共查询到18条相似文献，搜索用时 607 毫秒
1.
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. 相似文献
2.
《西北地质》2021,(2)
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。 相似文献
3.
滑坡易发性评价是滑坡灾害管理的基础工作,也是制定各项防灾减灾措施的重要依据。针对传统的信息量模型在评价过程中确定权重值存在准确性不高的缺点,文章提出RBF神经网络和信息量耦合模型。以甘肃省岷县为研究区,筛选坡度等9个指标因子构建了滑坡灾害易发性评价指标体系,应用RBF神经网络-信息量耦合模型（RBFNN-I）进行滑坡灾害易发性评价,利用合理性检验和ROC曲线对模型的评价结果进行精度检验。结果表明:（1）RBFNN-I模型的AUC值为0.853,相比单一的RBFNN和I模型分别提高了6.3%和9.7%,说明RBFNN-I模型具有更好的评价精度;（2）岷县滑坡灾害的极高易发区和高易发区主要分布在临潭—宕昌断裂带、洮河及其支流、闾井河和蒲麻河两侧河谷地带,距断层距离、降雨量、距道路距离和NDVI是影响岷县滑坡灾害分布的主控因子。 相似文献
4.
赣南地区滑坡灾害点多、面广、规模小,具有群发性和突发性的特点,90%以上的滑坡是因人工切坡导致的。为研究赣南地区小型削方滑坡对易发性评价模型的适用性,以赣州市于都县银坑镇为例,基于野外地质调查成果,并利用地理探测器,选取坡度、坡体结构、岩组、断层、道路、植被等6个评价指标,分别选用信息量模型、人工神经网络模型、决策树模型和逻辑回归模型开展易发性评价。结果表明:信息量、人工神经网络、决策树和逻辑回归等模型得到的AUC值分别为0.800、0.708、0.672和0.586,信息量模型所得的易发性结果与研究区滑坡实际分布情况较吻合,高易发区和中易发区滑坡占比近80%。信息量模型较其他三个模型,更适合于赣南地区小型削方滑坡易发性评价,评价结果对该地区地质灾害易发性评价模型选取提供了参考与借鉴。 相似文献
5.
滑坡灾害易发性评价研究对规划灾害区域、制定防灾策略等方面具有十分重要的意义。以滑坡灾害频发的汶川及周边两县（理县和茂县）为例,提出滑坡灾害易发性评价的快速聚类-信息量模型。选取坡度、高程、坡向、距构造的距离、距水系的距离、地层岩性和土地利用情况为对滑坡有重要影响的7个影响因子,并在二级因子的分类上,对上述前5个影响因子依据159处滑坡样本分别开展快速聚类分析,同时也给出了传统的等距分类法,以便与快速聚类方法形成对比,对后2个影响因子则以定性方法分类。根据上述二级分类方法的不同,以及滑坡样本是否考虑面积因素,将信息量模型细分为四类（模型a:快速聚类-数量模型、模型b:等距分类-数量模型、模型c:快速聚类-面积模型、模型d:等距分类-面积模型）,分别计算各二级指标信息量,并通过ArcGIS空间叠加分析得到研究区域信息量分布,然后通过自然断点法将研究区滑坡易发性划分为五个等级。以易发性递增原则和线下面积（Area Under Curve,AUC）作为精度评价指标,结果表明:①快速聚类模型（模型a和模型c）整体效果优于等距分类模型（模型b和模型d）;②相同分类方法下,面积模型（模型c与模型d）整体优于数量模型（模型a和模型b）;③在上述两项优势的加持下,模型c相较于模型b,评价精度明显提升,其AUC值从80.46%提高到87.25%。 相似文献
6.
《地质科技情报》2020,(3)
巴东县城由于其特殊的地理位置和特有的地质条件,使之成为滑坡灾害多发地带,严重威胁着巴东县城的发展,因此,有必要对巴东县城进行滑坡易发性评价研究。首先,基于GIS平台分别提取影响滑坡发生发育的各指标因子(地层岩性、地形地貌、地质构造、水文地质条件等),并划分证据层;其次,采用证据权法分别计算各证据层的权重及后验概率;然后将单元各证据层后验概率进行叠加,生成滑坡易发性分区图;最后,使用自然断点法将研究区按滑坡易发程度分为极高易发区、高易发区、中易发区、低易发区与极低易发区5类,极高易发区与高易发区面积之和约占研究区总面积的33%,其中86%的已有滑坡发生在极高易发区和高易发区,利用成功率曲线检验表明区划效果较好。 相似文献
7.
基于多模型的滑坡易发性评价以甘肃岷县地震滑坡为例 总被引：1，自引：0，他引：1
2013年7月22日,甘肃省岷县漳县交界处发生了MS6.6级地震(岷县地震),本文以这次地震烈度Ⅷ度区为研究区,根据地震前后遥感影像解译出来的2330个地震滑坡数据,以坡度、坡向、水系、岩性和断层为因子图层,分别应用模糊逻辑法,信息量模型及Shannon熵改进的信息量模型,对研究区的地震滑坡易发性进行评价。结果表明: 1滑坡的高易发性地区位于研究区的中间部分,以及水系0～50m这一缓冲区范围内,离水系越近滑坡易发性等级越高; 2应用ROC曲线对3个模型的易发性评价结果进行比较,信息量模型和Shannon熵改进的信息量模型的AUC值分别为0.8488, 0.8502; 模糊逻辑模型的AUC值为0.7640,表明前两个模型的表现较好,而模糊逻辑模型相对来说表现一般; 3通过对比3个模型中各等级易发性所占的面积比例和各等级易发性中滑坡数目占总数比例,表明Shannon熵改进后的模型更适用于灾害风险评价以及应急风险管理等实际应用。 相似文献
8.
基于斜坡单元与信息量法结合的宝塔区黄土滑坡易发性评价 总被引：4，自引：0，他引：4
滑坡易发性评价对滑坡灾害的防治与管理具有重要意义。为了评价延安宝塔区黄土滑坡易发性,以斜坡为基本评价单元,选取斜坡坡度、坡高、坡向、坡形、斜坡结构类型、植被和人类工程活动7个指标作为评价因子,在Arc GIS平台下,利用信息量模型对研究区的黄土滑坡进行易发性分区评价。评价结果表明,宝塔区滑坡高易发区面积1092.39km~2,占全区面积的30.81%,主要分布于宝塔区的中部及北部地区,低易发区集中于宝塔区南部汾川河流域。以斜坡作为评价单元提高了与实际地形地貌的吻合度。应用信息量模型进行滑坡易发性评价具有较高的预测精度,已有滑坡点落在很高易发区和高易发区中的比例为95.7%,较真实地反映了客观实际。 相似文献
9.
滑坡易发性定量评估是预测滑坡发生空间概率的重要手段,基于统计分析原理的评估方法目前在国内外应用最为广泛,且不同评估方法的对比研究逐渐成为热点。以青海沙塘川流域黄土梁峁区为例,剖析了信息量模型和逻辑回归模型在滑坡易发性评估中的优越性和局限性,并探索提出基于二者的耦合模型。考虑坡度、坡向、起伏度、岩性、与干流距离、与支流距离和植被指数等7个影响因素,对比分析了基于信息量、逻辑回归及二者耦合模型的滑坡易发性评估的技术流程及结果。3种模型的成功率分别为:耦合模型成功率(78. 9%)>信息量模型成功率(71. 8%)>逻辑回归模型成功率(70. 8%)。在沙塘川流域黄土滑坡的易发性评估中,信息量和逻辑回归模型的表现基本相当,但信息量-逻辑回归耦合模型的成功率明显提升。该研究结果可为黄土高原区滑坡易发性定量评估提供借鉴。 相似文献
10.
我国目前滑坡易发性评价研究主要集中在西南地区,对东南部降雨引发特别是梅雨引发的滑坡研究较少.选取浙江省西北部梅雨控制区淳安县为研究区,通过遥感解译结合野外详细调查,共确定滑坡596处,并建立滑坡编录数据库.选取高程、坡向、坡度、曲率、工程岩组、断层、道路、建设用地、植被等9个滑坡影响因子,基于GIS栅格分析方法,采用人工神经网络(ANN)、logistic回归和信息量3种评价模型,分别对32种不同影响因子组合进行滑坡易发性对比评价,得到滑坡易发性指数图.应用评价曲线下面积AUC(area under curve)对评价结果进行检验,ANN、logistic回归和信息量3种模型的正确率分别是93.75%、89.76%和90.06%;采用淳安县2014年梅汛期发生的13处滑坡作为预测样本,3种模型预测率分别是94.75%、94.33%和77.21%.上述分析结果表明:ANN模型优于其他两者.以ANN模型评价结果指数图为基础进行易发性分区,采用滑坡强度指标进行分区结果检验,滑坡强度值由易发性低、较低、中和高依次递增,说明分区结果合理.研究成果可以为浙西降雨型滑坡特别是由梅雨引发滑坡的易发性评价提供参考. 相似文献
11.
Landslide susceptibility zonation mapping using logistic regression and its validation in Hashtchin Region,northwest of Iran 总被引：1，自引：0，他引：1
Reza Talaei 《Journal of the Geological Society of India》2014,84(1):68-86
Landslide susceptibility zonation mapping assists researchers greatly to understand the spatial distribution of slope failure probability in a region. Being extremely useful in reducing landslide hazards, such maps could simply be produced using both qualitative and quantitative methods. In the present study, a multivariate statistical method called ‘logistic regression’ was used to assess landslide susceptibility in Hashtchin region, situated in west of Alborz Mountainsnorthwest of Iran. In this study, two independent variables, categorical (predictor) and continuous, were drawn on together in the model. To identify the region’s landslides use was made of aerial photographs, field studies and topographic maps. To prepare the database of factors affecting the region’s landslides and to determine landslide zones, geographic information system (GIS) was used. Using such information, landslide susceptibility modeling was accomplished. The data related to factors causing landslides were extracted as independent variables in each cell (in 50 m×50 m cells). Then, the whole data were input into the SPSS, Version 18. The prepared database was later analyzed using logistic regression, the forward stepwise method and based on maximum likelihood estimation. Regression equation was determined using obtained constants and coefficients and the landslide susceptibility of the area in grid-cells (pixels) was computed between 0 and 0.9954. The Receiver Operating Characteristic (ROC) curve was used to assess the accuracy of the logistic regression model. The predicting ability of the model was 84.1% given the area under ROC curve. Finally, the degree of success of landslide susceptibility zonation mapping was estimated to be 79%. 相似文献
12.
Kaixiang Zhang Xueling Wu Ruiqing Niu Ke Yang Lingran Zhao 《Environmental Earth Sciences》2017,76(11):405
Landslide susceptibility mapping is an indispensable prerequisite for landslide prevention and reduction. At present, research into landslide susceptibility mapping has begun to combine machine learning with remote sensing and geographic information system (GIS) techniques. The random forest model is a new integrated classification method, but its application to landslide susceptibility mapping remains limited. Landslides represent a serious threat to the lives and property of people living in the Zigui–Badong area in the Three Gorges region of China, as well as to the operation of the Three Gorges Reservoir. However, the geological structure of this region is complex, involving steep mountains and deep valleys. The purpose of the current study is to produce a landslide susceptibility map of the Zigui–Badong area using a random forest model, multisource data, GIS, and remote sensing data. In total, 300 pre-existing landslide locations were obtained from a landslide inventory map. These landslides were identified using visual interpretation of high-resolution remote sensing images, topographic and geologic data, and extensive field surveys. The occurrence of landslides is closely related to a series of environmental parameters. Topographic, geologic, Landsat-8 image, raining data, and seismic data were used as the primary data sources to extract the geo-environmental factors influencing landslides. Thirty-four layers of causative factors were prepared as predictor variables, which can mainly be categorized as topographic, geological, hydrological, land cover, and environmental trigger parameters. The random forest method is an ensemble classification technique that extends diversity among the classification trees by resampling the data with replacement and randomly changing the predictive variable sets during the different tree induction processes. A random forest model was adopted to calculate the quantitative relationships between the landslide-conditioning factors and the landslide inventory map and then generate a landslide susceptibility map. The analytical results were compared with known landslide locations in terms of area under the receiver operating characteristic curve. The random forest model has an area ratio of 86.10%. In contrast to the random forest (whole factors, WF), random forest (12 major factors, 12F), decision tree (WF), decision tree (12F), the final result shows that random forest (12F) has a higher prediction accuracy. Meanwhile, the random forest models have higher prediction accuracy than the decision tree model. Subsequently, the landslide susceptibility map was classified into five classes (very low, low, moderate, high, and very high). The results demonstrate that the random forest model achieved a reasonable accuracy in landslide susceptibility mapping. The landslide hazard zone information will be useful for general development planning and landslide risk management. 相似文献
13.
Prabin Kayastha 《Arabian Journal of Geosciences》2015,8(10):8601-8613
For assessing landslide susceptibility, the spatial distribution of landslides in the field is essential. The landslide inventory map is prepared on the basis of historical information of individual landslide events from different sources such as previously published reports, satellite imageries, aerial photographs and interview with local inhabitants. Then, the distribution of landslides in the study area is verified with field surveys. However, the selection of contributing factors for modelling landslide susceptibility is an inhibit task. The previous studies show that the factors are chosen as per availability of data. This paper documents the landslide susceptibility mapping in the Garuwa sub-basin, East Nepal using frequency ratio method. Nine different contributing factors are considered: slope aspect, slope angle, slope shape, relative relief, geology, distance from faults, land use, distance from drainage and annual rainfall. To analyse the effect of contributing factors, the landslide susceptibility index maps are generated four times using (a) topographical factors and geological factors, (b) topographical factors, geological factors and land use, (c) topographical factors, geological factors, land use and drainage and (d) all nine causative factors. By comparing with the pre-existing landslides, the fourth case (considering all nine causative factors) yields the best success rate accuracy, i.e. 81.19 %, which is then used to produce the final landslide susceptibility zonation map. Then, the final landslide susceptibility map is validated through chi-square test. The standard chi-square value with 3 degrees of freedom at the 0.001 significance level is 16.3, whereas the calculated chi-square value is 7,125.79. Since the calculated chi-square value is greater than the standard chi-square value, it can be concluded that the landslide susceptibility map is considered as statistically significant. Moreover, the results show that the predicted susceptibility levels are found to be in good agreement with the past landslide occurrences. 相似文献
14.
Landslide zoning in a part of the Garhwal Himalayas 总被引：21，自引：1，他引：20
The Himalayas are undergoing constant rupturing in the thrust belt zone in the Garhwal Himalayas, due to which earthquake
and mass movement activity is triggered. These processes of mass movement and landslides have been constantly modifying the
landscape. Landslides are one of the indicators of the geomorphological modifications taking place in this active and fragile
terrain. This work is aimed at providing another example of landslide susceptibility mapping based on geological and geomorphological
attributes. The data collected from aerial photographs, topographic sheets and the image suggests that there is a correlation
between the distribution of landslides and some of the geological and geomorphological factors, for example, the distance
from an active fault, relative relief and slope. Parameters like factor of safety, altitude, relief, slope and the distance
from the fault lineament have been included in the study. A rating system has been applied to the factors for arriving at
a quantitative estimate of landslide susceptibility for each physiographic unit. Since terrain classification forms the foundation
of this work, the entire study can be grouped into two sequential activities: (1) the terrain classification and (2) landslide
susceptibility mapping. The result is the landslide susceptibility zoning map presented. The landslides have not been classified
with respect to time and may represent the final result of the on-going geological, geomorphological and seismic activity
since the Holocene period or late Pleistocene time when the glaciers retreated.
The area chosen for the study lies between Badri gad and Barni gad in Yamuna valley region of the Garhwal Himalaya where a
very large scale investment is in the pipe line for Hydroelectric power generation.
Received: 12 August 1993 · Accepted: 13 January 1998 相似文献
15.
Landslide susceptibility mapping using LiDAR and DMC data: a case study in the Three Gorges area, China 总被引：2，自引：0，他引：2
The objective of this study is to map landslide susceptibility in Zigui segment of the Yangtze Three Gorges area that is known as one of the most landslide-prone areas in China by using data from light detection and ranging (LiDAR) and digital mapping camera (DMC). The likelihood ratio (LR) and logistic regression model (LRM) were used in this study. The work is divided into three phases. The first phase consists of data processing and analysis. In this phase, LiDAR and DMC data and geological maps were processed, and the landslide-controlling factors were derived such as landslide density, digital elevation model (DEM), slope angle, aspect, lithology, land use and distance from drainage. Among these, the landslide inventories, land use and drainage were constructed with both LiDAR and DMC data; DEM, slope angle and aspect were constructed with LiDAR data; lithology was taken from the 1:250,000 scale geological maps. The second phase is the logistic regression analysis. In this phase, the LR was applied to find the correlation between the landslide locations and the landslide-controlling factors, whereas the LRM was used to predict the occurrence of landslides based on six factors. To calculate the coefficients of LRM, 13,290,553 pixels was used, 29.5 % of the total pixels. The logical regression coefficients of landslide-controlling factors were obtained by logical regression analysis with SPSS 17.0 software. The accuracy of the LRM was 88.8 % on the whole. The third phase is landslide susceptibility mapping and verification. The mapping result was verified using the landslide location data, and 64.4 % landslide pixels distributed in “extremely high” zone and “high” zone; in addition, verification was performed using a success rate curve. The verification result show clearly that landslide susceptibility zones were in close agreement with actual landslide areas in the field. It is also shown that the factors that were applied in this study are appropriate; lithology, elevation and distance from drainage are primary factors for the landslide susceptibility mapping in the area, while slope angle, aspect and land use are secondary. 相似文献
16.
山区地质灾害易发性评价对城镇地质灾害风险管理具有重要意义。本文以康定市为例,以斜坡单元为最小评价单元,选取高程、坡度、坡向、曲率、工程地质岩组、距道路距离、距断裂距离、距水系距离和斜坡结构等9个滑坡影响因子,根据各因子滑坡面积比曲线与证据权值曲线的突变点,划分滑坡影响因子二级状态,并对各影响因子进行相关性分析,剔除相关性较高的距道路距离因子,在此基础上,采用证据权模型进行滑坡易发性评价。对已有治理工程的斜坡单元,本文尝试利用折减系数法对其易发性进行进一步评价。结合现场调查,将研究区滑坡易发性程度划分为：极高易发、高易发、中等易发、低易发。评价结果表明,自然工况下极高易发区主要位于康定市炉城镇以及研究区北侧二道桥村一带,高易发区主要位于雅拉河、折多河与瓦斯沟河谷两侧,对治理工程所在的斜坡单元进行折减后,极高易发区面积由11.21%降至8.42%,滑坡比率由4.03降低至2.3,研究结果符合实际情况,模型精度达77.8%。评价结果较好地反映了康定市区的滑坡易发性分布情况,可为城镇精细化评价提供一定的参考依据。 相似文献
17.
川藏铁路位于青藏高原中东部,其地形地貌和地质构造复杂,是我国大型滑坡发育最为密集的地区,严重影响了我国西南地区的人类生命财产安全和重大工程建设。在面上资料分析的基础上,重点以川藏铁路沿线茶树山滑坡、川藏公路102道班滑坡、八宿怒江滑坡、理塘乱石包高速远程滑坡为例,在ENVI51和eCognition软件平台上,利用高分辨率WorldView 2以及Landsat遥感卫星数据,结合野外实地调查,采用基于面向对象分类法对滑坡的遥感信息进行分析研究。结果表明,采用面向对象分类法可以提取出关键信息和目标区域,再结合目视解译,能够得到滑坡的细部信息,提高遥感影像滑坡解译的成功率,特别是对川藏铁路沿线等地质条件复杂区域的滑坡调查工作有重要意义。最后,结合灰度共生矩阵(GLCM)和归一化植被指数(NDVI)对古滑坡和新生滑坡的识别进行探讨。基于灰度共生矩阵和植被指数提出了滑坡遥感信息量判别(GVI)模型,并构建模型的质量函数IGVI;统计样本的结果显示古滑坡的IGVI值明显低于新生滑坡,表明本研究提出的GVI模型可以为识别古滑坡和新生滑坡提供依据。 相似文献
18.
基于GIS和信息量模型的广西花岗岩分布区滑坡易发性评价 总被引：1，自引：0，他引：1
广西花岗岩分布区的岩土体结构松散,分布有大量较大厚度的风化坡残积土,受侵蚀、剥蚀、切割作用强烈,局部的水土流失严重,而且该区降雨量丰富,经常会有滑坡地质灾害发生。在统计分析的基础上选取坡度、高程、地质构造、植被、降雨、人类工程活动、滑坡灾害体积密度作为易发性评价指标,基于ArcGIS软件并运用信息量模型对广西花岗岩分布区进行滑坡易发性区划、完成滑坡易发性评价,并与滑坡灾害点和隐患点进行了验证。广西花岗岩区滑坡易发性评价的结果与实际滑坡的分布较为吻合,为广西花岗岩分布区滑坡预警预报及防治工作奠定基础。 相似文献