Creep mechanical and microstructural insights into the failure mechanism of loess landslides induced by dry-wet cycles in the Heifangtai platform, China

Landslide susceptibility analysis can provide theoretical support for landslide risk management. However, some susceptibility analyses are not sufficiently interpretable. Moreover, the accuracy of many research methods needs to be improved. Therefore, this study can supplement these deficiencies. This study aims to research the evaluation effects of random forest (RF) and extreme gradient boosting (XGBoost) classifier models on landslide susceptibility, and to compare their applicability in Fengjie County, Chongqing, a typical landslide‐prone area in southwest of China. Firstly, 1624 landslides information from 1980 to 2020 were obtained through field investigation, and a geospatial database of 16 conditional factors had been constructed. Secondly, non‐landslide points were selected to form a complete data set and RF and XGBoost models were established. Finally, the area under the ROC curve (AUC) value, accuracy, and F‐score were used to compare the two models. The results show that even though both classifiers have a highly accurate evaluation of landslide susceptibility, the RF model performs better. In comparison, the RF model has a higher AUC value of 0.866, and its accuracy and F‐score are approximately 2% higher than XGBoost. The land use, elevation, and lithology of Fengjie County contribute to the occurrence of landslides. This is due to human engineering activities (such as land reclamation, and housing construction) resulting in low slope stability and landslides in widely distributed sandstone, siltstone, and mudstone layers owing to their low permeability and planes of weakness.

Landslide Susceptibility mapping using random forest and extreme gradient boosting: A case study of Fengjie, Chongqing

Ensemble machine learning methods have been widely used for modeling landslide susceptibility, but there has been no uniform ensemble method for this problem. The main objective of this study is to compare popular ensemble machine learning-based models and apply them to landslides susceptibility mapping. The selected models include the random forest (RF), which is a typical bagging ensemble model, and three advanced boosting models, namely, adaptive boosting (AB), gradient boosting decision trees (GBDT), and extreme gradient boosting (XGBoost). This study considers 94 landslide points and 12 affecting factors. The data are divided into a training dataset consisting of 70% of the overall data, and a validation dataset, containing the remaining 30% of the data. The models are evaluated using the area under the receiver operating characteristic curve (AUC) and three common performance metrics: sensitivity, specificity, and accuracy. The results indicate that the four ensemble models have an AUC of more than 0.8, suggesting that they can appropriately and accurately predict landslide susceptibility maps. In particular, the XGBoost model achieves the best performance among all models, having a sensitivity of 92.86, specificity of 90.00, and accuracy of 91.38. Furthermore, the bagging model has a sensitivity of 89.29, specificity of 86.67, and accuracy of 87.93, and it is superior to the GBDT, which achieves a sensitivity of 86.21, specificity of 86.21, and accuracy of 86.21, and the AB, reaching a sensitivity of 82.14, specificity of 80.00, and accuracy of 81.03. The results presented in this study indicate that the advanced ensemble model, the XGBoost model, could be a promising tool for the selection of ensemble models for predicting landslide susceptibility mapping.

/pdf/application-of-tree-based-ensemble-models-to-landslide-374zr0xy.pdf

Application of Tree-Based Ensemble Models to Landslide Susceptibility Mapping: A Comparative Study

Advanced hyperparameter optimization for improved spatial prediction of shallow landslides using extreme gradient boosting (XGBoost)

Initiation and mobility of recurring loess flowslides on the Heifangtai irrigated terrace in China: Insights from hydrogeological conditions and liquefaction criteria

Landslides are widely distributed worldwide and often result in tremendous casualties and economic losses, especially in the Loess Plateau of China. Taking Wuqi County in the hinterland of the Loess Plateau as the research area, using Bayesian hyperparameters to optimize random forest and extreme gradient boosting decision trees model for landslide susceptibility mapping, and the two optimized models are compared. In addition, 14 landslide influencing factors are selected, and 734 landslides are obtained according to field investigation and reports from literals. The landslides were randomly divided into training data (70%) and validation data (30%). The hyperparameters of the random forest and extreme gradient boosting decision tree models were optimized using a Bayesian algorithm, and then the optimal hyperparameters are selected for landslide susceptibility mapping. Both models were evaluated and compared using the receiver operating characteristic curve and confusion matrix. The results show that the AUC validation data of the Bayesian optimized random forest and extreme gradient boosting decision tree model are 0.88 and 0.86, respectively, which showed an improvement of 4% and 3%, indicating that the prediction performance of the two models has been improved. However, the random forest model has a higher predictive ability than the extreme gradient boosting decision tree model. Thus, hyperparameter optimization is of great significance in the improvement of the prediction accuracy of the model. Therefore, the optimized model can generate a high-quality landslide susceptibility map.

/pdf/application-of-bayesian-hyperparameter-optimized-random-46rb1npecu.pdf

Application of Bayesian hyperparameter optimized random forest and XGBoost model for landslide susceptibility mapping

On 27 January 2021, at 21:00 (UTC + 8), a shallow loess landslide occurred in Heifangtai, Yongjing County, Gansu Province, northwest of the Chinese Loess Plateau. Fortunately, the independently developed global navigation satellite system predicted the landslide 7 h in advance. Although farmland and channels were buried and destroyed, no damage has been done to the lives and houses of residents. In order to explore the triggering factors and movement process of the landslide, based on the field investigation, we collected the precipitation and temperature data more than 1 year before the landslide and comprehensively used UAV photogrammetry, numerical simulation, and laboratory test for comprehensive research. It was found that as the temperature rose and freeze–thaw cycles, changes in mechanical properties of loess and unique stratum structure were the main factors triggering the landslide. The rise in temperature led to an increase in groundwater levels, and the strength of soil decreased gradually until shear liquefaction occurred. This landslide caused a substantial topographic change, which provided conditions for slope instability in the future. The process of landslide movement can be divided into three stages: start-up stage, severe sliding stage, and deceleration stage. Simulation results show that the maximum velocity was 22 m/s, and the maximum sliding distance was 393 m. The main movement period was 40 s, and the apparent friction angle was 5°. Finally, this study provides a reliable basis for studying the dynamic process and failure mechanism of loess landslides.

Hong-yu Fan

Papers

Application of Bayesian hyperparameter optimized random forest and XGBoost model for landslide susceptibility mapping

A landslide in Heifangtai, northwest of the Chinese Loess Plateau: triggered factors, movement characteristics, and failure mechanism