Search

Slope stability analysis is undoubtedly one of the most complex problems in geotechnical engineering and its study plays a paramount role in mitigating the risk associated with the occurrence of a landslide. This problem is commonly tackled by using limit equilibrium methods or advanced numerical techniques to assess the slope safety factor or, sometimes, even the displacement field of the slope. In this study, as an alternative approach, an attempt to assess the stability condition of homogeneous slopes was made using a machine learning (ML) technique. Specifically, a meta-heuristic algorithm (Harmony Search (HS) algorithm) and K-means algorithm were employed to perform a clustering analysis by considering two different classes, depending on whether a slope was unstable or stable. To achieve the purpose of this study, a database made up of 19 case studies with 6 model inputs including unit weight, intercept cohesion, angle of shearing resistance, slope angle, slope height and pore pressure ratio and one output (i.e., the slope safety factor) was established. Referring to this database, 17 out of 19 slopes were categorized correctly. Moreover, the obtained results showed that, referring to the considered database, the intercept cohesion was the most significant parameter in defining the class of each slope, whereas the unit weight had the smallest influence. Finally, the obtained results showed that the Harmony Search algorithm is an efficient approach for training K-means algorithms. [ABSTRACT FROM AUTHOR]

Data driven methods are widely used for the development of Landslide Susceptibility Mapping (LSM). The results of these methods are sensitive to different factors, such as the quality of input data, choice of algorithm, sampling strategies, and data splitting ratios. In this study, five different Machine Learning (ML) algorithms are used for LSM for the Wayanad district in Kerala, India, using two different sampling strategies and nine different train to test ratios in cross validation. The results show that Random Forest (RF), K Nearest Neighbors (KNN), and Support Vector Machine (SVM) algorithms provide better results than Naïve Bayes (NB) and Logistic Regression (LR) for the study area. NB and LR algorithms are less sensitive to the sampling strategy and data splitting, while the performance of the other three algorithms is considerably influenced by the sampling strategy. From the results, both the choice of algorithm and sampling strategy are critical in obtaining the best suited landslide susceptibility map for a region. The accuracies of KNN, RF, and SVM algorithms have increased by 10.51%, 10.02%, and 4.98% with the use of polygon landslide inventory data, while for NB and LR algorithms, the performance was slightly reduced with the use of polygon data. Thus, the sampling strategy and data splitting ratio are less consequential with NB and algorithms, while more data points provide better results for KNN, RF, and SVM algorithms. [ABSTRACT FROM AUTHOR]

In this work residents' social vulnerability and buildings' physical vulnerability of the Loures municipality (Portugal) were combined to locate the areas where the vulnerability is the highest, and to analyse the landslide risk. The social vulnerability of Loures was assessed using the Geographic Basis for Information Reference (BGRI) terrain units by combining sensitivity and lack of resilience based on the population and housing Census 2011 data. The physical vulnerability was assessed in a previous study based on an inquiry of a pool of European landslide experts and a sub-pool of landslide experts who know the study area. A matrix approach was used to cross the classes of the social and physical vulnerabilities. Finally, the landslide risk was analysed for each terrain unit considering the combined vulnerability, the buildings' economic value and the landslide susceptibility for a specific landslide magnitude (3-metre-deep rotational slide). Results show that 0.9% of the population reside in the area of the municipality where 75% of the future landslide should occur, and 0.8% of the buildings of the municipality--which represent a value of EUR 146,170,000--are also located in this dangerous area. This approach is reproducible: the risk analysis can be applied for another magnitude scenario in Loures, and the combined vulnerability can be assessed in any Portuguese municipality thanks to the availability of the data. [ABSTRACT FROM AUTHOR]

This paper explores warning system options in the landslide-prone community of Gmunden/Gschliefgraben in Upper Austria. It describes stakeholder perspectives on the technical, social, economic, legal and institutional characteristics of a warning system. The perspectives differ on issues such as responsibility allocation in decisions regarding warnings, technologies used for monitoring and forecasting, costs and financial aspects, open data policies and the role of the residents. Drawing on the theory of plural rationality and based on a desk study and interviews, stakeholder perspectives and discourses on the warning system problem and its solution were elicited. The perspectives formed the basis for the specification of three technical policy options for a warning system in Gschliefgraben: a minimal-cost and cost-effective system; a technical-expert system; and a resident-centered system. The case demonstrates the importance of accounting for a plurality of values and preferences and of giving voice to competing discourses in communities contemplating warning systems or other public good policies. This paper concludes that understanding the different and often conflicting perspectives and technical policy options is the starting point for formulating an agreed compromise for an effective warning system. We describe the compromise solution in an accompanying paper included in this Special Issue. [ABSTRACT FROM AUTHOR]

In this paper, we propose a methodology for validating landslide susceptibility results in the Pinggu district (Beijing, China). A landslide inventory including 169 landslides was prepared, and eight factors correlated to landslides (lithology, tectonic faults, topographic elevation, slope gradient, aspect, slope curvature, land use, and road network) were processed, integrating two techniques, namely the frequency ratio (FR) and the certainty factor (CF), in a geographic information system (GIS) environment. The area under the curve (success rate curve and prediction curve) analysis was used to evaluate model compatibility and predictability. Validation results indicated that the values of the area under the curve for the FR model and the CF model were 0.769 and 0.768, respectively. Considering spatial correlation, an alternative complementary method for validating landslide susceptibility maps was introduced. The spatially approximate maps could be discriminated from their matrices which carry structural information, and the structural similarity index (SSI) was then proposed to quantify the similarity. As a specific example, the SSI value of the FR (74.15%) scored higher than that of the CF model (69.36%), demonstrating its promise in validating different landslide susceptibility maps. These results show that the FR model outperforms the CF model in producing a landslide susceptibility map in the study area. [ABSTRACT FROM AUTHOR]

Frequently occurring landslides in Ethiopia endanger rapidly expanding settlements and infrastructure. We investigated a large landslide on the western escarpment of the Main Ethiopian Rift close to Debre Sina. To understand the extent and amplitude of the movements, we derived vectors of horizontal displacements by feature matching of very high resolution satellite images (VHR). The major movements occurred in two phases, after the rainy seasons in 2005 and 2006 reaching magnitudes of 48 ± 10.1 m and 114 ± 7.2 m, respectively. The results for the first phase were supported by amplitude tracking using two Envisat/ASAR scenes from the 31 July 2004 and the 29 October 2005. Surface changes in vertical direction were analyzed by subtraction of a pre-event digital elevation model (DEM) from aerial photographs and post-event DEM from ALOS/PRISM triplet data. Furthermore, we derived elevation changes using satellite laser altimetry measurement acquired by the ICESat satellite. These analyses allowed us to delineate the main landslide, which covers an area of 6.5 km², shallow landslides surrounding the main landslide body that increased the area to 8.5 km², and the stable area in the lower part of the slope. We assume that the main triggering factor for such a large landslide was precipitation cumulated over several months and we suspect that the slope failure will progress towards the foot of the slope. [ABSTRACT FROM AUTHOR]

The 5 September 2018 (UTC time) Mw6.6 earthquake of Tomakomai, Japan has triggered about 10,000 landslides with high density, causing widespread concern. We attempted to establish a detailed inventory of this slope failure and use proper methods to assess landslide susceptibility in the entire affected area. To this end we applied the logistic regression (LR) and the support vector machine (SVM) for this study. Based on high-resolution (3 m) optical satellite images (planet image) before and after the earthquake, we delineated 9295 individual landslides triggered by the earthquake, occupying an area of 30.96 km2. Ten controlling factors were selected for susceptibility analysis, including elevation, slope angle, aspect, curvature, distances to faults, distances to the epicenter, Peak ground acceleration (PGA), distance to rivers, distances to roads and lithology. Using the LR and SVM, two landslide susceptibility maps were produced for the study area. The results show that in the LR model, the success rate is 84.7% between the landslide susceptibility map and the training dataset, and the prediction rate is 83.9% shown by comparing the test dataset and the landslide susceptibility map. In the SVM model, a success rate of 90.9% exists between the susceptibility map and the test samples, and a prediction rate of 87.1% from comparison of the test dataset and the landslides susceptibility map. In comparison, the performance of the SVM is slightly better than the LR model. [ABSTRACT FROM AUTHOR]

The paper focuses on the assessment of landslide hazard and risk along or across the Trans Adriatic Pipeline (TAP) natural gas pipeline project in Albania. TAP is a natural gas pipeline that will transport gas from the Caspian Sea to Europe, crossing Northern Greece and Southern Albania. It has long been recognised that landsliding is a major factor for TAP's pipeline route selection in mountainous regions, especially the challenging area of central Albania. Experience from similar major pipelines has shown that hazard avoidance is generally the most cost- and time-efficient strategy to minimise the landslide risk since geohazard-related decision-making is usually risk-based. For landslides, the risk profile is expected to be dominated by the upslope expansion of existing landslides, resulting in a loss of ridge crest (where the Right of Way (RoW) is usually located), possibly leading to pipeline rupture. However, it is still possible that new landslides could develop under static and/or seismic conditions, especially on steep ridge flanks along the route. An expert determination approach was adopted to define a consensus for the estimate of the risk (i.e., chance of rupture) for the pipeline at eighty-two (82) identified landslide sites in Albania, to identify "hot spots" along the route, where risk-reduction measures could be prioritised. Ten landslides were characterised as "High Risk", fifteen as "Medium Risk" and nineteen as "Low Risk". Following this risk assessment, two large re-routings, as well as several local re-routings, were considered. Further investigation was required to identify the site-specific geotechnical conditions and probable remedial measures in cases where landslides could not be avoided by rerouting. [ABSTRACT FROM AUTHOR]

Rainfall-induced landslides form an important natural threat in Vietnam. The purpose of this study is to explore regional landslide susceptibility mapping in the mountainous district of A Luoi in Thua Thien Hue Province, where data on the occurrence and causes of landslides are very limited. Three methods are applied to examine landslide susceptibility: statistical index, logistic regression and certainty factor. Nine causative factors are considered: elevation, slope, geological strata, fault density, geomorphic landforms, weathering crust, land use, distance to rivers and annual precipitation. The reliability of the landslide susceptibility maps is evaluated by a receiver operating characteristic curve and the area under the curve is used to quantify and compare the prediction accuracy of the models. The certainty factor model performs best. This model is optimized by maximizing the difference between the true positive rate and the false positive rate. The optimal model correctly identifies 84% of the observed landslides. The results are verified with a validation test, whereby the model is calibrated with 75% randomly selected observed landslides, while the remaining 25% of the observed landslides are used for validation. The validation test correctly identifies 81% of the observed landslides in the training set and 73% of the observed landslides in the validation set. [ABSTRACT FROM AUTHOR]

The main objective of this study is to better understand and quantify the consequences for landslide susceptibility assessment caused by (i) the discrimination (or not) of landslide typology and (ii) the use of different predisposing factor combinations. The study area for this research was Lajedo parish (Flores Island, Azores—Portugal). For the landslide susceptibility modeling, 12 predisposing factors and a historical landslide inventory with a total of 474 individual landslide rupture areas were used as inputs, and the Information Value method was then applied. It was concluded that susceptibility models developed specifically for each landslide typology achieve better results when compared to the model developed for the total inventory, which suffers from a bias caused by the strong spatial abundance of one landslide typology. A total of 4095 susceptibility models were tested for each typology, and the best models were selected according to their goodness of fit. The best model for both falls and slides has seven predisposing factors, some of which do not correspond to the factors that have the best individual discriminatory capabilities. The number of expected and observed unique terrain conditions for each model allowed us to conclude that with the successive addition of predisposing factors, there is an inability of the territory to generate new observed unique terrain conditions. This consequence was directly related to the inability to increase the goodness of fit of the computed models. For each landslide typology, the predictive capacity of the best susceptibility model was assessed by computing the Prediction Rate Curves and the Area Under the Curve. [ABSTRACT FROM AUTHOR]