首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 718 毫秒
1.
X. Yao  L.G. Tham  F.C. Dai 《Geomorphology》2008,101(4):572-582
The Support Vector Machine (SVM) is an increasingly popular learning procedure based on statistical learning theory, and involves a training phase in which the model is trained by a training dataset of associated input and target output values. The trained model is then used to evaluate a separate set of testing data. There are two main ideas underlying the SVM for discriminant-type problems. The first is an optimum linear separating hyperplane that separates the data patterns. The second is the use of kernel functions to convert the original non-linear data patterns into the format that is linearly separable in a high-dimensional feature space. In this paper, an overview of the SVM, both one-class and two-class SVM methods, is first presented followed by its use in landslide susceptibility mapping. A study area was selected from the natural terrain of Hong Kong, and slope angle, slope aspect, elevation, profile curvature of slope, lithology, vegetation cover and topographic wetness index (TWI) were used as environmental parameters which influence the occurrence of landslides. One-class and two-class SVM models were trained and then used to map landslide susceptibility respectively. The resulting susceptibility maps obtained by the methods were compared to that obtained by the logistic regression (LR) method. It is concluded that two-class SVM possesses better prediction efficiency than logistic regression and one-class SVM. However, one-class SVM, which only requires failed cases, has an advantage over the other two methods as only “failed” case information is usually available in landslide susceptibility mapping.  相似文献   

2.
During the last decade, slope failures were reported in a 500 km2 study area in the Geba–Werei catchment, northern Ethiopia, a region where landslides were not considered an important hazard before. Field observations, however, revealed that many of the failures were actually reactivations of old deep-seated landslides after land use changes. Therefore, this study was conducted (1) to explore the importance of environmental factors controlling landslide occurrence and (2) to estimate future landslide susceptibility. A landslide inventory map of the study area derived from aerial photograph interpretation and field checks shows the location of 57 landslides and six zones with multiple landslides, mainly complex slides and debris flows. In total 14.8% of the area is affected by an old landslide. For the landslide susceptibility modelling, weights of evidence (WofE), was applied and five different models were produced. After comparison of the models and spatial validation using Receiver Operating Characteristic curves and Kappa values, a model combining data on elevation, hillslope gradient, aspect, geology and distance to faults was selected. This model confirmed our hypothesis that deep-seated landslides are located on hillslopes with a moderate slope gradient (i.e. 5°–13°). The depletion areas are expected on and along the border of plateaus where weathered basalts rich in smectite clays are found, and the landslide debris is expected to accumulate on the Amba Aradam sandstone and upper Antalo limestone. As future landslides are believed to occur on inherently unstable hillslopes similar to those where deep-seated landslides occurred, the classified landslide susceptibility map allows delineating zones where human interventions decreasing slope stability might cause slope failures. The results obtained demonstrate that the applied methodology could be used in similar areas where information on the location of landslides is essential for present-day hazard analysis.  相似文献   

3.
The purpose of this study was to investigate the capabilities of different landslide susceptibility methods by comparing their results statistically and spatially to select the best method that portrays the susceptibility zones for the Ulus district of the Bart?n province (northern Turkey). Susceptibility maps based on spatial regression (SR), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), logistic regression (LR) method, and artificial neural network method (ANN) were generated, and the effect of each geomorphological parameter was determined. The landslide inventory map digitized from previous studies was used as a base map for landslide occurrence. All of the analyses were implemented with respect to landslides classified as rotational, active, and deeper than 5 m. Three different sets of data were used to produce nine explanatory variables (layers). The study area was divided into grids of 90 m × 90 m, and the ‘seed cell’ technique was applied to obtain statistically balanced population distribution over landslide inventory area. The constructed dataset was divided into two datasets as training and test. The initial assessment consisted of multicollinearity of explanatory variables. Empirical information entropy analysis was implemented to quantify the spatial distribution of the outcomes of these methods. Results of the analyses were validated by using success rate curve (SRC) and prediction rate curve (PRC) methods. Additionally, statistical and spatial comparisons of the results were performed to determine the most suitable susceptibility zonation method in this large-scale study area. In accordance with all these comparisons, it is concluded that ANN was the best method to represent landslide susceptibility throughout the study area with an acceptable processing time.  相似文献   

4.
GIS支持下三峡库区秭归县滑坡灾害空间预测   总被引：3，自引：1，他引：2  
彭令  牛瑞卿  陈丽霞 《地理研究》2010,29(10):1889-1898
基于GIS空间分析和统计模型相结合进行区域评价与空间预测是滑坡灾害研究的重要方向之一。以三峡库区秭归县为研究区,选择坡度、坡向、边坡结构、工程岩组、排水系统、土地利用和公路开挖作为评价因子。为提高模型的预测精度、可信度和推广能力,利用窗口采样规则降低训练样本之间的空间相关性。建立Logistic回归模型,对滑坡灾害与评价因子进行定量相关性分析。计算研究区滑坡灾害易发性指数,对其进行聚类分析,绘制滑坡易发性分区图,其中高、中易发区占整个研究区面积的38.9%,主要分布在人类工程活动频繁和靠近排水系统的区域。经过验证,该模型的预测精度达到77.57%。  相似文献   

5.
Terrain attributes such as slope gradient and slope shape, computed from a gridded digital elevation model (DEM), are important input data for landslide susceptibility mapping. Errors in DEM can cause uncertainty in terrain attributes and thus influence landslide susceptibility mapping. Monte Carlo simulations have been used in this article to compare uncertainties due to DEM error in two representative landslide susceptibility mapping approaches: a recently developed expert knowledge and fuzzy logic-based approach to landslide susceptibility mapping (efLandslides), and a logistic regression approach that is representative of multivariate statistical approaches to landslide susceptibility mapping. The study area is located in the middle and upper reaches of the Yangtze River, China, and includes two adjacent areas with similar environmental conditions – one for efLandslides model development (approximately 250 km2) and the other for model extrapolation (approximately 4600 km2). Sequential Gaussian simulation was used to simulate DEM error fields at 25-m resolution with different magnitudes and spatial autocorrelation levels. Nine sets of simulations were generated. Each set included 100 realizations derived from a DEM error field specified by possible combinations of three standard deviation values (1, 7.5, and 15 m) for error magnitude and three range values (0, 60, and 120 m) for spatial autocorrelation. The overall uncertainties of both efLandslides and the logistic regression approach attributable to each model-simulated DEM error were evaluated based on a map of standard deviations of landslide susceptibility realizations. The uncertainty assessment showed that the overall uncertainty in efLandslides was less sensitive to DEM error than that in the logistic regression approach and that the overall uncertainties in both efLandslides and the logistic regression approach for the model-extrapolation area were generally lower than in the model-development area used in this study. Boxplots were produced by associating an independent validation set of 205 observed landslides in the model-extrapolation area with the resulting landslide susceptibility realizations. These boxplots showed that for all simulations, efLandslides produced more reasonable results than logistic regression.  相似文献   

6.
A landslide susceptibility map is proposed for the Pays de Herve (E Belgium), where large landslides affect Cretaceous clay outcrop areas. Based on a Bayesian approach, this GIS-supported probabilistic map identifies the areas most susceptible to deep landslides. The database is comprised of the source areas of ten pre-existing landslides (i.e. a sample of 154 grid cells) and of six environmental data layers, namely lithology, proximity to active faults, slope angle and aspect, elevation and distance to the nearest valley-floor. A 30-m-resolution DEM from the Belgian National Geographical Institute is used for the analysis. Owing to the small size of the sample, a special cross-validation procedure of the susceptibility map is performed, which uses in an iterative way each of the landslides to test the predictive power of the map derived from the other landslides. Four different sets of variables are used to produce four susceptibility maps, whose prediction curves are compared. While the prediction rates associated with the models not involving the “proximity to active fault” criterion are comparable to those of the models considering this variable, strong weaknesses inherent in the fault data on which the latter rely suggest that the final susceptibility map should be based on a model that excludes any reference to fault. This highlights the difference between a triggering factor and determining factors, and in the same time broadens the scope of the produced map. A single reactivated slide is also used to test the possibility of predicting future reactivation of existing landslides in the area. Finally, the need for geomorphological control over the mathematical treatment is underlined in order to obtain realistic prediction maps.  相似文献   

7.
A landslide-hazard map is intended to show the location of future slope instability. Most spatial models of the hazard lack reliability tests of the procedures and predictions for estimating the probabilities of future landslides, thus precluding use of the maps for probabilistic risk analysis. To correct this deficiency we propose a systematic procedure comprising two analytical steps: “relative-hazard mapping” and “empirical probability estimation”. A mathematical model first generates a prediction map by dividing an area into “prediction” classes according to the relative likelihood of occurrence of future landslides, conditional by local geomorphic and topographic characteristics. The second stage estimates empirically the probability of landslide occurrence in each prediction class, by applying a cross-validation technique. Cross-validation, a “blind test” here using non-overlapping spatial or temporal subsets of mapped landslides, evaluates accuracy of the prediction and from the resulting statistics estimates occurrence probabilities of future landslides. This quantitative approach, exemplified by several experiments in an area near Lisbon, Portugal, can accommodate any subsequent analysis of landslide risk.  相似文献   

8.
GIS and ANN model for landslide susceptibility mapping   总被引：1，自引：0，他引：1  
XU Zeng-wang 《地理学报》2001,11(3):374-381
Landslide hazard is as the probability of occurrence of a potentially damaging landslide phenomenon within specified period of time and within a given area. The susceptibility map provides the relative spatial probability of landslides occurrence. A study is presented of the application of GIS and artificial neural network model to landslide susceptibility mapping, with particular reference to landslides on natural terrain in this paper. The method has been applied to Lantau Island, the largest outlying island within the territory of Hong Kong. A three-level neural network model was constructed and trained by the back-propagate algorithm in the geographical database of the study area. The data in the database includes digital elevation modal and its derivatives, landslides distribution and their attributes, superficial geological maps, vegetation cover, the raingauges distribution and their 14 years 5-minute observation. Based on field inspection and analysis of correlation between terrain variables and landslides frequency, lithology, vegetation cover, slope gradient, slope aspect, slope curvature, elevation, the characteristic value, the rainstorms corresponding to the landslide, and distance to drainage line are considered to be related to landslide susceptibility in this study. The artificial neural network is then coupled with the ArcView3.2 GIS software to produce the landslide susceptibility map, which classifies the susceptibility into three levels: low, moderate, and high. The results from this study indicate that GIS coupled with artificial neural network model is a flexible and powerful approach to identify the spatial probability of hazards.  相似文献   

9.
GIS and ANN model for landslide susceptibility mapping   总被引：4，自引：0，他引：4  
1 IntroductionThe population growth and the expansion of settlements and life-lines over hazardous areas exert increasingly great impact of natural disasters both in the developed and developing countries. In many countries, the economic losses and casualties due to landslides are greater than commonly recognized and generate a yearly loss of property larger than that from any other natural disasters, including earthquakes, floods and windstorms. Landslides in mountainous terrain often occur a…  相似文献   

10.
Steep terrain and high a frequency of tropical rainstorms make landslide occurrence on natural terrain a common phenomenon in Hong Kong. This paper reports on the use of a Geographical Information Systems (GIS) database, compiled primarily from existing digital maps and aerial photographs, to describe the physical characteristics of landslides and the statistical relations of landslide frequency with the physical parameters contributing to the initiation of landslides on Lantau Island in Hong Kong. The horizontal travel length and the angle of reach, defined as the angle of the line connecting the head of the landslide source to the distal margin of the displaced mass, are used to describe runout behavior of landslide mass. For all landslides studied, the horizontal travel length of landslide mass ranges from 5 to 785 m, with a mean value of 43 m, and the average angle of reach is 27.7°. This GIS database is then used to obtain a logistic multiple regression model for predicting slope instability. It is indicated that slope gradient, lithology, elevation, slope aspect, and land-use are statistically significant in predicting slope instability, while slope morphology and proximity to drainage lines are not important and thus excluded from the model. This model is then imported back into the GIS to produce a map of predicted slope instability. The results of this study demonstrate that slope instability can be effectively modeled by using GIS technology and logistic multiple regression analysis.  相似文献   

11.
This work has evaluated the probability of earthquake-triggered landslide occurrence in the whole of El Salvador, with a Geographic Information System (GIS) and a logistic regression model. Slope gradient, elevation, aspect, mean annual precipitation, lithology, land use, and terrain roughness are the predictor variables used to determine the dependent variable of occurrence or non-occurrence of landslides within an individual grid cell. The results illustrate the importance of terrain roughness and soil type as key factors within the model — using only these two variables the analysis returned a significance level of 89.4%. The results obtained from the model within the GIS were then used to produce a map of relative landslide susceptibility.  相似文献   

12.
Comparing landslide inventory maps   总被引：10，自引：1，他引：9  
Landslide inventory maps are effective and easily understandable products for both experts, such as geomorphologists, and for non experts, including decision-makers, planners, and civil defense managers. Landslide inventories are essential to understand the evolution of landscapes, and to ascertain landslide susceptibility and hazard. Despite landslide maps being compiled every year in the word at different scales, limited efforts are made to critically compare landslide maps prepared using different techniques or by different investigators. Based on the experience gained in 20 years of landslide mapping in Italy, and on the limited literature on landslide inventory assessment, we propose a general framework for the quantitative comparison of landslide inventory maps. To test the proposed framework we exploit three inventory maps. The first map is a reconnaissance landslide inventory prepared for the Umbria region, in central Italy. The second map is a detailed geomorphological landslide map, also prepared for the Umbria region. The third map is a multi-temporal landslide inventory compiled for the Collazzone area, in central Umbria. Results of the experiment allow for establishing how well the individual inventories describe the location, type and abundance of landslides, to what extent the landslide maps can be used to determine the frequency-area statistics of the slope failures, and the significance of the inventory maps as predictors of landslide susceptibility. We further use the results obtained in the Collazzone area to estimate the quality and completeness of the two regional landslide inventory maps, and to outline general advantages and limitations of the techniques used to complete the inventories.  相似文献   

13.
基于数字高程模型(DEM)计算得到的坡度、坡向等地形属性是滑坡危险性评价模型的重要输入数据, DEM误差会导致地形属性计算结果不确定性, 进而影响滑坡危险性评价模型的结果。本文选择基于专家知识的滑坡危险性评价模型和逻辑斯第回归模型, 采用蒙特卡洛模拟方法, 研究DEM误差所导致的滑坡危险性评价模型结果不确定性。研究区位于长江中上游的重庆开县, 采用5 m分辨率的DEM, 以序贯高斯模拟方法模拟了不同大小(误差标准差为1 m、7.5 m、15 m)和空间自相关性(变程为0 m、30 m、60 m、120 m)的12 类DEM误差场参与滑坡危险性评价。每次模拟包括100 个实现, 通过对每次模拟分别计算滑坡危险性评价结果的标准差图层和分类一致性百分比图层, 用以评价结果不确定性。评价结果表明, 在不同的DEM精度下, 两个滑坡危险性评价模型所得结果的总体不确定性随空间自相关程度的变化趋势并不相同。当DEM空间自相关性程度不同时, 基于专家知识的滑坡危险性评价模型的评价结果总体不确定随着DEM误差增加而呈现不同的变化趋势, 而逻辑斯第回归模型的评价结果总体不确定性随着DEM误差大小增加而单调增加。从评价结果总体不确定性角度而言, 总体上逻辑斯第回归模型比基于专家知识的滑坡危险性评价模型更加依赖于DEM数据质量。  相似文献   

14.
次生滑坡灾害的影响是震后较长时间里人们持续关注的焦点,对其开展敏感性评价具有重要意义。选取5.12地震的重灾区汶川县北部作为研究区,利用遥感与地理信息技术提取地震滑坡信息,在全面分析滑坡与高程、坡度、坡向、岩性、断裂带、地震烈度以及水系等7个影响因子相关特性的基础上,采用信息量法与逻辑回归模型进行灾害敏感性评价,将研究区划分为极轻度、轻度、中度、高度和极高危险5个级别,并对不同模型的适用性开展分析和对比。结果表明,逻辑回归模型在描述区域滑坡灾害危险度总体特征方面稍具优势。  相似文献   

15.
基于专家知识的滑坡危险性模糊评估方法   总被引：6，自引：0，他引：6  
滑坡发生的影响因素众多, 其危险性与各因素之间的关系多呈非线性关系, 同时各因素之 间也存在或强或弱的相关性, 而目前的危险性评价方法难以体现这些要求。本文提出了一种借助 滑坡专家知识并利用模糊推理理论进行滑坡危险性评价的方法。该方法通过建立了①坡度与岩 层倾角之差和坡向与岩层倾向之差、②坡度和岩性、③临空面和岩性、④坡形和岩性等四种环境 因子组合, 以此将不同环境因子之间的相关性融入各组合模型中, 并将四种组合所得的模糊危险 度进行叠加用于滑坡危险度的模糊评价。环境组合模型中的参数利用专家经验给出。将该方法应 用于三峡库区云阳- 巫山段, 得到了滑坡危险性的分级分布图。从滑坡危险性分布图上可清楚发 现, 本方法所计算出的危险性值在滑坡发生的地区明显高于未发生滑坡的地区, 该结果可以用于 城镇建设和重要基础规划设施的参考。  相似文献   

16.
斜坡类型描述岩层产状与斜坡的角度关系,很大程度上决定了斜坡岩土体变形的方式和强度,对地质灾害分布具有重要作用。斜坡的顺向坡、反向坡与地形的阳坡、阴坡概念相似,可以利用改进的太阳辐射地形因子计算模型(TOBIA指数)对斜坡类型进行定量化表达。计算TOBIA指数需要斜坡坡度、坡向、岩层倾角、倾向4个参数。以三峡库区顺向坡基岩滑坡多发地段青干河流域为例,通过区域地质图上产状点获取离散岩层倾角和倾向数值,经空间插值得到空间连续分布的倾角和倾向参数;通过数字高程模型获取坡度和坡向参数,得到区内TOBIA指数分布。在此基础上进一步研究指数和滑坡发育关系。结果表明,TOBIA指数值与区内斜坡类型密切相关,根据TOBIA指数值能很好地区分斜坡类型。以二分类变量逻辑回归模型对坡度和指数两个变量进行分析,发现引入TOBIA指数后,回归模型对已知滑坡拟合度由55%提高到71.5%,能有效提高区域滑坡灾害危险性区划结果精度。  相似文献   

17.
Landslide hazard mapping is a fundamental tool for disaster management activities in mountainous terrains. The main purpose of this study is to evaluate the predictive power of weights-of-evidence modelling in landslide hazard assessment in the Lesser Himalaya of Nepal. The modelling was performed within a geographical information system (GIS), to derive a landslide hazard map of the south-western marginal hills of the Kathmandu Valley. Thematic maps representing various factors (e.g., slope, aspect, relief, flow accumulation, distance to drainage, soil depth, engineering soil type, landuse, geology, distance to road and extreme one-day rainfall) that are related to landslide activity were generated, using field data and GIS techniques, at a scale of 1:10,000. Landslide events of the 1970s, 1980s, and 1990s were used to assess the Bayesian probability of landslides in each cell unit with respect to the causative factors. To assess the accuracy of the resulting landslide hazard map, it was correlated with a map of landslides triggered by the 2002 extreme rainfall events. The accuracy of the map was evaluated by various techniques, including the area under the curve, success rate and prediction rate. The resulting landslide hazard value calculated from the old landslide data showed a prediction accuracy of > 80%. The analysis suggests that geomorphological and human-related factors play significant roles in determining the probability value, while geological factors play only minor roles. Finally, after the rectification of the landslide hazard values of the new landslides using those of the old landslides, a landslide hazard map with > 88% prediction accuracy was prepared. The methodology appears to have extensive applicability to the Lesser Himalaya of Nepal, with the limitation that the model's performance is contingent on the availability of data from past landslides.  相似文献   

18.
This study attempts to reconstruct the history of the Collinabos landslide, a landslide with a fresh morphology that is representative for more than 150 dormant, deep-seated (> 3 m) landslides in the Flemish Ardennes (Belgium). A geomorphological map was created based on LIDAR (Light Detection and Ranging)-derived maps and detailed field surveys. The map showed that the landslide consisted of three zones with significant differences in surface topography. The northern landslide zone 1 is characterised by at least five reverse slopes, whereas zones 2 and 3, the southern landslide zones, have only two reverse slopes and a convex foot. Electric resistivity profiles measured in zones 1 and 2 revealed that the differences in surface topography were not related to differences in internal structure as both parts of the landslide were initiated as a rotational earth slide with a surface of rupture at 15 m deep, where the displaced material broke apart in two blocks. However, two shear surfaces of reactivations within landslide debris were only distinguished in the accumulation area of zone 1. The observed differences in surface morphology can be caused by a temporary conversion of a forest into cropland in zone 2. It is suggested that reverse slopes of smaller reactivations within landslide debris were obliterated during the agricultural activities. AMS radiocarbon dating of organic material found in ponds located in reverse slopes generally resulted in relatively recent dates (i.e. 1400–1950 Cal AD) suggesting that several of the small local reactivations occurred in that period. One dating at 8700–8440 Cal BP of organic matter collected in a reverse slope in zone 1 suggests that an initiation under periglacial conditions cannot be excluded for the Collinabos landslide. By combining different technologies, this study provides valuable information for a better understanding of dormant landslides.  相似文献   

19.
GIS支持下的黄土高原地震滑坡区划研究   总被引：20，自引：4，他引：16  
分析了影响黄土滑坡的各项影响因子,利用层次分析法(AHP)确定各影响因子的权重。在GIS支持下,建立包括各因子图的空间数据库,对各因子进行分级赋值,然后进行因子加权叠加分析,完成三种超越概率下(50年超越概率2%、10%和63.5%)黄土高原地震滑坡区划图。黄土地震滑坡灾害最严重地区一个是宁夏南部及与其相邻的甘肃白银地区,另一个是甘肃天水地区。  相似文献   

20.
在GIS技术的支持下,以三峡库区忠县-石柱河段为研究区域(面积260.9km2,滑坡分布面积5.3km2),建立了地质、地形数据库等滑坡因子空间数据库和滑坡空间分布数据库(数据比例尺均为1∶10万);在进行滑坡影响因子敏感性分析的基础上;对双变量分析模型进行了改进应用,对滑坡影响定量因子采用滑坡种子网格数据驱动的分级新方法。在GIS系统中进行了滑坡危险度评价成果图制图,将评价结果分为很低、低、中等、高、很高5个等级,依次占研究区域19.9%、31.69%、27.95%、17.1%和3.6%。评价结果显示危险性高和很高的区域主要分布在长江两岸,这与实际的滑坡分布吻合。研究结果对在三峡库区推广应用、防灾减灾具有实际指导意义。  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号