Search

Long-runout landslides can be extremely hazardous and unpredictable. The prediction of long-runout landslides is challenging because it is unclear what factors control their mobility, and it is unclear how to best measure their runout given that they traverse changing topography. In this paper, we document the development and statistical evaluation of a Landslide Runout Score (LRS) system to predict short, medium, and long runout using a new mobility measure, the unitless Runout Number L/A1/2 (where L is landslide length and A is landslide area). The Runout Number has previously been correlated to three geomorphological factors (planimetric curvature, sand content, and upslope contributing area normalized to landslide area), so the LRS uses these factors as inputs. These factors are readily calculated using geographic information systems (GIS) and publicly available data sources. The LRS system predicts runout categories (short, medium, and long) with one-vs.-all accuracies (i.e., percentage of correct predictions within a given class) of 75, 58, and 72%, respectively, for a total weighted accuracy of approximately 65%. The results of this work are summarized in a worksheet that can be used by geologists and engineers to develop preliminary predictions of landslide runout behavior, which can be incorporated into or used alongside regional-scale landslide hazard assessments. [ABSTRACT FROM AUTHOR]

This paper presents rainfall-induced landslide thresholds and predicts landslide hazard in Kuala Lumpur metropolitan city and surrounding areas. Landslide events from 2000 to 2012 were collected. The long and short antecedent rainfall days were prepared for landslide and non-landslide days simultaneously. First, threshold analysis was conducted by using data obtained from rainfall stations located in highly urbanized areas of Kuala Lumpur metropolis. Six rainfall gauges were selected, and the study area was divided into six zones according to rainfall gauges: Taman Desa Station (TD-KL), Genting Klang (GK-KL), LDG Edinburgh Station (LDGE-KL), SG Raya Hulu Langat Station (SRHL-Slg), Puchong Drop Station (PD-Slg), and Bukit Antarabangsa (BTA-Slg). After the threshold analysis was conducted for different periods (10, 15, and 30 days) in each station, reliability index test was conducted to optimize the best threshold that limits the predicted events along the study period for each region. Second, the threshold analysis results were used as input in the Poisson probability model to estimate landslide temporal probability ( P). Third, the spatial probability ( P) analysis was prepared by using the evidential belief function multiplied by the P to obtain the hazard maps for 1-, 3-, and 5-year scenarios. Finally, a validation process was conducted to test the prediction performance of the resultant hazard map for a 1- and 2-year prediction by using the landslide inventory of 2012 to early 2014, which was not included in the modeling of the hazard map. Results showed a valid correlation between the high and moderate hazardous areas for the six zones. The predicted hazard maps indicated a quantitative assessment of the prone areas and proved to be a valid disaster management tool. The produced hazard maps may play a vital role as input component in risk analysis. [ABSTRACT FROM AUTHOR]

An ensemble algorithm of data mining decision tree (DT)-based CHi-squared Automatic Interaction Detection (CHAID) is widely used for prediction analysis in variety of applications. CHAID as a multivariate method has an automatic classification capacity to analyze large numbers of landslide conditioning factors. Moreover, it results two or more nodes for each independent variable, where every node contains numbers of presence or absence of landslides (dependent variable). Other DT methods such as Quick, Unbiased, Efficient Statistic Tree (QUEST) and Classification and Regression Trees (CRT) are not able to produce multi branches based tree. Thus, the main objective of this paper is to use CHAID method to perform the best classification fit for each conditioning factors, then, combined it with logistic regression (LR) to find the corresponding coefficients of best fitting function that assess the optimal terminal nodes. In the first step, a landslide inventory map with 296 landslide locations were extracted from various sources over the Pohang-Kyeong Joo catchment (South Korea). Then, the inventory was randomly split into two datasets, 70 % was used for training the models, and the remaining 30 % was used for validation purpose. Thirteen landslide conditioning factors were used for the susceptibility modeling. Then, CHAID was applied and revealed that some conditioning factors such as altitude, soil drain, soil texture and TWI, as terminal nodes and reflected the best classification fit. Then, a proposed ensemble technique was applied and the interpretations of the coefficients showed that the relationship between the decision tree branch nodes distance from drain, soil drain, and TWI, respectively, leads to better consequences assessment of landslides in the current study area. The validation results showed that both success and prediction rates, 75 and 79 %, respectively. This study proved the efficiency and reliability of ensemble DT and LR model in landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

Landslide susceptibility (LS) assessment by indirect approaches presents some limitations due to (1) the tendency to simplify the environmental factors (i.e., variables) and (2) the assumptions that landslides occur under the same combination of variables for a study site. Recently, some authors have discussed the interest to introduce expert knowledge in the indirect approaches in order to improve the quality of indirect LS maps. However, if the results are reliable, the procedures used seem fastidious and a very good knowledge of the study site is essential. The objectives of this paper are to discuss a methodology to introduce the expert knowledge in the indirect mapping process. After the definition of the expert rules associated to three landslide types, several indirect LS maps are produced by two indirect exploratory approaches, based on fuzzy set theory and on a modification of a bivariate method called expert weight of evidence. Then, the indirect LS maps are confronted to a landslide inventory and a LS map produced by a direct approach. The analyses indicate that the methodology used to introduce the expert rules in the mapping process increases the predictive power of indirect LS map. Finally, some indications about advantages and drawbacks of each approach are given to help the geoscientist to introduce his expert knowledge in the landslide susceptibility mapping process. [ABSTRACT FROM AUTHOR]

Preparation of landslide susceptibility maps is considered as the first important step in landslide risk assessments, but these maps are accepted as an end product that can be used for land use planning. The main objective of this study is to explore some new state-of-the-art sophisticated machine learning techniques and introduce a framework for training and validation of shallow landslide susceptibility models by using the latest statistical methods. The Son La hydropower basin (Vietnam) was selected as a case study. First, a landslide inventory map was constructed using the historical landslide locations from two national projects in Vietnam. A total of 12 landslide conditioning factors were then constructed from various data sources. Landslide locations were randomly split into a ratio of 70:30 for training and validating the models. To choose the best subset of conditioning factors, predictive ability of the factors were assessed using the Information Gain Ratio with 10-fold cross-validation technique. Factors with null predictive ability were removed to optimize the models. Subsequently, five landslide models were built using support vector machines (SVM), multi-layer perceptron neural networks (MLP Neural Nets), radial basis function neural networks (RBF Neural Nets), kernel logistic regression (KLR), and logistic model trees (LMT). The resulting models were validated and compared using the receive operating characteristic (ROC), Kappa index, and several statistical evaluation measures. Additionally, Friedman and Wilcoxon signed-rank tests were applied to confirm significant statistical differences among the five machine learning models employed in this study. Overall, the MLP Neural Nets model has the highest prediction capability (90.2 %), followed by the SVM model (88.7 %) and the KLR model (87.9 %), the RBF Neural Nets model (87.1 %), and the LMT model (86.1 %). Results revealed that both the KLR and the LMT models showed promising methods for shallow landslide susceptibility mapping. The result from this study demonstrates the benefit of selecting the optimal machine learning techniques with proper conditioning selection method in shallow landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]