致了地质灾害的发生。
通过对地质灾害易发性分区进行统计,得出易发性等级与地质灾害分布对比表（表3）。高易发区和较高易发区的总面积为934.833 km2,占研究区总面积的31.70%,高易发区和较高易发区地质灾害点个数分别为104和56,占据所有地质灾害点的81.4%。地质灾害点很少分布在中易发区及以下区域,可见,地质灾害点的分布与易发性区划具有很好的区分关系。
Tab. 3 Comparison of risk zones and geological hazards sites

表3 危险性等级分布表

易发性等级 该级别面积(km2) 占研究区面积比(%)(a) 灾害点个数 占灾害点总数比(%)(b) 灾积比（b/a）
低 449.617 15.27 3 1.5 0.09
较低 666.110 22.62 12 6.3 0.27
中 895.299 30.41 21 10.8 0.36
较高 648.251 21.97 56 28.7 1.31
高 286.582 9.73 104 52.7 5.42

4.2 精度评价

地质灾害易发区域评价精度验证有Kappa值和ROC曲线2种方法。由于ROC曲线简单、直观,可准确地反映所用分析方法特异性和敏感性的关系,具有很好的试验准确性,因而广泛应用于地质灾害易发性区域评价[20-22]。
ROC曲线指受试者工作特征曲线/接收器操作特性曲线（receiver operating characteristic curve）,是反映敏感性和特异性连续变量的综合指标。通过将连续变量设定出多个不同的临界值,计算出一系列敏感性和特异性,再以敏感性为纵坐标、1-特异性为横坐标绘制曲线。曲线下面积（AUC）越大,诊断准确性越高。在ROC曲线上,最靠近坐标图左上方的点为敏感性和特异性均较高的临界值。
使用成功率和预测率方法[23],通过将易发性区划分布图与已知地灾点比较,以验证地质灾害易发性预测结果。本文使用SPSS V21软件,将地质灾害样本值和模型模拟值输入进行ROC曲线分析,得到信息量模型的ROC曲线和AUC值。成功率可表明地质灾害分析结果与建模地灾点相符的程度。利用信息量模型获得的成功率曲线如图11(a)所示,其AUC值为0.796,结果表明,所用已知地灾点建立的易发性评价模型具有较高的准确性。预测率可解释地质灾害模型和影响因子预测地质灾害的可靠性。将预测灾害点（84个）与危险性预测图作对比,利用信息量模型得到预测率曲线如图11(b)所示,计算AUC为0.748。结果说明,该地质灾害区域易发性评价模型预测的结果是可靠的,可将其应用于涪陵区的地质灾害易发性评价。
Fig.11 Success-rate ROC curve and prediction-rate ROC curve

图11 成功率ROC曲线和预测率ROC曲线

5 结语

针对涪陵区地形地貌和地质气候特点,选取8个地质灾害影响因子,利用国产遥感数据提取动态影响因子,基于信息量模型,确立地质灾害易发性评价方法,开展了区域地质灾害易发性评价。通过ROC曲线对该评价方法验证,结果表明,该方法可靠,评价结果与实际基本相符,同时说明这种评价方法适合于涪陵区地质灾害易发性的评价。

The authors have declared that no competing interests exist.

参考文献

原文顺序 | 文献年度倒序 | 文中引用次数倒序
[1]
殷坤龙,朱良峰. 滑坡灾害空间区划及GIS应用研究[J].地学前缘,2001,8(2):279-284.滑坡灾害空间区划研究是当前国内外滑坡领域的重要研究方向之一。 虽然滑坡灾害的发生具有随机性的特点，但其发生的区域性和重复性特点则是区域滑坡分布与发生的总体规律。从减灾与土地规划的角度，开展滑坡灾害空间区划研 究具有十分重要的理论和实际意义。文中重点探讨了滑坡灾害空间区划的理论体系、灾害风险评估的基本术语定义及GIS制图的基本原理，采用MAPGIS软件 为平台及其二次开发的滑坡灾害信息分析系统，在中国滑坡重灾害的汉江流域开展了灾害危险性空间区划应用研究。

DOI

[2]
Dieu T B, Biswajeet P, Owe L, et al.Landslide susceptibility assessment in the Hoa Binh province of Vietnam: A comparison of the Levenberg-Marquardt and Bayesian regularized neural networks[J]. Geomorphology, 2012,(171-172):12-29.This study investigates the potential application of artificial neural networks in landslide susceptibility mapping in the Hoa Binh province of Vietnam. A landslide inventory map of the study area was prepared by combining landslide locations investigated through three projects during the last 10 years. Some recent landslide locations were identified based on SPOT satellite images, field surveys, and existing literature. The images have a spatial resolution of 2.5 m. Ten landslide conditioning factors were utilized in the multilayer feed-forward neural network analysis: slope, aspect, relief amplitude, lithology, land use, soil type, rainfall, distance to roads, distance to rivers and distance to faults. Two back-propagation training algorithms, Levenberg-Marquardt and Bayesian regularization, were utilized to determine synoptic weights using a training dataset. Relative importance of each landslide conditioning factor was assessed using the above mentioned synoptic weights. The final connection weights obtained in the training phase were applied to the entire study area to produce landslide susceptibility indexes. The results were then imported to a GIS and landslide susceptibility maps were constructed. Landslide locations not used in the training phase were used to verify and compare the results of the landslide susceptibility maps. Finally, the two landslide susceptibility maps were validated using the prediction-rate method. Subsequently, areas under the prediction curves were assessed. The prediction accuracy of landslide susceptibility maps produced by the Bayesian regularization neural network and the Levenberg-Marquardt neural network were 90.3% and 86.1 % respectively. These results indicate that the two models seem to have good predictive capability. The Bayesian regularization network model appears more robust and efficient than the Levenberg-Marquardt network model for landslide susceptibility mapping.

DOI

[3]
Pradhan B, Lee S.Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models[J]. Environmental Earth Sciences, 2010,60:1037-1054.This paper summarizes findings of landslide hazard analysis on Penang Island, Malaysia, using frequency ratio, logistic regression, and artificial neural network models with the aid of GIS tools and remote sensing data. Landslide locations were identified and an inventory map was constructed by trained geomorphologists using photo-interpretation from archived aerial photographs supported by field surveys. A SPOT 5 satellite pan sharpened image acquired in January 2005 was used for land-cover classification supported by a topographic map. The above digitally processed images were subsequently combined in a GIS with ancillary data, for example topographical (slope, aspect, curvature, drainage), geological (litho types and lineaments), soil types, and normalized difference vegetation index (NDVI) data, and used to construct a spatial database using GIS and image processing. Three landslide hazard maps were constructed on the basis of landslide inventories and thematic layers, using frequency ratio, logistic regression, and artificial neural network models. Further, each thematic layer’s weight was determined by the back-propagation training method and landslide hazard indices were calculated using the trained back-propagation weights. The results of the analysis were verified and compared using the landslide location data and the accuracy observed was 86.41, 89.59, and 83.55% for frequency ratio, logistic regression, and artificial neural network models, respectively. On the basis of the higher percentages of landslide bodies predicted in very highly hazardous and highly hazardous zones, the results obtained by use of the logistic regression model were slightly more accurate than those from the other models used for landslide hazard analysis. The results from the neural network model suggest the effect of topographic slope is the highest and most important factor with weightage value (1.0), which is more than twice that of the other factors, followed by the NDVI (0.52), and then precipitation (0.42). Further, the results revealed that distance from lineament has the lowest weightage, with a value of 0. This shows that in the study area, fault lines and structural features do not contribute much to landslide triggering.

DOI

[4]
Yilmaz I.The effect of the sampling strategies on the landslide susceptibility mapping by conditional probability (CP) and artificial neural networks (ANN)[J]. Environmental Earth Sciences, 2010,60:505-519.This study presented herein compares the effect of the sampling strategies by means of landslide inventory on the landslide susceptibility mapping. The conditional probability (CP) and artificial neural networks (ANN) models were applied in Sebinkarahisar (Giresun–Turkey). Digital elevation model was first constructed using a geographical information system software and parameter maps affecting the slope stability such as geology, faults, drainage system, topographical elevation, slope angle, slope aspect, topographic wetness index, stream power index and normalized difference vegetation index were considered. In the last stage of the analyses, landslide susceptibility maps were produced applying different sampling strategies such as; scarp, seed cell and point. The maps elaborated were then compared by means of their validations. Scarp sampling strategy gave the best results than the point, whereas the scarp and seed cell methods can be evaluated relatively similar. Comparison of the landslide susceptibility maps with known landslide locations indicated that the higher accuracy was obtained for ANN model using the scarp sampling strategy. The results obtained in this study also showed that the CP model can be used as a simple tool in assessment of the landslide susceptibility, because input process, calculations and output process are very simple and can be readily understood.

DOI

[5]
Sdao F, Lioi D S, Pascale S, et al. Landslide susceptibility assessment by using a neuro-fuzzy model: A case study in the Rupestrian heritage rich area of Matera[J]. Natural Hazards and Earth System Sciences, 2013(13):395-407.The complete assessment of landslide susceptibility needs uniformly distributed detailed information on the territory. This information, which is related to the temporal occurrence of landslide phenomena and their causes, is often fragmented and heterogeneous. The present study evaluates the landslide susceptibility map of the Natural Archaeological Park of Matera (Southern Italy) (Sassi and area Rupestrian Churches sites). The assessment of the degree of "spatial hazard" or "susceptibility" was carried out by the spatial prediction regardless of the return time of the events. The evaluation model for the susceptibility presented in this paper is very focused on the use of innovative techniques of artificial intelligence such as Neural Network, Fuzzy Logic and Neuro-fuzzy Network. The method described in this paper is a novel technique based on a neuro-fuzzy system. It is able to train data like neural network and it is able to shape and control uncertain and complex systems like a fuzzy system. This methodology allows us to derive susceptibility maps of the study area. These data are obtained from thematic maps representing the parameters responsible for the instability of the slopes. The parameters used in the analysis are: plan curvature, elevation (DEM), angle and aspect of the slope, lithology, fracture density, kinematic hazard index of planar and wedge sliding and toppling. Moreover, this method is characterized by the network training which uses a training matrix, consisting of input and output training data, which determine the landslide susceptibility. The neuro-fuzzy method was integrated to a sensitivity analysis in order to overcome the uncertainty linked to the used membership functions. The method was compared to the landslide inventory map and was validated by applying three methods: a ROC (Receiver Operating Characteristic) analysis, a confusion matrix and a SCAI method. The developed neuro-fuzzy method showed a good performance in the determination of the landslide susceptibility map.

DOI

[6]
Conforti M, Pascale S, Robustelli G, et al. Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the Turbolo River catchment (northern Calabria, Italy)[J]. Catena, 2014(113):236-250.Landslides are one of the most widespread natural hazards that cause damage to both property and life every year, and therefore, the spatial distribution of the landslide susceptibility is necessary for planning future developmental activities. In this paper the artificial neural network (ANN) technique is tested for developing a landslide susceptibility map in Turbolo River catchment, North Calabria, South Italy. Landslides were mapped through air-photo interpretation and field surveys, by identifying both the landslide depletion zones (DZs) and accumulation zones (AZs); and relevant geo-environmental thematic layers pertaining to landslide predisposing factors were generated using air-photo interpretation, field surveys and Geographic Information System (GIS) tools. Ten predisposing factors were related to the occurrence of landslide: lithology, faults, land use, drainage network, and a series of topographic factors: elevation, slope, aspect, plan curvature, topographic wetness index (TWI) and stream power index (SPI). In order to evaluate and validate landslide susceptibility, the DZs were divided in two groups using a random partition strategy. The first group (training set) was used to prepare the susceptibility map, employing a back-propagation learning algorithm in the Idrisi Taiga software. The second group (testing set) was used to validate the landslide susceptibility model, using the confusion matrix and the receiver operating characteristic (ROC) curve. The susceptibility map was classified into five susceptibility classes: very low, low, moderate, high, and very high. About 46% of the study area falls in high to very high susceptible classes and most of the DZs mapped (87.3%) occur in the same classes. The validation results showed satisfactory agreement between the susceptibility map and the DZs locations; over 85% of the DZs of the validation set are correctly classified falling in high and very high susceptibility areas. Also, the ROC curve had shown an area under curve (AUC) value of 0.90 which demonstrates the robustness and good reliability of the landslide susceptibility model. According to these results, we conclude that the map produced by the artificial neural network is reliable and the methodology applied in the study produced high performance, and satisfactory results, which may be useful for land planning policy.

DOI

[7]
高克昌,崔鹏,赵纯勇,等.基于地理信息系统和信息量模型的滑坡易发性评价——以重庆万州为例[J].岩石力学与工程学报,2006(5):991-996.

[8]
牛全福,程维明,兰恒星,等.基于信息量模型的玉树地震次生地质灾害易发性评价[J].山地学报,2011(9):243-249.

[9]
陈玉,郭华东,王钦军.基于RS与GIS的芦山地震地质灾害敏感性评价[J].科学通报,2013(58):3859-3866.lt;p>北京时间2013年4月20日上午8：02分，四川芦山县发生了7.0级强震，地震发生后中国科学院遥感与数字地球研究所迅速启动重大灾害应急响应，及时对灾情进行评估. 通过0.6 m分辨率航空遥感影像解译的崩滑体分布情况，结合坡度、坡向、高程、岩性、构造、水系、植被覆盖及地震烈度8个评价因子信息，分别基于概率指数模型与信息量模型对地震重灾区芦山县、宝兴县进行了地质灾害敏感性评价. 各因子分析的贡献度排序表明，距离构造350 m以内对地质灾害影响最大，其次为较陡的坡度(40&deg;以上)及距离主干河道较近区域. 采用接收者操作特征(receiver operating characteristic，ROC)曲线对模型精度评价，表明信息量模型具有73.3%的精度，略高于概率指数模型的71.5%，二者的评价结果较吻合，均表明芦山县双石镇、太平镇、宝盛乡、龙门乡及宝兴县五龙乡、民治乡、永富乡等地具有较高的地质灾害敏感性. 评估结果为震后地质灾害隐患点排查，预防二次灾害提供技术支持.</p>

DOI

[10]
王佳佳,殷坤龙,肖莉丽.基于GIS和信息量的滑坡灾害易发性评价——以三峡库区万州区为例[J].岩石力学与工程学报,2014(4):797-808.以滑坡灾害发育较多的三峡库区万州区为研究区，基于指标因素状态分级和因素相关性分析结果，选取坡度、坡向、坡体结构、地层岩性、地质构造、水的作用以及土地利用7项影响因素，以全区700多个滑坡灾害点为样本数据，依据各因素状态下发生的滑坡频率曲线和信息量曲线的突变点为等级划分的临界值来确定因素状态，并在此基础上建立易发性评价指标体系。基于GIS的栅格数据模型，应用信息量理论开展研究区易发性评价，研究结果表明：易发性高和较高的区域主要分布在土地利用总体规划中的建设用地、侏罗系中统上沙溪庙组第二、三段(J2s2，J2s3)、库水变动带和河网影响带以及万州城区。统计结果表明，处在高易发和较高易发区面积为1 210 km2，其中高易发区和较高易发区分别占研究区总面积的9.71%和25.9%，研究区易发性评价精度高达87%。本文完整的论述了县域滑坡灾害易发性评价的理论方法和技术路线，并以三峡库区万州区为例开展滑坡灾害易发性评价、结果分析以及预测精度评价等，为该区域滑坡灾害防治规划与预测预报提供技术支持，为全国范围内县域滑坡灾害易发性评价提供理论指导和技术参考。

[11]
高振记,邬伦,赵兴征.基于GIS的深圳市滑坡危险性区划研究[J].灾害学,2014,29(1):67-74.深圳市在快速城市化过程中形成了大量人工边坡,这些边坡在强降雨及人为活动干扰下具有发生崩 塌和滑坡的潜在危险性,给当地人民群众生命财产安全带来较大威胁。基于深圳市斜坡调查结果,选择地层岩性、地质构造、地形、植被、水文、人类活动5个因子 37个变量,构建了深圳市滑坡危险性区划评价指标体系。基于信息量模型,利用GIS空间分析工具,完成了深圳市滑坡危险性区划工作,并利用野外调查第一手 资料对危险性区划进行了验证。结果表明,深圳市滑坡危险区面积为12.7 km2,占评价总面积的0.67%;较危险区面积为676.9 km2,占评价总面积的35.8%;较稳定区面积为1 040.5 km2,占评价总面积的55%;稳定区面积为160.1 km2,占评价总面积的8.5%。

DOI

[12]
Lee S, Min K.Statistical analysis of landslide susceptibility at Yongin, Korea[J]. Environmental Geology, 2001,40(9):1095-1113.

DOI

[13]
Pradhan B, Youssef A M.Manifestation of remote sensing data and GIS for landslide hazard analysis using spatial-based statistical models[J]. Arabian Journal of Geosciences, 2010,3(3):319-326.This paper presents landslide hazard analysis at Cameron area, Malaysia, using a geographic information system (GIS) and remote sensing data. Landslide locations were identified from interpretation of aerial photographs and field surveys. Topographical and geological data and satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. The factors chosen that influence landslide occurrence are topographic slope, topographic aspect, topographic curvature, and distance to rivers, all from the topographic database; lithology and distance to faults were taken from the geologic database; land cover from TM satellite image; the vegetation index value was taken from Landsat images; and precipitation distribution from meteorological data. Landslide hazard area was analyzed and mapped using the landslide occurrence factors by frequency ratio and bivariate logistic regression models. The results of the analysis were verified using the landslide location data and compared with the probabilistic models. The validation results showed that the frequency ratio model (accuracy is 89.25%) is better in prediction of landslide than bivariate logistic regression (accuracy is 85.73%) model.

DOI

[14]
Bai S, Lv G, Wang J Z, et al. GIS-based rare events logistic regression for landslide-susceptibility mapping of Lianyungang, China[J]. Environmental Earth Sciences, 2011(62):139-149.Landslides have had a huge effect on human life, the environment and local economic development, and therefore they need to be well understood. In this study, we presented an approach for the analysis and modeling of landslide data using rare events logistic regression and applied the approach to an area in Lianyungang, China. Digital orthophotomaps, digital elevation models of the region, geological maps and different GIS layers including settlement, road net and rivers were collected and applied in the analysis. Landslides were identified by monoscopic manual interpretation and validated during the field investigation. To validate the quality of mapping, the data from the study area were divided into a training set and validation set. The result map showed that 4.26% of the study area was identified as having very high susceptibility to landslides, whereas the others were classified as having very low susceptibility (47.2%), low susceptibility (22.21%), medium susceptibility (14.39%) and high susceptibility (11.93%). The quality of the landslide-susceptibility map produced in this paper was validated, and it can be used for planning protective and mitigation measures. The landslide-susceptibility map is a fundamental part of the Lianyungang city landslide risk assessment.

DOI

[15]
Bui D T, Lofman O, Revhaug I, et al.Landslide susceptibility analysis in the Hoa Binh province of Vietnam using statistical index and logistic regression[J]. Natural Hazards 2011,59(3):1413-1444.The purpose of this study is to evaluate and compare the results of applying the statistical index and the logistic regression methods for estimating landslide susceptibility in the Hoa Binh province of Vietnam. In order to do this, first, a landslide inventory map was constructed mainly based on investigated landslide locations from three projects conducted over the last 10 years. In addition, some recent landslide locations were identified from SPOT satellite images, fieldwork, and literature. Secondly, ten influencing factors for landslide occurrence were utilized. The slope gradient map, the slope curvature map, and the slope aspect map were derived from a digital elevation model (DEM) with resolution 20 × 20 m. The DEM was generated from topographic maps at a scale of 1:25,000. The lithology map and the distance to faults map were extracted from Geological and Mineral Resources maps. The soil type and the land use maps were extracted from National Pedology maps and National Land Use Status maps, respectively. Distance to rivers and distance to roads were computed based on river and road networks from topographic maps. In addition, a rainfall map was included in the models. Actual landslide locations were used to verify and to compare the results of landslide susceptibility maps. The accuracy of the results was evaluated by ROC analysis. The area under the curve (AUC) for the statistical index model was 0.946 and for the logistic regression model, 0.950, indicating an almost equal predicting capacity.<br/>

DOI

[16]
邓辉,何政伟,陈晔,等.信息量模型在山地环境地质灾害易发性评价中的应用——以四川泸定县为例[J].自然灾害学报,2014(23):67-76.

[17]
殷坤龙,柳源.滑坡灾害区划系统研究[J].中国地质灾害与防治学报,2000,11(4):28-33.本文系统地介绍了滑坡灾害区划 研究的国内外研究现状 ,提出减灾的关键在于从区域上做好预防研究的观点 ,并阐述了滑坡灾害与风险术语统一化的重要性 ,由此提出滑坡灾害区划的核心是 :灾害、易损性和风险三要素的综合分析。文章进一步提出了灾害区划研究的两种基本途径 ,破坏概率法和信息分析法 ,把传统的滑坡单体稳定性分析延伸到以 Monte- Carlo方法的概率模拟分析 ,在信息论原理的基础上 ,建立了滑坡灾害分区的信息分析系统 ,从而建立了多因素分析的滑坡灾害预测分区方法 ,并结合我国多滑坡的重庆市进行了滑坡灾害预测区划的应用研究。

DOI

[18]
阮沈勇,黄润秋.基于GIS的信息量法模型在地质灾害危险性区划中的应用[J].成都理工学院学报,2001(28):89-92.讨论了将信息量模型与GIS系统结合，进行地质灾害危险性区划的 方法。其基本 思路是充分利用GIS强大的空间图形和属性数据管理功能，实现对地质环境数据的分层次管 理。在此基础上，利用信息量模型开发了基于GIS的空间分析地质灾害危险性区划模块。最 后，以长江三峡库区为典型实例，讨论了GIS与信息量法模型结合及其在地质灾害危险 性区划中的应用。

DOI

[19]
戴悦. 基于信息量模型的三峡库区滑坡区域易发性评价方法研究[D].北京:清华大学,2013.

[20]
Liang J W, Kazuhide S, Shuji M.Landslide susceptibility analysis with logistic regression model based on FCM sampling strategy[J]. Computers & Geosciences, 2013,57:81-92.Several mathematical models are used to predict the spatial distribution characteristics of landslides to mitigate damage caused by landslide disasters. Although some studies have achieved excellent results around the world, few studies take the inter-relationship of the selected points (training points) into account. In this paper, we present the Fuzzy c-means (FCM) algorithm as an optimal method for choosing the appropriate input landslide points as training data. Based on different combinations of the Fuzzy exponent (m) and the number of clusters (c), five groups of sampling points were derived from formal seed cells points and applied to analyze the landslide susceptibility in Mizunami City, Gifu Prefecture, Japan. A logistic regression model is applied to create the models of the relationships between landslide-conditioning factors and landslide occurrence. The pre-existing landslide... more Several mathematical models are used to predict the spatial distribution characteristics of landslides to mitigate damage caused by landslide disasters. Although some studies have achieved excellent results around the world, few studies take the inter-relationship of the selected points (training points) into account. In this paper, we present the Fuzzy c-means (FCM) algorithm as an optimal method for choosing the appropriate input landslide points as training data. Based on different combinations of the Fuzzy exponent (m) and the number of clusters (c), five groups of sampling points were derived from formal seed cells points and applied to analyze the landslide susceptibility in Mizunami City, Gifu Prefecture, Japan. A logistic regression model is applied to create the models of the relationships between landslide-conditioning factors and landslide occurrence. The pre-existing landslide bodies and the area under the relative operative characteristic (ROC) curve were used to evaluate the performance of all the models with different m and c. The results revealed that Model no. 4 (m=1.9, c=4) and Model no. 5 (m=1.9, c=5) have significantly high classification accuracies, i.e., 90.0%. Moreover, over 30% of the landslide bodies were grouped under the very high susceptibility zone. Otherwise, Model no. 4 and Model no. 5 had higher area under the ROC curve (AUC) values, which were 0.78 and 0.79, respectively. Therefore, Model no. 4 and Model no. 5 offer better model results for landslide susceptibility mapping. Maps derived from Model no. 4 and Model no. 5 would offer the local authorities crucial information for city planning and development. less

DOI

[21]
Hamid R P, Majid M, Biswajeet P.Landslide susceptibility mapping using index of entropy and conditional probability models in GIS: Safarood Basin, Iran[J]. Catena, 2012,97:71-84.Landslide susceptibility mapping is essential for land use planning and decision-making especially in the mountainous areas. The main objective of this study is to produce landslide susceptibility maps at Safarood basin, Iran using two statistical models such as an index of entropy and conditional probability and to compare the obtained results. At the first stage, landslide locations were identified in the study area by interpretation of aerial photographs and from field investigations. Of the 153 landslides identified, 105 (≈0270%) locations were used for the landslide susceptibility maps, while the remaining 48 (≈0230%) cases were used for the model validation. The landslide conditioning factors such as slope degree, slope aspect, altitude, lithology, distance to faults, distance to rivers, distance to roads, topographic wetness index (TWI), stream power index (SPI), slope–length (LS), land use, and plan curvature were extracted from the spatial database. Using these factors, landslide susceptibility and weights of each factor were analyzed by index of entropy and conditional probability models. Finally, the ROC (receiver operating characteristic) curves for landslide susceptibility maps were drawn and the areas under the curve (AUC) were calculated. The verification results showed that the index of entropy model (AUC02=0286.08%) performed slightly better than conditional probability (AUC02=0282.75%) model. The produced susceptibility maps can be useful for general land use planning in the Safarood basin, Iran.

DOI

[22]
Omar F A, Biswajeet P, Saro L.Application of an evidential belief function model in landslide susceptibility mapping[J]. Computers & Geosciences, 2012(44):120-135.The objective of this paper is to exploit the potential application of an evidential belief function model to landslide susceptibility mapping at Kuala Lumpur city and surrounding areas using geographic information system (GIS). At first, a landslide inventory map was prepared using aerial photographs, high resolution satellite images and field survey. A total 220 landslides were mapped and an inventory map was prepared. Then the landslide inventory was randomly split into a testing dataset 70% (153 landslides) and remaining 30% (67 landslides) data was used for validation purpose. Fourteen landslide conditioning factors such as slope, aspect, curvature, altitude, surface roughness, lithology, distance from faults, ndvi (normalized difference vegetation index), land cover, distance from drainage, distance from road, spi (stream power index), soil type, precipitation, were used as thematic layers in the analysis. The Dempster&ndash;Shafer theory of evidence model was applied to prepare the landslide susceptibility maps. The validation of the resultant susceptibility maps were performed using receiver operating characteristics (ROC) and area under the curve (AUC). The validation results show that the area under the curve for the evidential belief function (the belief map) model is 0.82 (82%) with prediction accuracy 0.75 (75%). The results of this study indicated that the EBF model can be effectively used in preparation of landslide susceptibility maps.

DOI

[23]
Chung C J F, Fabbri A G. Validation of spatial prediction models for landslide hazard mapping[J]. Natural Hazards, 2003,30(3):451-472.<a name="Abs1"></a>This contribution discusses the problemof providing measures of significance ofprediction results when the predictionswere generated from spatial databases forlandslide hazard mapping. The spatialdatabases usually contain map informationon lithologic units, land-cover units,topographic elevation and derived attributes(slope, aspect, etc.) and the distributionin space and in time of clearly identifiedmass movements. In prediction modelling wetransform the multi-layered databaseinto an aggregation of functional values toobtain an index of propensity of the landto failure. Assuming then that the informationin the database is sufficiently representativeof the typical conditions in which the massmovements originated in space and in time,the problem then, is to confirm the validity ofthe results of some models over otherones, or of particular experiments that seem touse more significant data. A core pointof measuring the significance of a prediction isthat it allows interpreting the results.Without a validation no interpretation is possible,no support of the method or of theinput information can be provided. In particularwith validation, the added value canbe assessed of a prediction either in a fixedtime interval, or in an open-ended time orwithin the confined space of a study area.Validation must be of guidance in datacollection and field practice for landslidehazard mapping.

DOI

Options
文章导航

/

〈 〉