Determination of importance for comprehensive topographic factors on landslide hazard mapping using artificial neural network

A landslide is one of the natural disasters that occur in Malaysia. In addition to the geological factor and the rain as triggering factor, topographic factors such as elevation, slope angle, slope aspect, and curvature are considered as the main causes of landslides. The study in this paper was conducted in three stages. The first stage involved the extraction of extra topographic factors. Previous landslide studies had identified only four of the topographic factors. However, eight new additional factors have also been identified in this study. They are general curvature, longitudinal curvature, tangential curvature, cross-section curvature, surface area, diagonal line length, surface roughness, and rugosity. At this stage, 13 factors were extracted from the digital elevation model. The second stage involved specifying the importance of each factor. The multilayer perceptron network and backpropagation algorithm were used to specify the weight of each factor. Results were verified using the receiver operating characteristics based on the area under the curve method in the third stage. The results indicated 76.07 % accuracy in predicting of landslides, with slope angle as the most important factor while the tangential curvature has the least importance.     

Spatial prediction of landslide susceptibility using GIS-based statistical and machine learning models in Wanzhou County,Three Gorges Reservoir,China

Landslide susceptibility mapping is vital for landslide risk management and urban planning. In this study, we used three statistical models [frequency ratio, certainty factor and index of entropy (IOE)] and a machine learning model [random forest (RF)] for landslide susceptibility mapping in Wanzhou County, China. First, a landslide inventory map was prepared using earlier geotechnical investigation reports, aerial images, and field surveys. Then, the redundant factors were excluded from the initial fourteen landslide causal factors via factor correlation analysis. To determine the most effective causal factors, landslide susceptibility evaluations were performed based on four cases with different combinations of factors (“cases”). In the analysis, 465 (70%) landslide locations were randomly selected for model training, and 200 (30%) landslide locations were selected for verification. The results showed that case 3 produced the best performance for the statistical models and that case 2 produced the best performance for the RF model. Finally, the receiver operating characteristic (ROC) curve was used to verify the accuracy of each model’s results for its respective optimal case. The ROC curve analysis showed that the machine learning model performed better than the other three models, and among the three statistical models, the IOE model with weight coefficients was superior.

     

基于Mamdani FIS模型的滑坡易发性评价研究

滑坡的形成是众多非线性关系的影响因子相互作用的结果,传统滑坡预测方法需要大量实地勘查数据。利用Mamdani FIS(模糊推理系统)模型对三峡库区巴东-秭归段进行滑坡易发性预测,并对结果进行评价。通过地理信息系统(geographic information system,GIS)、遥感(remote sensing,RS)技术和区域地质背景资料获取地形类、生态环境类和地质背景类共3类7种滑坡影响因子,建立了192条相关的推理规则,在Matlab平台下基于Mamdani FIS模型得到研究区滑坡易发性预测指数,并生成滑坡易发性区划图。预测结果的受试者工作特征曲线下的面积值为82.8%,显示滑坡评估效果良好。结果证明,与其他模型相比,基于空间信息技术的Mamdani FIS模型,利用其非线性分析能力和基于专家意见的推理规则,评估滑坡易发性时不需要先验知识支撑,简化了模型使用时对数据的要求。另外,该模型只需通过专家意见改变推理规则就可以应用于不同的地质地理环境区域,显示其较强的适应性。     

滑坡发生时间预报分析

系统论述了滑坡监测资料的整理方法：滤波和等时化。讨论了滑坡运动响应的主要组成成分。重点阐述了滑坡发生时间预报的理论基础，此基础不同于一般物理方程建立的思路，而是直接来源于观察和经验总结，并抽象为一定的数学模型。单次滑坡发生的整个过程包括孕育、如速、减速、停止等4个阶段，滑坡发生时间则指加速向减速转换的特征时间点，此点是滑坡爆发的峰值点，也是需要预报的特征时间。能够反映滑坡如此运动过程的典型数学函数是Pearl曲线，本质上此S型曲线与系统有阻尼的自由振动微分方程是一致的，也与生物群体演化的虫口方程一致，它们都共同反映了物质运动的一般规律，因此可以用来预测滑坡运动过程。直接运用一般力学报分方程描述滑坡运动过程的困难在于缺乏对滑体系统力学参数的精确把握，直接运用Logistic虫口微分方程则存在模型参数识别的困难，作者还发现某些误用灰色系统理论对Verbulst非线性方程，参数进行辩识。文末，为展示方法而不强调结果，以拥有10a监测资料的某滑坡为例，分析预报了滑坡活动过程，并进行了预测结果的数学检验。     

基于突变理论的滑坡危险性评价

滑坡危险性评价与预测是滑坡灾害防治中的首要任务,科学合理地评价滑坡危险性十分重要。以岩桑树水电站库区发育的潜在滑坡为例,据其特有的地质环境条件,选取坡体风化程度、斜坡坡度等9个影响因素作为滑坡危险性评价的指标,并建立分级标准将滑坡危险性分为轻度危险、中度危险、重度危险和极度危险4个等级。将突变理论运用到滑坡危险性评价中,从而建立了新的稳定性评判模型。基于突变级数法的滑坡危险性评价方法,综合考虑了各评价指标间的相关性,真实地描绘了滑坡系统的内在机制。实例分析结果表明,该方法评判结果准确率高,可为滑坡的防治提供依据。     

诱发因素影响下的滑坡参数优化预测模型研究

本文结合三峡库区地质灾害监测预警建设历程、地质灾害监测分析现状及面临的问题,从地质灾害监测分析概念和内涵、发展趋势等方面进行了探讨,获得了以下认识：(1)探讨了地质灾害监测分析的内涵,提出了地质灾害监测分析的定义,即围绕着监测目的、监测内容和监测方法,对地质灾害监测数据及相关成果资料开展综合性分析的工作,针对预警预报、防控决策、施工安全、工程效果等不同监测目的,总结了地质灾害监测分析的主要内容;(2)面对多源、异构、实时、海量的地质灾害监测及相关数据,发展地质灾害智能化监测分析系统,实现地质灾害监测数据、分析技术方法、应用服务以及监测分析工作流程化等方面有效集成,是破解监测分析困境和问题的关键。     

Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO,BAT and COA algorithms

In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth, aerial photographs, and other validated sources. A support vector regression (SVR) machine-learning model was used to divide the landslide inventory into training (70%) and testing (30%) datasets. The landslide susceptibility map was produced using 14 causative factors. We applied the established gray wolf optimization (GWO) algorithm, bat algorithm (BA), and cuckoo optimization algorithm (COA) to fine-tune the parameters of the SVR model to improve its predictive accuracy. The resultant hybrid models, SVR-GWO, SVR-BA, and SVR-COA, were validated in terms of the area under curve (AUC) and root mean square error (RMSE). The AUC values for the SVR-GWO (0.733), SVR-BA (0.724), and SVR-COA (0.738) models indicate their good prediction rates for landslide susceptibility modeling. SVR-COA had the greatest accuracy, with an RMSE of 0.21687, and SVR-BA had the least accuracy, with an RMSE of 0.23046. The three optimized hybrid models outperformed the SVR model (AUC = 0.704, RMSE = 0.26689), confirming the ability of metaheuristic algorithms to improve model performance.     

Statistical modelling of Europe-wide landslide susceptibility using limited landslide inventory data

In many regions, the absence of a landslide inventory hampers the production of susceptibility or hazard maps. Therefore, a method combining a procedure for sampling of landslide-affected and landslide-free grid cells from a limited landslide inventory and logistic regression modelling was tested for susceptibility mapping of slide- and flow-type landslides on a European scale. Landslide inventories were available for Norway, Campania (Italy), and the Barcelonnette Basin (France), and from each inventory, a random subsample was extracted. In addition, a landslide dataset was produced from the analysis of Google Earth images in combination with the extraction of landslide locations reported in scientific publications. Attention was paid to have a representative distribution of landslides over Europe. In total, the landslide-affected sample contained 1,340 landslides. Then a procedure to select landslide-free grid cells was designed taking account of the incompleteness of the landslide inventory and the high proportion of flat areas in Europe. Using stepwise logistic regression, a model including slope gradient, standard deviation of slope gradient, lithology, soil, and land cover type was calibrated. The classified susceptibility map produced from the model was then validated by visual comparison with national landslide inventory or susceptibility maps available from literature. A quantitative validation was only possible for Norway, Spain, and two regions in Italy. The first results are promising and suggest that, with regard to preparedness for and response to landslide disasters, the method can be used for urgently required landslide susceptibility mapping in regions where currently only sparse landslide inventory data are available.     

基于滑坡分类的西宁市滑坡易发性评价

以往的滑坡易发性评价多以全体滑坡为研究对象,忽视了滑坡类型的区别。各评价指标对不同类型滑坡的影响程度不同,也导致指标权重无法精确地反映其对滑坡的影响。为更准确地对滑坡灾害进行空间预测,针对西宁市滑坡特征及发育机理,将全区滑坡分为土质滑坡和岩质滑坡;在野外实际调查的基础上,结合相关性分析,选取坡度、坡向、剖面曲率、平面曲率、工程地质岩组,以及滑坡点距断层、水系、道路的距离远近等8项因素作为滑坡易发性评价指标,并通过滑坡点分布密度和滑坡点相对分布密度,分析各评价指标分别对土质滑坡和岩质滑坡的影响;利用信息量模型,计算各评价指标对两类滑坡的信息量值,利用人工神经网络模型,赋予各评价指标对两类滑坡的权重;最后基于GIS平台利用加权信息量模型对研究区进行易发性评价。通过统计方法和ROC曲线法分别计算滑坡易发性评价成功率,结果表明:评价成功率可达到82.61%和82.30%,与未经滑坡分类的成功率比较,分别提高了10.9%和5.2%;同时,经过滑坡分类后,湟水河两岸地质条件较差的地区转变为滑坡高易发区。     

海量监测数据下分布式BP神经网络区域滑坡空间预测方法

提出BP神经网络的分布式区域滑坡预测方法,算法设计在大数据分布式处理平台Spark下实现,通过构造包含均方误差和L2正则化的代价函数,提高运算实时性和算法泛化能力。统计影响滑坡评价因子的量化指标和定义监测剖面危险级别评价值,并进行评价因子特征选取,用于三峡库区忠县区域9个滑坡11年月监测海量数据挖掘,对研究区所有滑坡监测剖面每月进行危险级别评价,实现以月为周期的区域滑坡危险程度空间预测。试验表明,采用所述方法得到的拟合精度、准确度、效率均比梯度提升决策树、随机森林算法好,预测的滑坡危险级别准确,该方法可作为区域滑坡空间预测的一种新思路。     

Assessment of landslide susceptibility and risk factors in China

Natural Hazards - Landslides represent some of the most important geological disasters and not only pose a threat to human beings but also have a serious destructive impact on the environment and...     

利用证据权法实现滑坡易发性区划

依托“5.12”特大地震的抗震救灾工作,以汶川地震12个极重灾县市为研究对象,在1:5万滑坡详细调查、编录和遥感影像解译的基础上,利用DEM数据,ETM影像及基础地质数据,使用证据权法完成了研究区滑坡易发性评价因子的提取与制图以及相关性统计分析,实现了1:5万的滑坡易发性区划。     

机器学习及其相关算法综述

机器学习已经在滑坡易发性评价中大量应用且取得了较好的表现,但在进行大区域评价时,仍存在数据库样本需求量大,算力要求高;影响因素分级机械化,未考虑其与滑坡机理的相关性等情况。为减少数据库样本需求,本文提出了构建包含3种坡体状态的滑坡的数据库：已经发生过失稳的坡体、正处于失稳状态的坡体、失稳概率小的坡体,该数据库可以在数值上划分出临界值,便于模型更准确地识别滑坡,较大幅度地减小了数据量。针对影响因素分级机械化的问题,提出了基于频数分布图、累计曲线及其导数图的数理统计方式,更精细地描述因数与滑坡易发性的关系。以新疆滑坡灾害为例,验证了“包含3种坡体状态的数据库”与“基于数理统计的描述方法”的适用性,获得了新疆滑坡灾害易发性分区图。结果表明与传统数据库对比,在不明显改变精度的前提下,减少了90%以上的样本量;基于数理统计的描述方法可以绘制出更加细致的滑坡危险性分区图;活动性断裂和地形起伏度对新疆滑坡易发性起到重要的控制作用。     

考虑线状环境因子适宜性和不同机器学习模型的滑坡易发性预测建模规律

对于滑坡易发性预测中的水系、公路和断层等线状环境因子,现有研究大多采用缓冲分析提取距离线状因子的距离.但缓冲分析得到的线距离属于离散型变量,带有大小不等的随机波动性且对点或线要素的误差较为敏感,导致滑坡易发性建模精度下降.提出了使用水系和公路的空间密度等连续型变量改进线状环境因子的适宜性.以江西省安远县为例,选取高程、...     

An evolutionary approach for spatial prediction of landslide susceptibility using LiDAR and symbolic classification with genetic programming

Natural Hazards - This research examines the potential of spatial prediction of landslide susceptibility by implementing an evolutionary approach using symbolic classification with genetic...     

Method for prediction of landslide movements based on random forests

Prediction of landslide movements with practical application for landslide risk mitigation is a challenge for scientists. This study presents a methodology for prediction of landslide movements using random forests, a machine learning algorithm based on regression trees. The prediction method was established based on a time series consisting of 2 years of data on landslide movement, groundwater level, and precipitation gathered from the Kostanjek landslide monitoring system and nearby meteorological stations in Zagreb (Croatia). Because of complex relations between precipitations and groundwater levels, the process of landslide movement prediction is divided into two separate models: (1) model for prediction of groundwater levels from precipitation data and (2) model for prediction of landslide movements from groundwater level data. In a groundwater level prediction model, 75 parameters were used as predictors, calculated from precipitation and evapotranspiration data. In the landslide movement prediction model, 10 parameters calculated from groundwater level data were used as predictors. Model validation was performed through the prediction of groundwater levels and prediction of landslide movements for the periods from 10 to 90 days. The validation results show the capability of the model to predict the evolution of daily displacements, from predicted variations of groundwater levels, for the period up to 30 days. Practical contributions of the developed method include the possibility of automated predictions, updated and improved on a daily basis, which would be an important source of information for decisions related to crisis management in the case of risky landslide movements.     

Uncertainty pattern in landslide susceptibility prediction modelling: Effects of different landslide boundaries and spatial shape expressions

In some studies on landslide susceptibility mapping (LSM), landslide boundary and spatial shape characteristics have been expressed in the form of points or circles in the landslide inventory instead of the accurate polygon form. Different expressions of landslide boundaries and spatial shapes may lead to substantial differences in the distribution of predicted landslide susceptibility indexes (LSIs); moreover, the presence of irregular landslide boundaries and spatial shapes introduces uncertainties into the LSM. To address this issue by accurately drawing polygonal boundaries based on LSM, the uncertainty patterns of LSM modelling under two different landslide boundaries and spatial shapes, such as landslide points and circles, are compared. Within the research area of Ruijin City in China, a total of 370 landslides with accurate boundary information are obtained, and 10 environmental factors, such as slope and lithology, are selected. Then, correlation analyses between the landslide boundary shapes and selected environmental factors are performed via the frequency ratio (FR) method. Next, a support vector machine (SVM) and random forest (RF) based on landslide points, circles and accurate landslide polygons are constructed as point-, circle- and polygon-based SVM and RF models, respectively, to address LSM. Finally, the prediction capabilities of the above models are compared by computing their statistical accuracy using receiver operating characteristic analysis, and the uncertainties of the predicted LSIs under the above models are discussed. The results show that using polygonal surfaces with a higher reliability and accuracy to express the landslide boundary and spatial shape can provide a markedly improved LSM accuracy, compared to those based on the points and circles. Moreover, a higher degree of uncertainty of LSM modelling is present in the expression of points because there are too few grid units acting as model input variables. Additionally, the expression of the landslide boundary as circles introduces errors in measurement and is not as accurate as the polygonal boundary in most LSM modelling cases. In addition, the results under different conditions show that the polygon-based models have a higher LSM accuracy, with lower mean values and larger standard deviations compared with the point- and circle-based models. Finally, the overall LSM accuracy of the RF is superior to that of the SVM, and similar patterns of landslide boundary and spatial shape affecting the LSM modelling are reflected in the SVM and RF models.     

基于机器学习的滑坡易发性预测建模及其主控因子识别

不同机器学习预测滑坡易发性的建模过程及其不确定性有所差异,另外如何有效识别滑坡易发性的主控因子意义重大.针对上述问题,以支持向量机(support vector machine,简称SVM)和随机森林(random forest,简称RF)为例探讨了基于机器学习的滑坡易发性预测及其不确定性,创新地提出了"权重均值法"来...