Random Forests for Landslide Prediction in Tsengwen River Watershed, Central Taiwan

Landslides have been identified as one of the costliest and deadliest natural disasters, causing tremendous damage to humans and societies. Information regarding the spatial extent of landslides is thus important to allow officials to devise successful strategies to mitigate landslide hazards. This study aims to develop a machine-learning approach for predicting landslide areas in the Tsengwen River Watershed (TRW), which is one of the most landslide-prone areas in Central Taiwan. Various spatial datasets were collected from 2009 to 2015 to derive 36 predictive variables used for landslide modeling with random forests (RF). The results of landslide prediction, compared with ground reference data, indicated an overall accuracy of 91.4% and Kappa coefficient of 0.83, respectively. The findings achieved from estimates of predictor importance also indicated to officials that the land-use/land-cover (LULC) type, distance to previous landslides, distance to roads, bank erosion, annual groundwater recharge, geological line density, aspect, and slope are the most influential factors that trigger landslides in the study region.

Landslide susceptibility mapping using Forest by Penalizing Attributes (FPA) algorithm based machine learning approach

Landslide susceptibility mapping is a helpful tool for assessment and management of landslides of an area. In this study, we have applied first time Forest by Penalizing Attributes (FPA) algorithm-based Machine Learning (ML) approach for mapping of landslide susceptibility at Muong Lay district (Vietnam). For this aim, 217 historical landslides locations were identified and analyzed for the development of FPA model and generation of susceptibility map. Nine landslide topographical and geo-environmental conditioning factors (curvature, geology/lithology, aspect, distance from faults, rivers and roads, weathering crust, slope, and deep division) were utilized to construct the training and validating datasets for landslide modeling. Different quantitative statistical indices including Area Under the Receiver Operating Characteristic (ROC) curve (AUC) were used to evaluate the performance of the model. The results indicate that the predictive capability of the FPA is very good for landslide susceptibility mapping on both training (AUC = 0.935) and validating (AUC = 0.882) datasets. Thus, the novel FPA based ML model can be utilized for the development of accurate landslide susceptibility map of the study area and this approach can also be applied in other landslide prone areas.

Effect of Rainfall, Runoff and Infiltration Processes on the Stability of Footslopes

To analyze the effect of runoff on shallow landslides, a model coupling one-dimensional rainfall–runoff and two-dimensional infiltration was established to simulate rainfall, infiltration, and runoff processes. Based on Bishop’s limit equilibrium method, the slope failure of a hypothetical footslope was studied. First, conditions with and without inflow were compared. The results reveal a remarkable difference in factors of safety (FS) between the two conditions, suggesting that considering the effect of runoff is crucial for landslide modeling. In terms of a series of tests of the various magnitudes, durations, lag-time, and peak position of the hydrograph, analyses show that larger inflow leads to more accumulated infiltration and triggers landslides earlier. A long-term duration inflow decreases the stability more than short intensive inflow does. With subsequent surface inflow, slope failure may occur after rainfalls stop, owing to the inflow, and the shape of inflow hydrographs could slightly affect the variance in FS. Results also indicate the necessity of considering the surface runoff when using a numerical model to analyze landslide, particularly on a footslope.

Altitude as an indicator of biased sampling design in landslide prediction

<p>Variables related to terrain morphology are widely used and have proven particularly effective in landslides detection as well as susceptibility modelling. Altitude has often been found as one of the main predictors in landslide modelling, although it does not have clear conceptual or empirical justification as predisposing factor. As most other land-surface variables are derived from it, altitude might be just a surrogate for more meaningful predictors in a statistically-based landslide modeling. For instance, altitude might replace curvature simply because convexities tend to occur in upper parts of a landscape, while concavities are associated with lower altitudes. Our work intends to examine the hypothesis that altitude points out issues in sampling design when appears as a main predictor in landslide modeling. The tests were conducted in two study areas, one in the Buzău County, Romania and the other in the Shizuoka Prefecture, Japan, with landslide inventories available. Two sampling designs were tested in each study area: random sampling over the entire study area (random point allocation within each landslide scarp polygon and the same number of points randomly created outside landslide scarp area, as absence data), and stratified random sampling based on lithological strata. Following stratified random sampling based on lithological homogeneity, three study areas in Buzau and two in Japan resulted.  Variable importance analysis and prediction of landslide scarp were conducted with Random Forest (RF) on databases with presence/absence of landslide scarp and associated values of 14 terrain variables. The results of variable importance analysis showed that variable hierarchy changed significantly when using lithological stratified sampling. In the random sampling scenario, altitude showed as the second most important landslide predictor in both study areas. In four out of five cases, the lithologically stratified random sampling led to decrease of altitude importance as landslide predictor, in two cases altitude even being one of least important variables. The results of model performance metrics showed that in four out of five cases the lithologically stratified random sampling significantly improved the prediction. In both areas in Japan, all four metrics show improvement of lithological stratified sampling over random sampling, by 6 and 4 % for AUC, 3% for OOB, 3 and 5 % for OA, and 6 and 10 % for Kappa, respectively. We conclude that landslide modeling is sensitive to lithological homogeneity and the presence of altitude as an important predictor could indicate a bias in the sampling design.</p>

Mathematical Optimization Problems for Particle Finite Element Analysis Applied to 2D Landslide Modeling

Notwithstanding its complexity in terms of numerical implementation and limitations in coping with problems involving extreme deformation, the finite element method (FEM) offers the advantage of solving complicated mathematical problems with diverse boundary conditions. Recently, a version of the particle finite element method (PFEM) was proposed for analyzing large-deformation problems. In this version of the PFEM, the finite element formulation, which was recast as a standard optimization problem and resolved efficiently using advanced optimization engines, was adopted for incremental analysis whilst the idea of particle approaches was employed to tackle mesh issues resulting from the large deformations. In this paper, the numerical implementation of this version of PFEM is detailed, revealing some key numerical aspects that are distinct from the conventional FEM, such as the solution strategy, imposition of displacement boundary conditions, and treatment of contacts. Additionally, the correctness and robustness of this version of PFEM in conducting failure and post-failure analyses of landslides are demonstrated via a stability analysis of a typical slope and a case study on the 2008 Tangjiashan landslide, China. Comparative studies between the results of the PFEM simulations and available data are performed qualitatively as well as quantitatively.

A Novel Intelligence Approach of a Sequential Minimal Optimization-Based Support Vector Machine for Landslide Susceptibility Mapping

The main objective of this study is to propose a novel hybrid model of a sequential minimal optimization and support vector machine (SMOSVM) for accurate landslide susceptibility mapping. For this task, one of the landslide prone areas of Vietnam, the Mu Cang Chai District located in Yen Bai Province was selected. In total, 248 landslide locations and 15 landslide-affecting factors were selected for landslide modeling and analysis. Predictive capability of SMOSVM was evaluated and compared with other landslide models, namely a hybrid model of the cascade generalization optimization-based support vector machine (CGSVM), individual models, such as support vector machines (SVM) and naïve Bayes trees (NBT). For validation, different quantitative criteria such as statistical based methods and area under the receiver operating characteristic curve (AUC) technique were used. Results of the study show that the SMOSVM model (AUC = 0.824) has the highest performance for landslide susceptibility mapping, followed by CGSVM (AUC = 0.815), SVM (AUC = 0.804), and NBT (AUC = 0.800) models, respectively. Thus, the proposed novel SMOSVM model is a promising method for better landslide susceptibility mapping and prediction, which can be applied also in other landslide prone areas.