共查询到20条相似文献，搜索用时 140 毫秒
1.
基于SVM多类分类的滑坡区域危险性评价方法研究 总被引：6，自引：0，他引：6
近年来，随着新理论、新技术得发展，提出了许多新模型和方法应用于滑坡区域危险性评价中。支持向量机（support vector machine，SVM）是新一代的学习算法，已有前人利用SVM应用于滑坡灾害预测中。然而大多只是利用了SVM的两分类算法，得到的结果只有稳定不稳定两种．这对滑坡区域评价来说是远远不够的。本文尝试利用SVM的多类分类算法进行滑坡危险性区域评价，取得了较好的结果。 相似文献
2.
区域滑坡危险性评价是进行区域滑坡风险性研究的基础.由于滑坡演变机制的复杂性,使得目前基于独立分析各因素对滑坡影响的“白箱”型评价模式具有一定风险性,同时这类评价方法要求对滑坡演变和研究区地质地理背景进行非常细致的监测和调查.为了克服这些问题,文章提出了一种基于Kriging插值理论的“黑箱”型评价方法.在利用该方法对历史滑坡点的规模进行评价的基础上,利用Kriging插值法获取研究区的滑坡危险性区划,并以四川省苍溪县为例,验证了运用该方法进行区域滑坡危险性评价的可行性. 相似文献
3.
王涛等基于简化Newmark位移模型的区域地震滑坡危险性快速评估以汶川MS8.0级地震为例一文的地震滑坡危险性快速评价结果与2008年汶川地震触发实际滑坡空间分布的相关性较低。本文试图通过对该文中基础数据、分析处理过程、研究结果的分析与讨论,找出这种相关性较低的原因。结果表明值得针对王涛等文章中的Arias烈度分布数据的准确性、工程地质岩组的划分情况、汶川地震滑坡危险性评价结果的客观性共三个方面开展更深入的分析与研究。本文对探索与发掘更客观的地震滑坡危险性评价模型起到了积极的作用。 相似文献
4.
应用概率地震危险性评价模型进行地震滑坡危险性区划,是解决潜在地震诱发滑坡危险性评价中震源不确定性与诱发滑坡时空不确定性的有效方法.通过理论分析,结合鲁甸地震区的实际情况,对基于力学原理的Newmark滑块位移模型与概率地震滑坡危险性分析方法中的参数的不确定性问题进行了分析,将斜坡岩土体地震作用下的强度衰减效应、地震加速度地形放大效应、断层破碎带效应融合到了斜坡累积位移计算模型中,进行了模型计算参数的优化.改进后的分析模型,更好地反映了高陡斜坡地形与断层破碎带对地震滑坡灾害发育的控制作用,在鲁甸地震区域滑坡应用中,优化模型中的滑坡失稳极高风险区与实际地震滑坡分布表现出了较好的一致性,在超越概率2%的滑坡失稳概率分布中,鲁甸地区包谷垴—小河断裂、鲁甸—昭通断裂带及牛栏江河谷地带地震滑坡高—极高风险区分布面积增幅十分显著.因此,在Newmark滑块位移模型中考虑地震动参数与岩土参数动态响应规律与变量间的定量关系,对于提高区域斜坡稳定性分析的可靠性具有重要意义. 相似文献
5.
地质滑坡对人员和经济形成了巨大威胁,因此,区域地质滑坡危险性评价变得极其重要.为了将滑坡带来的损失降到最低,这里以芦山县作为研究区,分析研究区内地质环境的滑坡成因等相关特征,选择12种滑坡因子作为其滑坡危险性评价指标,采用AHP层次分析法确定滑坡因子权重,使用基于径向基核函数的支持向量机模型和信息量模型,对芦山区域进行... 相似文献
6.
区域地质灾害评价是减灾防治的重要非工程手段,构建区域滑坡危险性评价模型,对提高地质灾害评价精度和防治效率具有重要意义。文章以滑坡频发的大渡河中游地区为研究区,初选高程、坡度、坡向、地震动参数、土壤类型、工程地质岩组、年平均降雨量和地形湿度指数（TWI）等13个因子,建立滑坡危险性初级评价指标体系。考虑各因子对滑坡形成贡献程度的不同和目前常权栅格叠加方式对滑坡危险性评价结果精度的影响,引入了地理探测器和变权栅格叠加,构建了地理探测器、信息量法和变权栅格叠加的组合模型（GDIV模型）。基于2021年四川省1∶50 000地质灾害风险调查中313处滑坡地质灾害隐患点,开展基于GDIV模型的大渡河中游地区滑坡危险性评价,并与逻辑回归模型和信息量模型的组合模型（LRI模型）评价结果进行对比分析。结果表明：研究区以中危险及以下危险区为主,占总面积的78.3%,极高和高危险区主要分布在大渡河、革什扎河和东谷河两岸的低海拔地区;与LRI模型相比,基于GDIV模型的评价结果精度更高,其受试者工作特征（ROC）曲线的线下面积（AUC）值为0.917。文章提出的GDIV模型提高了区域滑坡危险性评价精度,可为... 相似文献
7.
综合统计模型和物理模型的地质灾害精细评估——以福建省龙山社区为例 总被引：1，自引：0，他引：1
地质灾害易发性和危险性评价对象相同但评价内容有差异,即两者表达地质灾害的时间、空间和强度信息各有不同。本文将崩塌滑坡易发性中的统计模型和危险性评价中的物理模型进行结合,综合统计模型客观预测空间位置信息的优点以及物理模型模拟包含地质灾害发生机制的优势,弥补了区域统计模型无法预测灾害强度信息的不足,也对物理模型模拟的空间位置进行了有效的控制和修正,进而完成区域崩塌滑坡的易发性和危险性等级综合分析,实现对区域崩塌滑坡潜在高风险位置的精细评估。本文以福建省福鼎市龙山社区为例,利用野外获取的高清影像、地形、钻孔和地质灾害等数据,通过综合统计模型评价和物理模型危险性评估,完成潜在高风险位置的精细化分析。研究结果表明:需要进行重点排查治理的区域约占社区附近山体总面积的26.92%;研究区域内需要进行集中排查与治理的区域有5个,其中3个区域需要进行重点治理,其潜在高风险区域与野外地质灾害调查区域隐患点吻合;5个高风险区域直接对180幢左右楼房（约360余户居民）的安全构成威胁,该评估将野外调研中划定的大范围高风险区域精细化处理,并验证了该评价方法体系的可行性。该评价方法体系为区域崩塌滑坡地质灾害精细化排查和治理提供了工作思路和指导。 相似文献
8.
我国滑坡灾害分布范围广,危害严重。区域滑坡危险性评价一直都是滑坡灾害防灾减灾的重要内容之一。近年来,随着大数据和人工智能技术的飞速发展,机器学习技术逐渐在滑坡灾害危险性评价方面得到广泛应用,并取得了较好效果。在大量研读文献的基础上,系统阐述了基于机器学习技术的滑坡危险性评价方法研究现状。综述从评价因子选择与量化归一化、数据清洗与样本集构建、模型选取与训练评价等三个关键环节对现有研究成果进行分析评述,最后对机器学习滑坡危险性评价方法的发展趋势提出讨论意见。 相似文献
9.
滑坡危险性评价是滑坡灾害防治和管理的重要依据。文章基于层次分析法和随机森林模型,结合距离函数法,探索性地提出了一种新的组合赋权法（RF-AHP）。采用RF-AHP对青海省贵德县北部山区滑坡进行了危险性评价,对比探讨了AHP、RF和RF-AHP三种模型评价结果与实际滑坡灾害的吻合性,结果表明:（1）RF-AHP在高危险区和极高危险区面积占比38.38%的情况下,包括了60.13%的滑坡灾害,结果准确性相比AHP和RF两种模型有较大提升;（2）随着危险性等级的逐步提高,RF-AHP区划结果中相应分区的灾害实际发生的比率也随之增高,并对三种方法出现结果差异的客观原因进行了分析讨论,证明RF-AHP适用于滑坡危险性评价工作。 相似文献
10.
《中国地质灾害与防治学报》2021,(4)
我国滑坡灾害分布范围广,危害严重。区域滑坡危险性评价一直都是滑坡灾害防灾减灾的重要内容之一。近年来,随着大数据和人工智能技术的飞速发展,机器学习技术逐渐在滑坡灾害危险性评价方面得到广泛应用,并取得了较好效果。在大量研读文献的基础上,系统阐述了基于机器学习技术的滑坡危险性评价方法研究现状。综述从评价因子选择与量化归一化、数据清洗与样本集构建、模型选取与训练评价等三个关键环节对现有研究成果进行分析评述,最后对机器学习滑坡危险性评价方法的发展趋势提出讨论意见。 相似文献
11.
Alireza Mostafizi Haizhong Wang Dan Cox Lori A. Cramer Shangjia Dong 《Natural Hazards》2017,85(3):1347-1362
The constant threat from landslides in the northeastern part of Istria, Croatia, calls for the need to apply accurate and reliable methods in landslide hazard assessment in order to prevent landslide damage and to set an early warning system if necessary. Furthermore, landslide susceptibility and hazard assessment enable optimal area management and regional urban planning. The study area is in the northeastern and central part of the Istrian Peninsula, well known as an area of frequent, small and shallow slope instability phenomena. Landslide susceptibility assessment in the area around the city of Buzet was performed using a deterministic landslide susceptibility model in the LS-RAPID software. LS-RAPID was developed to analyze stability at one single location, but the performed analysis has shown that LS-RAPID can be used as a powerful tool in landslide susceptibility and hazard assessment on regional scale. The objective of this paper is to establish the influence of the runout potential on the enlargement of the landslide-susceptible zones, due to expansion of the failure area around the initial failure zone. Performed analysis of rainfall return periods shows the frequency of landslide occurrence and provides the possible correlation with the time component of landslide hazard in the area. 相似文献
12.
地震滑坡危险性概念和基于力学模型的评估方法探讨 总被引：1，自引：0，他引：1
在我国大陆地区运用基于力学模型的Newmark位移分析方法开展地震滑坡危险性定量评估,尚处在起步阶段.为了进一步明确地震滑坡危险性概念和改进推广基于力学模型的评估方法,首先阐明了狭义的地震滑坡危险性预测评估与震后反演评估的关系; 同时为了应对地震应急、震后重建及潜在地震条件下的不同评估需求,初步提出了广义的地震滑坡危险性评估框架.随后申述了基于Newmark位移分析的地震滑坡危险性评估方法的理论基础、方法分类及最新进展,并以汶川地震滑坡危险性快速评估为例,剖析了目前影响评估有效性的不确定性及空间数据质量等问题,指出了基于力学模型的地震滑坡危险性评估方法的改进方向.建议开展潜在地震及其诱发滑坡危险性的耦合评估,建立适用于我国大陆地区地震滑坡位移分析的经验模型,以便为国家层面的地震滑坡危险性区划服务. 相似文献
13.
秦岭中部太白县地质灾害发育特征及危险性评估 总被引：2，自引：0，他引：2
以陕西省太白县为例,分析了秦岭中部山区地质灾害形成的地质环境条件,重点指出在植被茂密山区,异常强降雨及农耕、建房、修路和矿山开采4种人类工程活动对地质灾害的关键诱发作用。对崩塌、滑坡、泥石流和不稳定斜坡4类典型地质灾害进行了亚类细分和发育特征分析,并总结指出了地质灾害区域宏观分布特征。筛选了9种关键的地质灾害影响和诱发因素,基于将集中调查区指示的地质灾害发育规律,外推应用于全区地质灾害评估的思路,利用信息量模型对太白县全区进行了地质灾害危险性定量评估,结果显示高危险区主要集中分布在县域北部人口聚居的盆地区,以及南部河流与公路沿线地段。定量检验显示,危险性评估结果与地质灾害的实际分布十分吻合,表明基于信息量模型的地质灾害危险性评估方法能够很好地适用于秦岭腹地山区。 相似文献
14.
Dalia Bach Kirschbaum Robert Adler Yang Hong Sujay Kumar Christa Peters-Lidard Arthur Lerner-Lam 《Environmental Earth Sciences》2012,66(6):1683-1696
The increasing availability of remotely sensed data offers a new opportunity to address landslide hazard assessment at larger
spatial scales. A prototype global satellite-based landslide hazard algorithm has been developed to identify areas that may
experience landslide activity. This system combines a calculation of static landslide susceptibility with satellite-derived
rainfall estimates and uses a threshold approach to generate a set of ‘nowcasts’ that classify potentially hazardous areas.
A recent evaluation of this algorithm framework found that while this tool represents an important first step in larger-scale
near real-time landslide hazard assessment efforts, it requires several modifications before it can be fully realized as an
operational tool. This study draws upon a prior work’s recommendations to develop a new approach for considering landslide
susceptibility and hazard at the regional scale. This case study calculates a regional susceptibility map using remotely sensed
and in situ information and a database of landslides triggered by Hurricane Mitch in 1998 over four countries in Central America.
The susceptibility map is evaluated with a regional rainfall intensity–duration triggering threshold and results are compared
with the global algorithm framework for the same event. Evaluation of this regional system suggests that this empirically
based approach provides one plausible way to approach some of the data and resolution issues identified in the global assessment.
The presented methodology is straightforward to implement, improves upon the global approach, and allows for results to be
transferable between regions. The results also highlight several remaining challenges, including the empirical nature of the
algorithm framework and adequate information for algorithm validation. Conclusions suggest that integrating additional triggering
factors such as soil moisture may help to improve algorithm performance accuracy. The regional algorithm scenario represents
an important step forward in advancing regional and global-scale landslide hazard assessment. 相似文献
15.
滑坡危险性评价是滑坡灾害防治的重要前提和基础,简单高效的评价方式是其中的一个研究重点。本文以四川安县作为研究区域,基于ArcGIS中的分析功能,引入可视化的建模工具Modelbuilder,以模型的方式演示和运行整个滑坡危险性评价过程,得到了滑坡危险性的分级图,并进行对比分析。实验结果表明,利用可视化建模方式完成复杂地区的滑坡危险性评价,能够简化操作流程,节约时间和精力。 相似文献
16.
一种基于贝叶斯理论的区域斜坡稳定性评价模型 总被引：1，自引：0，他引：1
本文结合滑坡物理模型和统计模型的优点,针对小流域滑坡稳定性分析,建立了一种基于贝叶斯理论的区域斜坡稳定性评价模型。该模型主要采用灾害自身信息来修正原始模型中的参数,解决了区域稳定性评价中参数难以确定的问题。该方法首先设定模型的初始参数分布,然后利用采样点雨前和雨后稳定性不同的信息建立验证方程,再根据马尔科夫链蒙特卡罗模拟和贝叶斯方法确定最终的参数分布,进而得出区域稳定性分布。应用该模型对福建省蔡源小流域的6 13滑坡群发性事件进行分析。结果显示,蔡源小流域地区的无量纲黏聚系数C为0.028,有效摩擦角为16.7,土壤的导水系数T和降雨量q的比值为529.026m,可能不稳定地区和不稳定地区达到76.0%。该模型利用历史灾害数据自动模拟出合适的参数,对区域滑坡稳定性评价具有重要意义。 相似文献
17.
地质灾害危险性评价是防灾减灾工作的重要依据。本文以汶川县城周边64 km2为例,应用遥感信息提取技术与GIS空间分析方法,根据IKONOS遥感图像和地形图及野外调查资料,提取了崩塌和滑坡易发性评价因子,采用信息量法确定了因子分值,计算了崩塌和滑坡易发性,并分别提出崩塌和滑坡的危险性计算方法,形成了汶川地区崩塌和滑坡危险性分区图。研究结果表明:新的崩塌和滑坡危险性评价方法能够反映区内地质灾害危险程度,该方法可行,结果合理,这为中、大比例尺区域范围内地质灾害危险性研究提供了有益的思路。 相似文献
18.
A new probabilistic methodology for landslide hazard assessment in regional scale using Copula modeling technique is presented. The current probabilistic landslide hazard analyses are performed under the assumption that landslide hazard elements, such as magnitude, frequency, and location, are independent. In this paper, a general approach is proposed to consider the possible dependence among hazard elements. Part of the Seattle, WA area was selected to evaluate the competence of the presented method. A total of 357 slope failure events and their corresponding topography and geology data were included in the study to develop and test the model. Based on the results, the mean success rates of the presented model in predicting landslide occurrence are 90 % in hazardous area and 12 % in safe locations on average, while these success rates are 63 and 44 % when these hazard elements were treated as mutually independent. 相似文献
19.
Regional assessment of landslide impact in the Three Gorges area, China, using ASTER data: Wushan-Zigui 总被引：1，自引：0，他引：1
This paper is focussed on the hazard impact of landslides in the Three Gorges, and represents the progression of our ongoing
study on regional land instability assessment in the Three Gorges area using imagery data from the Advanced Spaceborne Thermal
Emission Radiometer (ASTER). The key development here is the establishment of a model that integrates land instability with
several factors that can relate hazard to human life, such as slope failures occurring in proximity to built-up areas and
roads, and areas of high landslide risk along the bank of Yangtze and its major tributaries. The method correctly identifies
some of the known destructive landslides in the region, like Qianjiangping and Huangtupo, as belonging to areas of potentially
high landslide impact. Our results suggest that several population centres, including the towns of Wushan and Badong, are
rated at high landslide hazard levels. This study highlights the importance of differentiating between landslide types within
susceptibility assessment, and identifies those locations in the Three Gorges where the probability of landslide occurrence
with negative impact to life and property is greatest. 相似文献
20.
For the socio-economic development of a country, the highway network plays a pivotal role. It has therefore become an imperative to have landslide hazard assessment along these roads to provide safety. The current study presents landslide hazard zonation maps, based on the information value method and frequency ratio method using GIS on 1:50,000 scale by generating the information about the landslide influencing factors. The study was carried out in the year 2017 on a part of Ravi river catchment along one of the landslide-prone Chamba to Bharmour road corridor of NH-154A in Himachal Pradesh, India. A number of landslide triggering geo-environmental factors like “slope, aspect, relative relief, soil, curvature, Land Use and Land Cover (LULC), lithology, drainage density, and lineament density” were selected for landslide hazard mapping based on landslide inventory. The landslide inventory has been developed using satellite imagery, Google earth and by doing exhaustive field surveys. A digital elevation model was used to generate slope gradient, slope aspect, curvature, and relative relief map of the study area. The other information, i.e., soil maps, geological maps, and toposheets, have been collected from various departments. The landslide hazard zonation map was categorized namely “very high hazard, high hazard, medium hazard, low hazard, and very low hazard.” The results from these two methods have been validated using area under curve (AUC) method. It has been found that hazard zonation map prepared using frequency ratio model had a prediction rate of 75.37% while map prepared using information value method had prediction rate of 78.87%. Hence, on the basis of prediction rate, the landslide hazard zonation map, obtained using information value method, was experienced to be more suitable for the study area. 相似文献