Review on landslide susceptibility mapping using support vector machines
基于支持向量机的滑坡易发性制图综述
CATENA, Volume 165, June 2018, Pages 520-529
Yu Huang, Lu Zhao
摘要：Landslides are natural phenomena that can cause great loss of life and damage to property. A landslide susceptibility map is a useful tool to help with land management in landslide-prone areas. A support vector machine (SVM) is a machine learning algorithm that uses a small number of samples for prediction and has been widely used in recent years. This paper presents a review of landslide susceptibility mapping using SVM. It presents the basic concept of SVM and its application in landslide susceptibility assessment and mapping. Then it compares the SVM method with four other methods (analytic hierarchy process, logistic regression, artificial neural networks and random forests) used in landslide susceptibility mapping. The application of SVM in landslide susceptibility assessment and mapping is discussed and suggestions for future research are presented. Compared with some of the methods commonly used in landslide susceptibility assessment and mapping, SVM has its strengths and weaknesses owing to its unique theoretical basis. The combination of SVM and other techniques may yield better performance in landslide susceptibility assessment and mapping. A high-quality informative database is essential and classification of landslide types prior to landslide susceptibility assessment is important to help improve model performance.
Composite mechanism of the Büyükçekmece (Turkey) landslide as conditioning factor for earthquake-induced mobility
土耳其Büyükçekmece地震诱发滑坡移动性条件因素的复合机理
Geomorphology, Volume 308, 1 May 2018, Pages 64-77
S. Martino, L. Lenti, C. Bourdeau
摘要：Earthquake-induced displacements of landslides are significantly conditioned by their 1D and 2D interactions with seismic waves, as currently proven by several studies. Nevertheless, the role of a more complex geological setting, responsible for a heterogeneous composition of the landslide mass, can significantly influence these phenomena. The heterogeneity can also depend on multiple phases of the landslide activity, responsible for dislodging the whole landslide mass into submasses, each one delimited by secondary scarps and characterized by individual mobility. Hence, in the framework of the European project “MARSite – Marmara Supersite: new directions in seismic hazard assessment through focused Earth observation in the Marmara Supersite”, the Büyükçekmece landslide, located approximately 30 km W of Istanbul (Turkey), was considered as a case study. This landslide involves a large mass of approximately 140 million cubic metres, composed of silty clays, tuffs and sands ascribable to Cenozoic geological formations. The landslide is characterized by multiple phases of activity with a composite rototranslational mechanism, which created seven submasses delimited by secondary scarps. The scheme of water circulation in the landslide slope, based on piezometer data as well as on a geological survey, accounts for two flow nets: the first, shallower flow net is located in superficial sandy deposits, outcropping in the dislodged landslide submasses; the second, deeper flow net is located in the main sliding surface. A slope stability analysis following a global limit equilibrium approach provided a distribution of the pseudostatic coefficient vs. pore water pressure. The results show that the stability of the landslide submasses increases moving downslope, and reactivations are expected in the case of earthquakes with a return period between 475 and 2475 yr, according to the local seismic hazard. Dynamic numerical modelling was also performed using the stress-strain finite difference code FLAC 7.0 to derive the distributions of horizontal displacements vs. characteristic period ratios, defined as the period due to depth (Ts) and total length (Tl) of the landslide mass over the earthquake characteristic period (Tm). The obtained results indicate that an effective characteristic period of the landslide (Tl⁎), related to the length of a single counter-slope tilted submass, can provide a more correct explanation for the effect of seismic wave interactions on earthquake-induced displacements. This result indicates that the earthquake-induced mobility of the Büyükçekmece landslide is strongly conditioned by its composite rototranslational mechanisms. In general, these results indicate that landslide evolution can induce a change over time for the characteristic periods related to the dimensions of the dislodged landslide portions and then modify its interactions with seismic waves.
Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China
基于GIS机器学习技术的中国江西崇仁滑坡易发性模拟
Science of The Total Environment, Volume 626, 1 June 2018, Pages 1121-1135
Wei Chen, Jianbing Peng, Haoyuan Hong, Himan Shahabi, Zhao Duan
摘要：The preparation of a landslide susceptibility map is considered to be the first step for landslide hazard mitigation and risk assessment. However, these maps are accepted as end products that can be used for land use planning. The main goal of this study is to assess and compare four advanced machine learning techniques, namely the Bayes' net (BN), radical basis function (RBF) classifier, logistic model tree (LMT), and random forest (RF) models, for landslide susceptibility modelling in Chongren County, China. A total of 222 landslide locations were identified in the study area using historical reports, interpretation of aerial photographs, and extensive field surveys. The landslide inventory data was randomly split into two groups with a ratio of 70/30 for training and validation purposes. Fifteen landslide conditioning factors were prepared for landslide susceptibility modelling. The spatial correlation between landslides and conditioning factors was analyzed using the information gain (IG) method. The BN, RBF classifier, LMT, and RF models were constructed using the training dataset. Finally, the receiver operating characteristic (ROC) and statistical measures, including sensitivity, specificity, and accuracy, were employed to validate and compare the predictive capabilities of the models. Out of the tested models, the RF model had the highest sensitivity, specificity, and accuracy values of 0.787, 0.716, and 0.752, respectively, for the training dataset. Overall, the RF model produced an optimized balance for the training and validation datasets in terms of AUC values and statistical measures. The results of this study also demonstrate the benefit of selecting optimal machine learning techniques with proper conditioning selection methods for landslide susceptibility modelling.
Evaluation of potential landslide damming: Case study of Urni landslide, Kinnaur, Satluj valley, India
滑坡堵江（河）可能性评估：印度Satluj河谷Urni滑坡实例研究
Geoscience Frontiers, In press, corrected proof, Available online 26 May 2018
Vipin Kumar, Vikram Gupta, Imlirenla Jamir, Shovan Lal Chattoraj
摘要：This work aims to understand the process of potential landslide damming using slope failure mechanism, dam dimension and dam stability evaluation. The Urni landslide, situated on the right bank of the Satluj River, Himachal Pradesh (India) is taken as the case study. The Urni landslide has evolved into a complex landslide in the last two decade (2000–2016) and has dammed the Satluj River partially since year 2013, damaging∼200 m stretch of the National Highway (NH-05). The crown of the landslide exists at an altitude of∼2180–2190 m above msl, close to the Urni village that has a human population of about 500. The high resolution imagery shows∼50 m long landslide scarp and∼100 m long transverse cracks in the detached mass that implies potential for further slope failure movement. Further analysis shows that the landslide has attained an areal increase of 103,900 ± 1142 m2 during year 2004–2016. About 86% of this areal increase occurred since year 2013. Abrupt increase in the annual mean rainfall is also observed since the year 2013. The extreme rainfall in the June, 2013; 11 June (∼100 mm) and 16 June (∼115 mm), are considered to be responsible for the slope failure in the Urni landslide that has partially dammed the river. The finite element modelling (FEM) based slope stability analysis revealed the shear strain in the order of 0.0–0.16 with 0.0–0.6 m total displacement in the detachment zone. Further, kinematic analysis indicated planar and wedge failure condition in the jointed rockmass. The debris flow runout simulation of the detached mass in the landslide showed a velocity of∼25 m/s with a flow height of∼15 m while it (debris flow) reaches the valley floor. Finally, it is also estimated that further slope failure may detach as much as 0.80 ± 0.32 million m3 mass that will completely dam the river to a height of 76 ± 30 m above the river bed.
Simulating the failure process of the Xinmo landslide using discontinuous deformation analysis
基于非连续变形分析的四川茂县叠溪镇新磨村滑坡破坏过程模拟
Engineering Geology, Volume 239, 18 May 2018, Pages 269-281
Kun-Ting Chen, Jian-Hong Wu
摘要：The Xinmo landslide slope in Sichuan, China, was stable during the intensive Wenchuan Earthquake in 2008 but failed on June 24, 2017. Landslide debris buried Xinmo Village and blocked the Songpinggou River at the slope toe. This study aims to clarify the post-failure behavior of the landslide using two-dimensional discontinuous deformation analysis (2D DDA). The simulation results provide comprehensive information on the initiation and the evolution of the landslide. The failure process determined by the DDA correlates well with the seismic signal analysis results. In addition, the location of the calculated rock deposit is similar to that shown by the topographic map after the landslide. The maximum rock velocity in the landslide is 65.4 m/s. Therefore, the impacts of the high-velocity blocks and the buildings in Xinmo Village must be considered to simulate the burial of Xinmo Village by rocks and the transport of additional rocks across the Songpinggou River. This Xinmo landslide study demonstrates that the DDA accurately simulates the post-failure behavior and determines the impact area of a landslide with complicated failure processes and topography.
Three-dimensional information extraction from GaoFen-1 satellite images for landslide monitoring
高分一号卫星滑坡监测图像的三维信息提取技术
Geomorphology, Volume 309, 15 May 2018, Pages 77-85
Shixin Wang, Baolin Yang, Yi Zhou, Futao Wang, Qing Zhao
摘要：To more efficiently use GaoFen-1 (GF-1) satellite images for landslide emergency monitoring, a Digital Surface Model (DSM) can be generated from GF-1 across-track stereo image pairs to build a terrain dataset. This study proposes a landslide 3D information extraction method based on the terrain changes of slope objects. The slope objects are mergences of segmented image objects which have similar aspects; and the terrain changes are calculated from the post-disaster Digital Elevation Model (DEM) from GF-1 and the pre-disaster DEM from GDEM V2. A high mountain landslide that occurred in Wenchuan County, Sichuan Province is used to conduct a 3D information extraction test. The extracted total area of the landslide is 22.58 ha; the displaced earth volume is 652,100 m3; and the average sliding direction is 263.83°. The accuracies of them are 0.89, 0.87 and 0.95, respectively. Thus, the proposed method expands the application of GF-1 satellite images to the field of landslide emergency monitoring.
