斜坡单元支持下的滑坡易发性评价支持向量机模型

针对传统滑坡预测手段数据源有限、数据更新周期长、难以发现隐藏在复杂滑坡系统中的规律等问题,本文以三峡库区为研究对象,从多源空间数据中提取滑坡孕灾环境和影响因素等信息,采用数字地形水文分析方法划分斜坡单元,对评价因子进行重采样,进而构建两类支持向量机模型。分析了多源影响因素与滑坡易发性的定量关系,并生成滑坡易发性分区图。采用成功率曲线和误差率评价预测结果,模型预测精度达到98.21%,与野外调查实际情况吻合较好。     

一种结合SMOTE和卷积神经网络的滑坡易发性评价方法

大规模的人类工程活动诱发和加剧了滑坡灾害的致灾情况,严重威胁工程安全和环境安全。滑坡易发性评价是滑坡监测预警的关键技术。针对传统滑坡监测手段数据源有限、缺乏挖掘滑坡灾害空间分布特征及其诱发因素的有效方法等问题,以位于三峡库区的中国重庆市万州区为研究区,基于地形、地质和遥感影像等多源数据,首先提取了22个滑坡易发性评价因子,并对这些因子进行多重共线性检验;然后采用合成少数类过采样技术(synthetic minority oversampling technique, SMOTE)解决滑坡和非滑坡样本比例不平衡问题,建立输入训练集;最后构建卷积神经网络(convolutional neural networks,CNN)模型,定量预测滑坡易发性,生成滑坡易发性分区图。采用受试者工作特征曲线分析评价结果,测试数据集模型精度达89.50%,说明该模型是一种高性能的滑坡易发性评价方法。     

基于优化随机森林模型的滑坡易发性评价

以三峡库区沙镇溪镇-泄滩乡为研究区,探索基于最短描述长度原则的信息增益法对滑坡连续型因子进行离散的效果,计算皮尔森系数去除高相关因子。利用信息量法预测的极低、低易发区随机抽取非滑坡样本点。通过迭代计算袋外误差估计确定较优的随机特征及其数目,将优化后的随机森林对研究区滑坡进行易发性评价,并与逻辑回归等方法进行比较。绘制各算法预测结果的接收灵敏度曲线,其中优化后的随机森林预测结果的曲线下面积较高,达91.8%,表明优化随机森林模型在滑坡易发性评价中具有较高的预测能力。     

顾及样本优化选择的多核支持向量机滑坡灾害易发性分析评价

滑坡灾害易发性分析评价对地质灾害的防治与管理具有重要意义。针对滑坡灾害样本选择策略,单核支持向量机多特征映射不合理的问题,本文提出顾及样本优化选择的多核支持向量机(multiple kernel support vector machine,MKSVM)滑坡灾害易发性分析评价方法。为了保证样本平衡性并提高负样本的合理性,采用相对频率比(relative frequency,RF)综合评价各状态对于滑坡灾害易发性影响的重要程度,实现各评价因子状态的合理划分;利用确定性系数法(certainty factor,CF)计算各评价因子各状态分级影响滑坡灾害的敏感性,并在此基础上进行加权求和得到各栅格单元的滑坡灾害易发性指数,在滑坡灾害易发性指数极低和低易发区内随机选择与滑坡灾害点数目一致的非滑坡灾害点作为负样本数据。利用MKSVM对各特征空间最优核函数进行线性组合,解决了单一核函数映射不合理的问题,提高了模型的分类准确率和预测精度。以湖南省湘西土家族苗族自治州为研究区,从滑坡灾害易发性分区图、分区统计及评价模型精度3个方面对CF样本策略的MKSVM模型、CF样本策略的单核SVM模型、随机样本策略的MKSVM模型、随机样本策略的单核SVM模型进行了对比分析。结果表明,4种模型的受试者工作特征曲线(receiver operating characteristic,ROC)下的面积(area under curve,AUC)分别为0.859、0.809、0.798、0.766,验证了CF样本策略的合理性、有效性及MKSVM模型的可靠性。     

基于卷积神经网络的区域滑坡易发性评价:以三峡库区万州区为例

开展区域滑坡易发性评价是滑坡气象预警与风险评价的关键。针对目前诸多易发性研究未考虑滑坡发生与邻接环境有关的情况,本文提出了一种基于卷积神经网络(CNN)的区域滑坡易发性建模框架。以三峡库区万州区为例,选取坡度、坡向等12个因子构建评价指标体系,通过信息量法分析因子对滑坡发育的影响程度,采用二维矩阵构建数据集,运用CNN进行易发性建模,得到易发性评价图,同时探究构建样本时二维矩阵的大小对精度的影响。研究结果表明,越靠近水库带越易发生滑坡,水系和人类工程活动对于滑坡发育具有较大影响;CNN模型精度为0.925,相比机器学习模型精度明显提升;增大构建样本时的二维矩阵可提高精度。CNN模型在多维空间数据处理方面具有优势,它考虑了滑坡位置及其邻接环境的影响,是一种准确可靠的区域滑坡易发性评价方法。     

熵指数融入支持向量机的滑坡灾害易发性评价方法——以陕西省为例

滑坡灾害易发性评价可为滑坡灾害风险管理、国土空间规划及滑坡监测提供科学依据。针对现有滑坡灾害易发性评价模型无法消除易发性评价指标因子在量纲、性质等方面的差异,尚未考虑易发性评价指标因子与滑坡灾害相关性,以及精度较高的经典机器学习模型训练效率较低、参数选取困难等问题,引入熵指数(index of entropy,IOE)和粒子群优化(particle swarm optimization,PSO)算法,提出IOE融入支持向量机(support vector machine, SVM)的滑坡灾害易发性评价方法。首先,基于滑坡灾害易发性评价指标因子,利用IOE模型计算SVM的调节因子;然后,采用PSO算法迭代求解SVM最优解,根据SVM二分类得到的隶属度来区分滑坡灾害易发性;最后,以陕西省作为实验区,从滑坡灾害易发性分区图、分区统计及评价模型精度3个方面将所提方法与SVM方法进行了对比,实验结果表明所提方法的准确性、可靠性优于SVM方法。     

顾及样本敏感性的滑坡易发性评价

滑坡作为一种危害极大的自然地质现象,严重威胁着人民的生命财产安全。因此,科学、准确地评价滑坡体的易发性至关重要。随着机器学习的发展,基于机器学习的滑坡易发性评价逐渐成为研究热点。而在真实情况中,滑坡区域与非滑坡区域面积占比悬殊,这使得机器学习模型的应用存在较严重的样本不均衡问题。本文采用样本敏感性分析方法,综合多个机器学习模型在不同比例的正负滑坡样本集上的表现,以获取最均衡滑坡样本集;并在此样本集基础上采用深度随机森林模型,在示范研究区开展滑坡易发性评价。最终的评价结果接近真实分布,表明本文方法具有较好的有效性。     

改进的学习向量量化滑坡易发性评价模型研究

针对传统的学习向量量化模型只能进行欧式空间的度量问题，该文将在学习向量量化(LVQ)模型的基础上引入径向基核函数(RBF)建立径向基函数的学习向量量化(RBF-LVQ)评价模型。以文成县为研究区，结合GIS技术选取坡度、坡向、坡形、断层距离、地质岩组、极端小时降雨量、地形湿度指数、地表覆盖、风化层厚度、黏聚力10个评价因子构建滑坡易发性评价体系，随机选取70%数据作为训练样本，分别采用RBF神经网络、LVQ神经网络和RBF-LVQ模型进行滑坡灾害易发性评价，并将剩余的30%数据利用ROC曲线进行精度检验。结果显示，训练后的RBF-LVQ模型AUC值为0.88,优于RBF神经网络的0.85和LVQ的0.86。RBF-LVQ模型拥有更好的预测能力，可为研究区域提供模型和决策支持。     

基于不同模型和单元的滑坡易发性评价比较

基于地理信息系统的滑坡灾害空间预测研究发展迅速,出现了多种滑坡空间预测模型。在总结滑坡灾害空间预测研究现状的基础上,简要介绍了决策树和支持向量机2种模型的基本原理。以秭归县一个研究区为例,选取11个滑坡影响因子,采用2种不同的研究单元,分别建立了决策树和支持向量机模型并对滑坡易发性作出了评价。结果表明针对同一模型,面向对象单元的滑坡易发性评价精度优于栅格单元;针对同一数据单元,支持向量机模型的滑坡易发性评价精度优于决策树模型。     

GIS支持下应用PSO-SVM模型预测滑坡易发性

滑坡灾害易发性预测是滑坡监测、预警与评估的关键技术。如何有效地选取评价因子和构建预测模型是滑坡灾害定量预测研究中的难题。本文以三峡库区长江干流岸坡作为研究区,通过地形、地质和遥感等多源数据融合,提取滑坡孕灾环境和诱发因素的信息作为评价因子。在此基础上,针对滑坡灾害的非线性和不确定性特征,采用粒子群算法对支持向量机模型参数进行全局寻优,构建粒子群算法(particle swarm optimization, PSO)-支持向量机(support vector machine, SVM)模型,定量预测滑坡易发性。最后通过分类精度比较分析基于格网单元和对象单元的滑坡易发性预测精度,结果表明,基于对象单元的PSO-SVM预测精度较高,其曲线下面积为0.841 5,Kappa系数为0.849 0,预测结果与野外实际调查情况较为一致,可为三峡库区滑坡防灾减灾工作提供参考。     

Remote Sensing and GIS Based Landslide Susceptibility Assessment using Binary Logistic Regression Model: A Case Study in the Ganeshganga Watershed, Himalayas

A comprehensive Landslide Susceptibility Zonation (LSZ) map is sought for adopting any landslide preventive and mitigation measures. In the present study, LSZ map of landslide prone Ganeshganga watershed (known for Patalganga Landslide) has been generated using a binary logistic regression (BLR) model. Relevant thematic layers pertaining to the causative factors for landslide occurrences, such as slope, aspect, relative relief, lithology, tectonic structures, lineaments, land use and land cover, distance to drainage, drainage density and anthropogenic factors like distance to road, have been generated using remote sensing images, field survey, ancillary data and GIS techniques. The coefficients of the causative factors retained by the BLR model along with the constant have been used to construct the landslide susceptibility map of the study area, which has further been categorized into four landslide susceptibility zones from high to very low. The resultant landslide susceptibility map was validated using receiver operator characteristic (ROC) curve analysis showing an accuracy of 95.2 % for an independent set of test samples. The result also showed a strong agreement between distribution of existing landslides and predicted landslide susceptibility zones.     

Spatial model integration for shallow landslide susceptibility and its runout using a GIS-based approach in Yongin,Korea

Rainfall-triggered shallow landslide is very common in Korean mountains and the socioeconomic impact is much higher than in the past due to population pressure in hazardous zones. Present study is an attempt toward the development of a methodology for the integration of shallow landslide susceptibility zones and runout zones that could be reached by mobilized mass. Landslide occurrence areas in Yongin were determined based on the interpretation of aerial photographs and extensive field surveys. Nineteen landslide-related factors maps were collected and analysed in geographic information system environment. Among 109 identified landslides, about 85% randomly selected training landslide data from inventory map was used to generate an evidential belief function model and remaining 15% landslides were used to validate the shallow landslide susceptibility map. The resulting susceptibility map had a success rate of 89.2% and a predictive accuracy of 92.1%. A runout propagation from high susceptible area was obtained from the modified multiple-flow direction algorithm. A matrix was used to integrate the shallow landslide susceptibility classes and the runout probable zone. Thus, each pixel had a susceptibility class in relation to its failure probability and runout susceptibility class. The study of landslide potential and its propagation can be used to obtain a spatial prediction for landslides, which could contribute to landslide risk mitigation.     

Using InfoVal method and GIS techniques for the spatial modelling of landslide susceptibility in the upper catchment of river Meenachil in Kerala

A GIS-based statistical methodology for landslide susceptibility zonation is described and its application to a study area in the Western Ghats of Kerala (India) is presented. The study area was approximately 218.44 km² and 129 landslides were identified in this area. The environmental attributes used for the landslide susceptibility analysis include geomorphology, slope, aspect, slope length, plan curvature, profile curvature, elevation, drainage density, distance from drainages, lineament density, distance from lineaments and land use. The quantitative relationship between landslides and factors affecting landslides are established by the data driven-Information Value (InfoVal) — method. By applying and integrating the InfoVal weights using ArcGIS software, a continuous scale of numerical indices (susceptibility index) is obtained with which the study area is divided into five classes of landslide susceptibility. In order to validate the results of the susceptibility analysis, a success rate curve was prepared. The map obtained shows that a great majority of the landslides (74.42%) identified in the field were located in susceptible and highly susceptible zones (27.29%). The area ratio calculated by the area under curve (AUC) method shows a prediction accuracy of 80.45%. The area having a high scale of susceptibility lies on side slope plateaus and denudational hills with high slopes where drainage density is relatively low and terrain modification is relatively intense.     

Multi-hazard assessment using machine learning and remote sensing in the North Central region of Vietnam

Natural hazards constitute a diverse category and are unevenly distributed in time and space. This hinders predictive efforts, leading to significant impacts on human life and economies. Multi-hazard prediction is vital for any natural hazard risk management plan. The main objective of this study was the development of a multi-hazard susceptibility mapping framework, by combining two natural hazards—flooding and landslides—in the North Central region of Vietnam. This was accomplished using support vector machines, random forest, and AdaBoost. The input data consisted of 4591 flood points, 1315 landslide points, and 13 conditioning factors, split into training (70%), and testing (30%) datasets. The accuracy of the models' predictions was evaluated using the statistical indices root mean square error, area under curve (AUC), mean absolute error, and coefficient of determination. All proposed models were good at predicting multi-hazard susceptibility, with AUC values over 0.95. Among them, the AUC value for the support vector machine model was 0.98 and 0.99 for landslide and flood, respectively. For the random forest model, these values were 0.98 and 0.98, and for AdaBoost, they were 0.99 and 0.99. The multi-hazard maps were built by combining the landslide and flood susceptibility maps. The results showed that approximately 60% of the study area was affected by landslides, 30% by flood, and 8% by both hazards. These results illustrate how North Central is one of the regions of Vietnam that is most severely affected by natural hazards, particularly flooding, and landslides. The proposed models adapt to evaluate multi-hazard susceptibility at different scales, although expert intervention is also required, to optimize the algorithms. Multi-hazard maps can provide a valuable point of reference for decision makers in sustainable land-use planning and infrastructure development in regions faced with multiple hazards, and to prevent and reduce more effectively the frequency of floods and landslides and their damage to human life and property.     

A GIS-based comparative study of Dempster-Shafer,logistic regression and artificial neural network models for landslide susceptibility mapping

The main aim of present study is to compare three GIS-based models, namely Dempster–Shafer (DS), logistic regression (LR) and artificial neural network (ANN) models for landslide susceptibility mapping in the Shangzhou District of Shangluo City, Shaanxi Province, China. At First, landslide locations were identified by aerial photographs and supported by field surveys, and a total of 145 landslide locations were mapped in the study area. Subsequently, the landslide inventory was randomly divided into two parts (70/30) using Hawths Tools in ArcGIS 10.0 for training and validation purposes, respectively. In the present study, 14 landslide conditioning factors such as altitude, slope angle, slope aspect, topographic wetness index, sediment transport index, stream power index, plan curvature, profile curvature, lithology, rainfall, distance to rivers, distance to roads, distance to faults and normalized different vegetation index were used to detect the most susceptible areas. In the next step, landslide susceptible areas were mapped using the DS, LR and ANN models based on landslide conditioning factors. Finally, the accuracies of the landslide susceptibility maps produced from the three models were verified using the area under the curve (AUC). The validation results showed that the landslide susceptibility map generated by the ANN model has the highest training accuracy (73.19%), followed by the LR model (71.37%), and the DS model (66.42%). Similarly, the AUC plot for prediction accuracy presents that ANN model has the highest accuracy (69.62%), followed by the LR model (68.94%), and the DS model (61.39%). According to the validation results of the AUC curves, the map produced by these models exhibits the satisfactory properties.     

Comparison of landslide susceptibility mapping based on statistical index,certainty factors,weights of evidence and evidential belief function models

The main aim of this study was to produce landslide susceptibility maps using statistical index (SI), certainty factors (CF), weights of evidence (WoE) and evidential belief function (EBF) models for the Long County, China. Firstly, a landslide inventory map, including a total of 171 landslides, was compiled on the basis of earlier reports, interpretation of aerial photographs and supported by extensive field surveys. Thereafter, all landslides were randomly separated into two data sets: 70% landslides (120 points) were selected for establishing the model and the remaining landslides (51 points) were used for validation purposes. Eleven landslide conditioning factors, such as slope aspect, slope angle, plan curvature, profile curvature, altitude, distance to faults, distance to roads, distance to rivers, lithology, NDVI and land use, were considered for landslide susceptibility mapping in this study. Then, the SI, CF, WoE and EBF models were used to produce the landslide susceptibility maps for the study area. Finally, the four models were validated using area under the curve (AUC) method. According to the validation results, the EBF model (AUC = 78.93%) has a higher prediction accuracy than the SI model (AUC = 77.72%), the WoE model (AUC = 77.62%) and the CF model (AUC = 77.72%). Similarly, the validation results also indicate that the EBF model has the highest training accuracy of 80.25%, followed by SI (79.80%), WoE (79.71%) and CF (79.67%) models.     

Landslide Susceptibility Analysis of Shiv-Khola Watershed, Darjiling: A Remote Sensing & GIS Based Analytical Hierarchy Process (AHP)

In the present study, Remote Sensing Technique and GIS tools were used to prepare landslide susceptibility map of Shiv-khola watershed, one of the landslide prone part of Darjiling Himalaya, based on 9 landslide inducing parameters like lithology, slope gradient, slope aspect, slope curvature, drainage density, upslope contributing area, land use and land cover, road contributing area and settlement density applying Analytical Hierarchy Approach (AHA). In this approach, quantification of the factors was executed on priority basis by pair-wise comparison of the factors. Couple comparing matrix of the factors were being made with reasonable consistency for understanding relative dominance of the factors as well as for assigning weighted mean/prioritized factor rating value for each landslide triggering factors through arithmetic mean method using MATLAB Software. The factor maps/thematic data layers were generated with the help of SOI Topo-sheet, LIIS-III Satellite Image (IRS P6/Sensor-LISS-III, Path-107, Row-052, date-18/03/2010) by using Erdas Imagine 8.5, PCI Geomatica, Arc View and ARC GIS Software. Landslide frequency (%) for each class of all the thematic data layers was calculated to assign the class weight value/rank value. Then, weighted linear combination (WLC) model was implied to determine the landslide susceptibility coefficient value (LSCV or ??M??) integrating factors weight and assigned class weight on GIS platform. Greater the value of M, higher is the propensity of landslide susceptibility over the space. Then Shivkhola watershed was classified into seven landslide susceptibility zones and the result was verified by ground truth assessment of existing landslide location where the classification accuracy was 92.86 and overall Kappa statistics was 0.8919.