Modeling landslide susceptibility in data-scarce environments using optimized data mining and statistical methods

数据缺乏环境下基于数据挖掘与统计方法的滑坡易发性模拟

Geomorphology, Volume 303, 15 February 2018, Pages 284-298

Jung-Hyun Lee, Maher Ibrahim Sameen, Biswajeet Pradhan, Hyuck-Jin Park

摘要:This study evaluated the generalizability of five models to select a suitable approach for landslide susceptibility modeling in data-scarce environments. In total, 418 landslide inventories and 18 landslide conditioning factors were analyzed. Multicollinearity and factor optimization were investigated before data modeling, and two experiments were then conducted. In each experiment, five susceptibility maps were produced based on support vector machine (SVM), random forest (RF), weight-of-evidence (WoE), ridge regression (Rid_R), and robust regression (RR) models. The highest accuracy (AUC = 0.85) was achieved with the SVM model when either the full or limited landslide inventories were used. Furthermore, the RF and WoE models were severely affected when less landslide samples were used for training. The other models were affected slightly when the training samples were limited.

Sensitive clay landslide detection and characterization in and around Lakelse Lake, British Columbia, Canada

加拿大不列颠哥伦比亚Lakelse湖周围敏感黏土滑坡探测与特征化

Sedimentary Geology, Volume 364, February 2018, Pages 217-227

Marten Geertsema, Andrée Blais-Stevens, Eva Kwoll, Brian Menounos, Kelsey Wiebe

摘要:The Lakelse Lake area in northwestern British Columbia, Canada, has a long history, and prehistory, of rapid sensitive clay landslides moving on very low gradients. However, until now, many landslides have gone undetected. We use an array of modern tools to identify hitherto unknown or poorly known landslide deposits, including acoustic subbottom profiles, multibeam sonar, and LiDAR. The combination of these methods reveals not only landslide deposits, but also geomorphic and sedimentologic structures that give clues about landslide type and mode of emplacement. LiDAR and bathymetric data reveal the areal extent of landslide deposits as well as the orientation of ridges that differentiate between spreading and flowing kinematics. The subbottom profiles show two-dimensional structures of disturbed landslide deposits, including horst and grabens indicative of landslides classified as spreads. A preliminary computer tomography (CT) scan of a sediment core confirms the structures of one subbottom profile. We also use archival data from the Ministry of Transportation and Infrastructure and resident interviews to better characterize historic landslides.

Landslide susceptibility mapping using logistic regression model (a case study in Badulla District, Sri Lanka)

基于逻辑回归模型的滑坡易发性制图 –斯里兰卡Badulla地区实例研究

Procedia Engineering, Volume 212, 2018, Pages 1046-1053

Hasali Hemasinghe, R.S.S. Rangali, N.L. Deshapriya, Lal Samarakoon

摘要:The landslide is a universal term covering a wide variety of mass movements and processes involved in downward movement of masses of rock, earth or debris under the influence of gravity. Landslides are among the natural disasters that are often experienced in Sri Lanka. Approximately 20,000 km2 (30.7%) of the land area of the country is highly susceptible to landslides. With the increasing demand for development and expansion of human settlements, landslides have become a major concern in the mountainous regions of the country. Therefore, identification of landslide potential associated with the terrain is important for ensuring the sustainability of developments while minimizing the possible disasters due to landslides. The study was focused on landslide susceptibility mapping in Badulla District using logistic regression model. Slope, aspect, lithology, land cover, distance from the rivers and roads were selected as the causative factors for the analysis. According to the study, 20.5% area of the district is highly and extremely highly susceptible to the occurrence of landslides, 39.3% area is moderately susceptible to landslide occurrences and 40.2% area is low susceptible to the occurrence of landslides.

Prediction of the landslide susceptibility: Which algorithm, which precision?

滑坡易发性预测：最佳算法探索

CATENA, Volume 162, March 2018, Pages 177-192

Hamid Reza Pourghasemi, Omid Rahmati

摘要:Coupling machine learning algorithms with spatial analytical techniques for landslide susceptibility modeling is a worth considering issue. So, the current research intend to present the first comprehensive comparison among the performances of ten advanced machine learning techniques (MLTs) including artificial neural networks (ANNs), boosted regression tree (BRT), classification and regression trees (CART), generalized linear model (GLM), generalized additive model (GAM), multivariate adaptive regression splines (MARS), naïve Bayes (NB), quadratic discriminant analysis (QDA), random forest (RF), and support vector machines (SVM) for modeling landslide susceptibility and evaluating the importance of variables in GIS and R open source software. This study was carried out in the Ghaemshahr Region, Iran. The performance of MLTs has been evaluated using the area under ROC curve (AUC-ROC) approach. The results showed that AUC values for ten MLTs vary from 62.4 to 83.7%. It has been found that the RF (AUC = 83.7%) and BRT (AUC = 80.7%) have the best performances comparison to other MLTs.

Microstructures in landslides in northwest China – Implications for creeping displacements?

中国西北地区滑坡微构造 –蠕动位移影响？

Journal of Structural Geology, Volume 106, January 2018, Pages 70-85

M. Schäbitz, C. Janssen, H.-R. Wenk, R. Wirth, G. Dresen

摘要:Microstructures, mineralogical composition and texture of selected landslide samples from three landslides in the southern part of the Gansu Province (China) were examined with optical microscopy, transmission electron microscopy (TEM), x-ray diffraction (XRD) and synchrotron x-ray diffraction measurements. Common sheet silicates are chlorite, illite, muscovite, kaolinite, pyrophyllite and dickite. Other minerals are quartz, calcite, dolomite and albite. In one sample, graphite and amorphous carbon were detected by TEM-EDX analyses and TEM high-angle annular dark-field images. The occurrence of graphite and pyrophyllite with very low friction coefficients in the gouge material of the Suoertou and Xieliupo landslides is particularly significant for reducing the frictional strength of the landslides. It is proposed that the landslides underwent comparable deformation processes as fault zones. The low friction coefficients provide strong evidence that slow-moving landsliding is controlled by the presence of weak minerals. In addition, TEM observations document that grain size reduction in clayey slip zone material was produced mainly by mechanical abrasion. For calcite and quartz, grain size reduction was attributed to both pressure solution and cataclasis. Therefore, besides landslide composition, the occurrence of ultrafine-grained slip zone material may also contribute to weakening processes of landslides. TEM images of slip-zone samples show both locally aligned clay particles, as well as kinked and folded sheet silicates, which are widely disseminated in the whole matrix. Small, newly formed clay particles have random orientations. Based on synchrotron x-ray diffraction measurements, the degree of preferred orientation of constituent sheet silicates in local shear zones of the Suoertou and Duang-He-Ba landslide is strong. This work is the first reported observation of well-oriented clay fabrics in landslides.