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.     

滑坡遥感调查、监测与评估

滑坡遥感调查包括滑坡识别、基本信息获取和滑坡空间分析等，本文以天台乡滑坡遥感调查中用特征点法确定滑坡边界、影响带及滑坡运动特征及规模为例说明。滑坡遥感监测可分为直接监测和间接监测。由于突发的高速超高速崩塌、滑坡及泥石流活动时间难以预测，滑坡运动的规模相对于遥感地面分辨率较小，获取遥感数据的不连续性及价格昂贵等原因，目前较少应用遥感技术直接监测滑坡活动； 遥感监测滑坡运动引起的环境变化，称为间接滑坡监测，以遥感监测易贡大滑坡引起的易贡湖水面变化及溃坝造成的下游灾害为例说明。滑坡遥感评估指在获取滑坡及其发育环境基本信息的基础上，评估滑坡的稳定性，预测其未来活动性，评估区域滑坡的影响因子和进行区域滑坡危险性评价，文中以天台乡滑坡、千将坪滑坡稳定性评估及三峡库区中前段区域滑坡危险性评价为例说明。     

泸定Ms 6.8地震诱发滑坡应急评价研究

2022-09-05,四川省甘孜州泸定县发生Ms 6.8地震。地震在山区诱发了大量的地质灾害,造成了严重的人员伤亡。快速准确地获取地震诱发地质灾害的空间分布范围对震后应急决策和救援抢险至关重要。基于全球同震滑坡数据库与深度学习算法,构建了地震诱发滑坡空间分布概率近实时预测模型,在震后2 h内获取了泸定地震诱发地质灾害的预测结果。通过震后无人机与卫星遥感影像,采用机器学习与深度学习算法实现了震后大范围地质灾害的智能识别,共解译地震诱发滑坡3 633处,总面积13.78 km2。利用遥感解译的泸定地震滑坡数据,对地震诱发地质灾害预测模型进行了优化,获得了震区范围更广、准确性更高的同震滑坡预测结果。结果表明,同震滑坡预测模型能够快速获取震后地质灾害的空间分布情况,填补震后遥感影像获取前的空窗期,为灾后应急救援提供支撑;基于无人机与卫星遥感影像的智能识别技术是快速获取大范围地质灾害信息的有效手段。所取得的研究成果在泸定地震震后应急救援工作中发挥了重要作用。     

粒子群优化BP神经网络的滑坡敏感性评价

滑坡敏感性评价是地质灾害预测预报的关键环节。针对BP神经网络易陷入局部最小值、收敛速度慢等问题,该文以三峡库区秭归县境内为研究区,采用粒子群优化(PSO)算法对BP神经网络的初始权值和阈值进行优化,构建PSO-BP神经网络滑坡敏感性预测模型,实现研究区滑坡敏感性评价。采用受试者工作特征曲线分析模型预测精度,得到PSO-BP神经网络预测精度为0.931,预测结果与实际滑坡总体空间分布具有良好的一致性,且预测能力优于BP神经网络。实验结果表明,PSO-BP神经网络耦合模型在实现滑坡敏感性评价上具有理想的预测精度和良好的适用性。     

Use of LiDAR-derived DEM and a stream length-gradient index approach to investigation of landslides in Zagros Mountains,Iran

This paper presents an approach to stream length-gradient index analysis to identify tectonic signatures. The graded profile of the Dez River in Zagros Mountains, Iran, indicates that the area has been tectonically disturbed, and it triggers landslide hazards. The high-gradient index shows that a steeper gradient could be potentially a signature for landslides identification. The digital surface models acquired by airborne LiDAR were used in this study to generate the HRDEM. Our result shows a great potential for improving landslide investigations by implementing stream length-gradient index derived from the HRDEM in conjunction with the landslide inventories data-set in the GIS environment. We also identified a correlation between the stream length-gradient index and the graded topographic profile with slopes and landslides. This empirical approach was verified by geodata analytics and landslide inventories data-set in conjunction with field observations. This study has identified the locations of high-gradient indices with susceptible to landslides.     

GIS-based ordered weighted averaging and Dempster–Shafer methods for landslide susceptibility mapping in the Urmia Lake Basin,Iran

In this paper, GIS-based ordered weighted averaging (OWA) is applied to landslide susceptibility mapping (LSM) for the Urmia Lake Basin in northwest Iran. Nine landslide causal factors were used, whereby the respective parameters were extracted from an associated spatial database. These factors were evaluated, and then the respective factor weight and class weight were assigned to each of the associated factors using analytic hierarchy process (AHP). A landslide susceptibility map was produced based on OWA multicriteria decision analysis. In order to validate the result, the outcome of the OWA method was qualitatively evaluated based on an existing inventory of known landslides. Correspondingly, an uncertainty analysis was carried out using the Dempster–Shafer theory. Based on the results, very strong support was determined for the high susceptibility category of the landslide susceptibility map, while strong support was received for the areas with moderate susceptibility. In this paper, we discuss in which respect these results are useful for an improved understanding of the effectiveness of OWA in LSM, and how the landslide prediction map can be used for spatial planning tasks and for the mitigation of future hazards in the study area.     

时序InSAR技术探测芒康地区滑坡灾害隐患

位于中国西藏自治区东南部的芒康地区受自然条件制约和人类活动影响,近年来滑坡等地质灾害频发,对电网建设运行、交通干线通行和人民生命财产安全构成严重威胁,亟需有效技术手段对该地区分布的滑坡灾害隐患进行探测识别,从而为防灾减灾提供决策信息支持。采用小基线集（SBAS）时间序列雷达干涉测量技术,对覆盖芒康地区的历史存档ALOS PALSAR和ENVISAT ASAR数据集进行处理分析,探测发现了分布在318国道沿线和金沙江河谷的多处疑似滑坡灾害隐患点,获得了潜在滑坡形变的空间分布图和时间演化特征,证明了时序InSAR技术应用于藏东区域地质灾害调查的可行性和有效性。     

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.     

滑坡蠕变与遥感影像上植被异常关系

以滑坡蠕变阶段坡体的蠕变会引起环境条件的改变，进而影响植被生长状况的野外考察客观现实为依据，提出一种间接监测滑坡变化的新方法。利用高分辨率光学遥感技术，对滑坡蠕变阶段遥感影像上坡体上覆植被的异常特征进行判识，建立遥感影像上植被异常与滑坡蠕变的关系，反映滑坡的演化过程，弥补GPS技术、InSAR技术及部分地面监测手段在地势高、地形陡峭、植被茂盛等条件下监测工作的不足，为后续的滑坡预测研究提供帮助。以植被覆盖度较高的新磨村山体高位滑坡为例，首先，对研究区域进行分区；其次，计算各分区的植被覆盖度；最后，利用植被覆盖度分析遥感影像上的植被异常与滑坡蠕变的关系，并根据滑后遥感影像和实地考察情况进行验证。结果显示，2014年—2016年，滑坡的主要物源区、变形体上方细长局部崩滑区和泉眼及冲沟周边的植被覆盖度出现明显的下降，即随着滑坡发生时间的临近，植被受滑坡蠕变的影响变大，植被生长状况变差；而且随着距裸地等滑坡风险较大区域的距离增大，植被受滑坡蠕变的影响变小，植被生长状况变好。这表明，植被异常与滑坡蠕变存在明显的时空相关性，体现了滑坡蠕变阶段遥感影像上植被异常与滑坡蠕变的内在联系，反映了滑坡逐步失稳的演化过程，为进一步预测滑坡的发生提供依据。     

Landslide inventory validation and susceptibility mapping in the Gerecse Hills,Hungary

Landslides pose a threat to property both in the populated and cultivated areas of the Gerecse Hills (Hungary). The currently available landslide inventory database holds the records from many sites in the area, but the database is out-of-date. Here we address the problem of revising the National Landslides Cadastre landslide inventory database by creating a landslide suscept- ibility map with a multivariate model based on likelihood ratio functions. The model is applied to the TanDEM-X DEM (0.4″ res.), the current landslide inventory of the area, and data acquired from geological maps. By comparing the distributions of four variables in the landslide and non-landslide area with grid computation methods, the model yields landslide susceptibility estimates for the study area. The estimations show to what extent a certain area is similar to the sample areas, therefore, its likelihood to be affected by landslides in the future. The accuracy of the model predictions was checked in the field and compared to the results of our previous study using the SRTM-1 DEM for a similar analysis. The model gave accurate estimates when certain correction measures were applied to the input datasets. The limitations of the model, the input datasets, and the suggested correction measures are also discussed.     

Detecting the slope movement after the 2018 Baige Landslides based on ground-based and space-borne radar observations

On Oct. 11 and Nov. 3, 2018, two large-scale landslides occurred in the same location in Baige Village, Tibet, and massive rocks fell and encroached into the Jingsha River. These landslides posed a severe risk to the upstream and downstream areas. The occurrence, development and evolution of landslides are accompanied by a large number of changes in measurable variables. The deformation data are one of most important parameters for characterizing change and development trends of a landslide. This paper is centered on the results derived from ground-based radar and space-borne Synthetic Aperture Radar (SAR) images in the post-event phase to monitor the Baige landslides and to assess their residual risk. Two technologies play important roles in identifying and characterizing impending catastrophic slope failures: ground-based radar reveals the horizontal deformation, and satellite SAR images reveal the azimuth and range offset deformation. By combining satellite and ground-based SAR observations, we obtained high-precision three-dimensional (3D) deformation results and found that the vast majority of the instability regions mainly occur in the source area of the slope failures and that the direction of collapse converges from all sides to the middle. Additional information from UAV orthophoto maps and GNSS measurements also reveal that several cracks are distributed on the trailing edge of the landslide and are still moving. The comprehensive results revealed that the moving rock mass has still been remarkably active after the two landslide events. This study combined ground-based and space-borne SAR data to develop a long-term monitoring and stability evaluation process for implementation after a large landslide disaster. Based on the distribution characteristics of the 3D deformation fields, the present and future stability of the Baige Landslide was analyzed.     

The spatial response pattern of coseismic landslides induced by the 2008 Wenchuan earthquake to the surface deformation and Coulomb stress change revealed from InSAR observations

The 2008 Mw 7.9 Wenchuan earthquake triggered plenty of coseismic giant landslides, which resulted in almost one third of total fatalities and economic losses during the event. Previous studies investigated the spatial relations between landslide distribution and topographic and seismic factors such as elevation, slope aspect, distance from rupture trace and seismic intensity. However, few studies are performed exploring the effects of coseismic surface deformation and Coulomb stress change on triggering landslides due to lack of adequate deformation observation data and stress calculation model for slope failure. In this study, we develop an envelope method to map an entire coseismic deformation field in both near- and far-field areas of seismic faults through the data fusion from InSAR and pixel offset-tracking (POT) techniques. The change in static Coulomb stress (SCS) acting on coseismic landsliding surface caused by the event is determined using the faulting model derived from the joint inversion of InSAR and GPS data, and also with the use of the elastic half-space dislocation theory and the generalized Hook’s law. The analysis suggests the spatial response pattern of seismic landslides to the coseismic ground motion and stress change, especially in the vicinity of fault rupture trace. The landslide density dramatically rises with the stress increase within the range from Yingxiu to Beichuan areas along the major surface rupture. Moving further and eastward along the fault strike, most of large landslides are triggered as the zone of positive SCS change narrows. Moreover, the high-magnitude surface displacements are possibly responsible for the giant landsliding events in the easternmost section. From the analysis of the stress transfer, the occurrence of landslides in the study area is largely controlled by the Yingxiu-Beichuan fault with overwhelming rupture length and fault slip, yet the Pengguan fault indeed shows dominance in the area between the two faults. The results show that coseismic surface deformation (derived from InSAR data in this study) and static Coulomb stress change can serve as two significant controlling factors on seismic landslide distribution and that the stress factor seems more significant in the vicinity of surface rupture.     

Application of frequency ratio,weights of evidence and evidential belief function models in landslide susceptibility mapping

The landslide hazard occurred in Taibai County has the characteristics of the typical landslides in mountain hinterland. The slopes mainly consist of residual sediments and locate along the highway. Most of them are in the less stable state and in high risk during rainfall in flood season especially. The main purpose of this paper is to produce landslide susceptibility maps for Taibai County (China). In the first stage, a landslide inventory map and the input layers of the landslide conditioning factors were prepared in the geographic information system supported by field investigations and remote sensing data. The landslides conditioning factors considered for the study area were slope angle, altitude, slope aspect, plan curvature, profile curvature, distance to faults, distance to rivers, distance to roads, normalized difference vegetation index, lithological unit, rainfall and land use. Subsequently, the thematic data layers of conditioning factors were integrated by frequency ratio (FR), weights of evidence (WOE) and evidential belief function (EBF) models. As a result, landslide susceptibility maps were obtained. In order to compare the predictive ability of these three models, a validation procedure was conducted. The curves of cumulative area percentage of ordered index values vs. the cumulative percentage of landslide numbers were plotted and the values of area under the curve (AUC) were calculated. The predictive ability was characterized by the AUC values and it indicates that all these models considered have relatively similar and high accuracies. The success rate of FR, WOE and EBF models was 0.9161, 0.9132 and 0.9129, while the prediction rate of the three models was 0.9061, 0.9052 and 0.9007, respectively. Considering the accuracy and simplicity comprehensively, the FR model is the optimum method. These landslide susceptibility maps can be used for preliminary land use planning and hazard mitigation purpose.     

基于Google Earth影像的黄河上游干流地区滑坡特征分析

黄河上游干流地区由于特殊的地形地貌和地质构造使得滑坡灾害频发,对其开展滑坡灾害监测、分析研究,具有十分重要的意义。本文利用2015年间Google Earth遥感数据,提取并分析了该地区的滑坡灾害分布信息,取得了如下成果及认识:1)研究区的空间展布形态主要有7种,滑体性质类型有6种,岩质滑坡数量最多。2)从空间分布特征看,共发现研究区有各类滑坡162处,滑坡主要集中分布在群科-尖扎盆地;从滑坡类型看,研究区滑坡主要为大型滑坡和巨型滑坡。3)滑坡体长、宽主要集中在0~1 500 m和500~1 500 m之间,且长、宽呈两极化方向延伸,滑坡体面积分布不均,滑坡数量随着方量的增大呈现减少的趋势,发生的滑坡主要是滑坡体厚度在25~50 m的深层滑坡。4)滑坡数量在0°~90°之间有峰值出现,然后向两端逐渐减少。     

联合卫星SAR和地基SAR的海螺沟冰川动态变化及次生滑坡灾害监测

受全球气候变化的影响,近年来中国藏东南及横断山脉多数冰川物质持续亏损、运动速度减缓,导致泥石流、滑坡等灾害频发。为突破光学遥感受气候条件制约的瓶颈,联合卫星合成孔径雷达（synthetic aperture radar,SAR）和地基SAR两种技术手段,选取海螺沟冰川作为典型研究区域,开展时序监测分析。基于对近11 a间获取的38景PALSAR系列影像的像素偏移统计表明,海螺沟1号冰川粒雪盆和冰瀑布上沿区域整体运动最快,最大速度超过2 m/d;在海拔2 900~3 900 m的冰舌区,冰川运动趋缓,速度降至0.1~0.4 m/d;随着季节更替,海螺沟冰川运动速度呈周期性波动,积累区的夏冬两季差异为25%~35%,而冰舌段的差异则高达4倍。在年际变化方面,海螺沟1号冰川的运动速度平均减缓率为每年7.27%,消融区内减缓率高达每年15.57%。同时,使用像素偏移追踪和Stacking-InSAR（interferometric SAR）方法在海螺沟U型谷北坡探明了多处不稳定滑坡体,统计分析表明,此类滑坡运动与冰川消融具有强相关性,滑移速度于每年夏季达到峰值,2018年度最大滑移速度为南北向100 mm/d、东西向50 mm/d。进一步分析地基雷达的高频实时监测数据,确定该滑坡体的滑移速度在2018-07-09达到峰值（150 mm/d）,并于随后失稳垮塌,详细展现了整个蠕变致灾过程。相关研究数据及监测结果可为冰冻圈及山地灾害研究提供参考。     

Effects of Landslide Sampling Strategies on the Prediction Skill of Landslide Susceptibility Modelings

In this study, landslide susceptibility assessments were achieved using logistic regression, in a 523 km² area around the Eastern Mediterranean region of Southern Turkey. In reliable landslide susceptibility modeling, among others, an appropriate landslide sampling technique is always essential. In susceptibility assessments, two different random selection methods, ranging 78–83% for the train and 17–22% validation set in landslide affected areas, were applied. For the first, the landslides were selected based on their identity numbers considering the whole polygon while in the second, random grid cells of equal size of the former one was selected in any part of the landslides. Three random selections for the landslide free grid cells of equal proportion were also applied for each of the landslide affected data set. Among the landslide preparatory factors; geology, landform classification, land use, elevation, slope, plan curvature, profile curvature, slope length factor, solar radiation, stream power index, slope second derivate, topographic wetness index, heat load index, mean slope, slope position, roughness, dissection, surface relief ratio, linear aspect, slope/aspect ratio have been considered. The results showed that the susceptibility maps produced using the random selections considering the entire landslide polygons have higher performances by means of success and prediction rates.     

重大滑坡隐患分析方法综述

滑坡是发生频繁且破坏力巨大的典型地质灾害类型,高位山体崩滑和冰雪崩滑等重大滑坡隐患已经成为新型城镇化和川藏铁路工程等重大基础设施建设重要的制约因素。本文系统归纳总结了现有滑坡隐患监测技术和分析方法的特点与局限,提出了一种数据驱动与模型驱动协同的滑坡隐患可靠分析方法,构建滑坡隐患分析知识图谱、提取高层语义特征指标、知识引导精准判别滑坡隐患。该方法系统考虑了深部-地表内外动力耦合作用的致灾机制,为小样本、高复杂度的滑坡隐患可靠分析提供了新途径。     

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.     

基于InSAR技术和光学遥感的贵州省滑坡早期识别与监测

贵州省因其复杂的地形地貌和强降水等气候特征,滑坡灾害频繁发生。亟需一种可靠的滑坡早期识别和监测方法。传统的滑坡识别和监测方法存在局限性,而InSAR技术在大规模地质灾害监测中具有独特的优势。但是,基于单一地表形变值的滑坡识别结果存在一定的不确定性。因此,本文联合InSAR技术和光学遥感,利用Sentinel-1A雷达卫星影像数据对贵州省六盘水市、铜仁市、贵阳市等地区进行大规模地表形变监测和危险形变区识别;并采用基于NDVI时间序列分析和基于滑坡发育要素的滑坡识别方法对研究区潜在滑坡灾害进行调查。利用InSAR技术对研究区域内重点滑坡（鸡场镇）进行监测,及时掌握滑坡的运动状态。本文方法对贵州省的灾害防治和管理具有重要意义。     

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。