基于灰色关联度模型的区域滑坡敏感性评价

数理统计和机器学习模型如支持向量机(support vector machine,SVM)等,在区域滑坡敏感性评价中得到广泛的应用.但这些模型的建模过程往往较复杂,如在对机器学习进行训练和测试时难以选取合理的非滑坡栅格单元,而且有较多的模型参数需要确定.为提高滑坡敏感性评价建模的效率和精度,提出基于灰色关联度的敏感性评价模型.灰色关联度模型能有效计算各比较样本与参考样本之间的定量的关联度,具有建模过程简洁和评价精度高的优点,该模型目前在区域滑坡敏感性评价中的应用还没有引起研究人员的足够关注且有待进一步拓展.拟将灰色关联度模型用于浙江省飞云江流域南田—雅梅图幅(南田地区)的滑坡敏感性评价,并将得到的评价结果与SVM模型的敏感性评价结果作对比分析.结果显示,灰色关联度模型在高和极高敏感区的滑坡预测精度优于SVM模型,而在中等敏感区的滑坡预测精度略低于SVM模型;整体而言,灰色关联度模型对整个南田地区滑坡敏感性分布的预测精度略高于SVM模型.对两个模型建模过程的对比结果显示,灰色关联度模型建模较简单,具有比SVM模型更高的建模效率,为滑坡敏感性评价提供了一种新思路.     

基于粗糙集的支持向量机滑坡易发性评价

区域滑坡易发性评价对灾害中长期预测预报具有重要意义。以三峡库区秭归至巴东段为研究区,利用粗糙集理论对20个初始评价因子进行属性约简,去掉冗余或干扰信息,得到13个核心评价因子,并以此作为支持向量机的输入特征集,构建支持向量机模型,实现滑坡易发性评价。在易发性分区图中高易发区占8.2%,主要分布在童庄河右岸、归州河沿岸、青干河左岸、树坪至范家坪长江右岸、牛口到东壤口长江左岸和巴东附近;不易发区占 52.7%,主要分布于店子湾至巴东旧城以及远离长江水系及植被覆盖度高的区域。通过验证与分析,粗糙集-支持向量机模型在高中易发区中的预测精度为85.6%,其预测能力优于支持向量机模型;与野外调查对比,预测结果与实际情况吻合较好。研究表明,应用粗糙集和支持向量机相结合进行滑坡易发性评价具有预测能力强、计算效率高等优点。     

Support Vector Machines for Landslide Susceptibility Mapping: The Staffora River Basin Case Study, Italy

The aim of this study is the application of support vector machines (SVM) to landslide susceptibility mapping. SVM are a set of machine learning methods in which model capacity matches data complexity. The research is based on a conceptual framework targeted to apply and test all the procedural steps for landslide susceptibility modeling from model selection, to investigation of predictive variables, from empirical cross-validation of results, to analysis of predicted patterns. SVM were successfully applied and the final susceptibility map was interpreted via success and prediction rate curves and receiver operating characteristic (ROC) curves, to support the modeling results and assess the robustness of the model. SVM appeared to be very specific learners, able to discriminate between the informative input and random noise. About 78% of occurrences was identified within the 20% of the most susceptible study area for the cross-validation set. Then the final susceptibility map was compared with other maps, addressed by different statistical approaches, commonly used in susceptibility mapping, such as logistic regression, linear discriminant analysis, and naive Bayes classifier. The SVM procedure was found feasible and able to outperform other techniques in terms of accuracy and generalization capacity. The over-performance of SVM against the other techniques was around 18% for the cross-validation set, considering the 20% of the most susceptible area. Moreover, by analyzing receiver operating characteristic (ROC) curves, SVM appeared to be less prone to false positives than the other models. The study was applied in the Staffora river basin (Lombardy, Northern Italy), an area of about 275 km² characterized by a very high density of landslides, mainly superficial slope failures triggered by intense rainfall events.     

The Application of Artificial Neural Networks to Landslide Susceptibility Mapping at Janghung, Korea

The purpose of this study was to develop techniques for landslide susceptibility using artificial neural networks and then to apply these to the selected study area at Janghung in Korea. Landslide locations were identified from interpretation of satellite images and field survey data, and a spatial database of the topography, soil, forest, and land use. Thirteen landslide-related factors were extracted from the spatial database. These factors were then used with an artificial neural network to analyze landslide susceptibility. Each factor's weight was determined by the back-propagation training method. Five different training sets were applied to analyze and verify the effect of training. Then the landslide susceptibility indices were calculated using the back-propagation weights, and susceptibility maps were constructed from Geographic Information System (GIS) data for the five cases. Landslide locations were used to verify results of the landslide susceptibility maps and to compare them. The artificial neural network proved to be an effective tool for analyzing landslide susceptibility.     

雷达数据辅助下的滑坡易发性评价

岩土体含水量对滑坡,尤其是土质滑坡的稳定性具有极大的影响。本文以三峡库区秭归段内土质滑坡作为研究对象,利用Sentinel-1雷达数据反演地表岩土体含水量来替代传统的湿度指数因子,在保持其他因子不变的情况下,构建二元逻辑回归模型进行滑坡易发性评价。结果表明,利用成功率曲线对结果进行分析,采用岩土体含水量因子时预测精度达到80.2%,高于采用地形湿度指数的77.2%。利用雷达数据反演得到的岩土体含水量代替地形湿度指数进行滑坡易发性评价精度较高、预测能力较强。     

Validation of Spatial Prediction Models for Landslide Hazard Mapping

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.     

Methodology for Landslide Susceptibility Mapping by Means of a GIS. Application to the Contraviesa Area (Granada,Spain)

This article presents a method to map landslide susceptibility in rock massifs using Geographical Information Systems (GIS). The method is based on making an inventory of rupture zones of different types of slope movements and then analysing the bivariate correlation of these with the factors that determine instability. After determining the factors that present the highest correlation with each type of movement, a matrix is created to combine these factors and to determine the percentage of the rupture zone in each combination, which provides an expression of the susceptibility of the terrain. The map thus obtained is divided into susceptibility classes. The susceptibility maps (made in 1995) for each type of movement are first calibrated with the inventory of the movements from which they are derived (previous to 1995), and subsequently validated by another inventory elaborated after the susceptibility maps (in 1997). In both cases, significant correlation coefficients were obtained (the Goodman–Kruskal coefficients were over 0.8 and sometimes exceeded 0.9). The relative error (degree of accumulated fit for very low to low susceptibility classes) was always less than 5%,while the relative success rate was always above 50%. These resultsillustrate the adequacy of the method and of the maps obtained.     

A GIS-Based Multivariate Statistical Analysis for Shallow Landslide Susceptibility Mapping in La Pobla de Lillet Area (Eastern Pyrenees,Spain)

This paper presents a GIS-aided procedure for shallow landslide susceptibility mapping at a regional scale. Most of the input data for the susceptibility assessment have been captured automatically. A total of 13 parameters, related to the slope geometry, have been derived from the digital elevation model (DEM) while vegetation cover and thickness of superficial formations have been obtained from photointerpretation and field work. The susceptibility assessment is based on multivariate statistical techniques (discriminant analysis), which hasbeen tested in a pilot area in La Pobla de Lillet (Eastern Pyreenes, Spain). Theresults obtained using a random sample show that 82% of all the cells, and 90% of cells including slope failures, have been properly classified. A susceptibility map based on the discriminant function has given consistent results. The susceptibilityassessment is very sensitive to the parameters selected. Compared to thetraditional methods, the main advantage of the GIS-aided procedure is the rapidityprovided by the automatic capture of parameters. It also has the capability of coveringlarge areas, and the objectivity and reproducibility of the results. The main drawbackis that, at present, not all regions have DEM accurate enough to cope with small landslides.     

Landslide Susceptibility Mapping Using Fuzzy Logic System and Its Influences on Mainlines in Lashgarak Region,Tehran, Iran

Landslide susceptibility mapping is among the useful tools applied in disaster management and planning development activities in mountainous areas. The susceptibility maps prepared in this research provide valuable information for landslide hazard management in Lashgarak region of Tehran. This study was conducted to, first, prepare landslide susceptibility maps for Lashgarak region and evaluate landslide effect on mainlines and, second, to analyze the main factors affecting landslide hazard increase in the study area in order to propose efficient strategies for landslide hazard mitigation. A GIS-based multi-criteria decision analysis model (fuzzy logic) is used in the present work for scientific evaluation of landslide susceptible areas in Lashgarak region. To this end, ArcGIS, PCIGeomatica, and IDIRISI software packages were used. Eight information layers were selected for information analysis: ground strength class, slope angle, terrain roughness, normalized difference moisture index, normalized difference vegetation index, distance from fault, distance from the river, and distance from the road. Next, eight different scenarios were created to determine landslide susceptibility of the study area using different operators (intersection (AND), union (OR), algebraic sum (SUM), multiplication (PRODUCT), and different fuzzy gamma values) of fuzzy overlay approach. After that, the performance of various fuzzy operators in landslide susceptibility mapping was empirically compared. The results revealed the excellent consistency of landslide susceptibility map prepared using the fuzzy union (OR) operator with landslide distribution map in the study area. Eventually, the accuracy of landslide susceptibility map prepared using the fuzzy union (OR) operator was evaluated using the frequency ratio diagram. The results showed that frequency values of the landslides gradually increase from “low susceptibility” to high “susceptibility” as 88.34% of the landslides are categorized into two “high” and “very high” susceptibility classes, implying the satisfactory consistency between the landslide susceptibility map prepared using fuzzy union (OR) operator and landslide distribution map.     

Landslide Susceptibility Mapping: An Integrated Approach using Geographic Information Value,Remote Sensing,and Weight of Evidence Method

Geotechnical and Geological Engineering - Landslide events cause significant financial losses, human casualties, and irreversible changes in the natural landscape. In this paper, we have addressed...     

Use of Geomorphological Information in Indirect Landslide Susceptibility Assessment

The objective of this paper is to evaluate the importance of geomorphological expert knowledge in the generation of landslide susceptibility maps, using GIS supported indirect bivariate statistical analysis. For a test area in the Alpago region in Italy a dataset was generated at scale 1:5,000. Detailed geomorphological maps were generated, with legends at different levels of complexity. Other factor maps, that were considered relevant for the assessment of landslide susceptibility, were also collected, such as lithology, structural geology, surficial materials, slope classes, land use, distance from streams, roads and houses. The weights of evidence method was used to generate statistically derived weights for all classes of the factor maps. On the basis of these weights, the most relevant maps were selected for the combination into landslide susceptibility maps. Six different combinations of factor maps were evaluated, with varying geomorphological input. Success rates were used to classify the weight maps into three qualitative landslide susceptibility classes. The resulting six maps were compared with a direct susceptibility map, which was made by direct assignment of susceptibility classes in the field. The analysis indicated that the use of detailed geomorphological information in the bivariate statistical analysis raised the overall accuracy of the final susceptibility map considerably. However, even with the use of a detailed geomorphological factor map, the difference with the separately prepared direct susceptibility map is still significant, due to the generalisations that are inherent to the bivariate statistical analysis technique.     

基于GIS与WOE-BP模型的滑坡易发性评价

区域滑坡易发性研究对地质灾害风险管理具有重要意义.以往研究中,将多元统计模型与机器学习方法相结合用于滑坡易发性评价的研究较少.以三峡库区万州区为例,首先选取9种指标因子（坡度、坡向、剖面曲率、地表纹理、地层岩性、斜坡结构、地质构造、水系分布及土地利用类型）作为滑坡易发性评价指标.基于证据权模型（weights of evidence,WOE）计算得到的对比度和滑坡面积比与分级面积比的相对大小,对各指标因子进行状态分级;再利用粒子群法优化的BP神经网络模型（PSO-BP）得到各指标因子权重.综合两种模型确定的状态分级权重和指标因子权重（WOE-BP）计算滑坡易发性指数（landslide susceptibility index,LSI）,基于GIS平台得到全区滑坡易发性分区图.结果表明:水系、地层岩性和地质构造是影响万州区滑坡发育的主要指标因子;WOE-BP模型的预测精度为80.8%,优于WOE模型的73.1%和BP神经网络模型的71.6%,可为定量计算指标因子权重和优化滑坡易发性评价提供有效途径.      

不同组合模型区域滑坡易发性及精度分析

为探索区域滑坡易发性评价模型的适用性和评价结果的合理性,以滑坡灾害高发的白龙江流域为研究区,首先选取坡度、地形起伏度、距断层距离、地层岩性、流域沟壑密度、植被指数等6项影响滑坡发生的孕灾因子作为易发性的评价指标,以研究区2 093处滑坡灾害点为样本数据,依据各指标条件下的信息量值、确定性系数值和证据权重值曲线突变规律,并结合滑坡面积及分级面积频率比曲线作为等级划分的临界值来确定因子分级状态;其次,基于指标因子状态分级和相关性分析结果,采用信息量法、确定性系数法、证据权法分别与逻辑回归组合的3种模型开展区域滑坡灾害易发性评价,并从模型结果、适用性和精度等方面采用多手段对3种组合模型进行比较和讨论。研究结果表明：在区域滑坡易发性评价方面,3组模型均表现较为理想,信息量和逻辑回归组合模型的预测精度为94.6%,其预测精度和准确性优于其他2种组合模型。笔者以白龙江流域中游及其岷江支流段为例,开展滑坡灾害易发性评价模型适用性、评价结果分析以及预测精度评价对比和研究等,成果可为该区地质灾害防灾减灾和国土空间用途管制规划决策提供参考。     

Landslide HotSpot Mapping by means of Persistent Scatterer Interferometry

Landslide detection and mapping represent fundamental requirements for every hazard and risk evaluation and consequent improvement of the management strategies for such natural hazards. Optical and radar remote sensing can be used to observe landslide-induced ground deformation, ranging from regional to local scales. This work presents a methodology called Landslide HotSpot Mapping; this approach integrates cartographic, thematic and optical data with Persistent Scatterer Interferometry for the identification of extremely slow to very slow moving landslides, and for the evaluation of their state of activity and intensity. This methodology scans wide areas to detect hotspots, which are narrow unstable zones characterized by higher landslide hazard. To these hotspots, priority has to be given when planning field surveys and in situ validation campaigns, so that field work time and effort can be optimized and significantly reduced. The approach is tested in Central Calabria, over a 4,470?km² area located in southern Italy. ENVISAT ascending images acquired between 2003 and 2009 and processed with the Persistent Scatterer Pairs (PSP) technique are used to analyse deformation patterns. Combining conventional photo-interpretation with the analysis of PSP data, 64 new landslides are identified and the spatial (boundaries) and temporal (activity) information of 980 pre-mapped phenomena (23.6% of updated inventory) are updated. 1,012 active (continuous or reactivated) landslides are identified and 4 hotspot areas selected: San Fili, Rende, Lago, Catanzaro. Urgent field checks have to be organized for these hotspots to validate the satellite-based observations and to design appropriate mitigation measures to reduce impacts on the elements at risk.     

基于金矿规格单元数据的机器学习方法在成矿建模分析中的应用

现代金矿勘察主要是通过综合地球化学和地质测量等数字化方法对深部矿床进行研究,所需要的人力物力成本较高。而通过分析积累的金矿规格单元数据,可以建立金矿成矿情况与相关成矿元素含量之间的非线性关系,从已有的勘查数据中寻找金矿成矿的一般规律。本文基于与金矿相关的成矿元素含量数据,分别采用逻辑斯蒂回归、随机森林和决策树方法对原始数据和重采样数据进行训练,综合运用召回率、精确率和准确率对模型进行评价。通过对比发现,在训练和测试原始数据过程中,由于每组之间数据量的巨大差距,导致成矿数据被淹没;而在训练重采样数据过程中,随机森林在召回率和准确率方面均有较好的表现,分别达到了90.63%和70.78%;并最终分析了随机森林模型中不同分类边界对于金矿成矿情况预测结果的影响。利用不同的测量指标对模型进行评价分析,使模型更适用于金矿成矿预测,可有效地提高金矿勘察的效率。     

Landslide Susceptibility Mapping Using GIS-based Fuzzy Logic and the Analytical Hierarchical Processes Approach: A Case Study in Constantine (North-East Algeria)

The main purpose of this study was to compare and evaluate the performance of two multicriteria models for landslide susceptibility assessment in Constantine, north-east of Algeria. The landslide susceptibility maps were produced using the analytic hierarchy process (AHP) and Fuzzy AHP (FAHP) via twelve landslides conditioning factors, including the slope gradient, lithology, land cover, distance from drainage network, distance from the roads, distance from faults, topographic wetness index, stream power index, slope curvature, Normalized Difference Vegetation Index, slope aspect and elevation. In this study, the mentioned models were used to derive the weighting value of the conditioning factors. For the validation process of these models, the receiver operating characteristic analysis, and the area under the curve (AUC) were applied by comparing the obtained results to The landslide inventory map which prepared using the archives of scientific publications, reports of local authorities, and field survey as well as analyzing satellite imagery. According to the AUC values, the FAHP model had the highest value (0.908) followed by the AHP model (0.777). As a result, the FAHP model is more consistent and accurate than the AHP in this case study. The outcome of this paper may be useful for landslide susceptibility assessment and land use management.

     

滑坡治理方法及其应用实例

对目前国内外滑坡治理方法进行总结综述，例举了滑坡治理的几个实例，指出了滑坡治理的优先考虑方法。     

不同模型的滑坡易发性评价精度讨论

为探讨不同滑坡易发性评价模型其评价结果的差异和评价精度,本文以贵州省桐梓县为研究区,选取坡度、斜坡结构、地形起伏度、工程地质岩组、距水系距离、距断层距离6个影响因子建立评价指标体系,分别采用信息量模型、确定性系数法、频率比法3种方法开展区域地质灾害易发性评价,并通过ROC曲线对评价结果进行精度验证。评价结果表明:信息量模型(AUC=0800)的评价精度优于确定性系数法(AUC=0784)和频率比法(AUC=0787),因此信息量模型更适合于该区域的滑坡易发性评价。