Coupling logistic model tree and random subspace to predict the landslide susceptibility areas with considering the uncertainty of environmental features.

Landslide disasters cause huge casualties and economic losses every year, how to accurately forecast the landslides has always been an important issue in geo-environment research. In this paper, a hybrid machine learning approach RSLMT is firstly proposed by coupling Random Subspace (RS) and Logistic Model Tree (LMT) for producing a landslide susceptibility map (LSM). With this method, the uncertainty introduced by input features is considered, the problem of overfitting is solved by reducing dimensions to increase the prediction rate of landslide occurrence. Moreover, the uncertainty of prediction will be deeply discussed with the rank probability score (RPS) series, which is an important evaluation of uncertainty but rarely used in LSM. Qingchuan county, China was taken as a study area. 12 landslide causal factors were selected and their contribution on landslide occurrence was evaluated by ReliefF method. In addition, Logistic Model Tree (LMT), Naive Bayes (NB) and Logistic Regression (LR) were researched for comparison. The results showed that RSLMT (AUC = 0.815) outperformed LMT (AUC = 0.805), NB (AUC = 0.771), LR (AUC = 0.785). LSM of Qingchuan county was produced using the novel model, it indicated that landslides tend to occur along with the fault belts and the middle-low mountain area that is strongly influenced by the large numbers of human engineering activities.

Mine landslide susceptibility assessment using IVM, ANN and SVM models considering the contribution of affecting factors.

The fragile ecological environment near mines provide advantageous conditions for the development of landslides. Mine landslide susceptibility mapping is of great importance for mine geo-environment control and restoration planning. In this paper, a total of 493 landslides in Shangli County, China were collected through historical landslide inventory. 16 spectral, geomorphic and hydrological predictive factors, mainly derived from Landsat 8 imagery and Global Digital Elevation Model (ASTER GDEM), were prepared initially for landslide susceptibility assessment. Predictive capability of these factors was evaluated by using the value of variance inflation factor and information gain ratio. Three models, namely artificial neural network (ANN), support vector machine (SVM) and information value model (IVM), were applied to assess the mine landslide sensitivity. The receiver operating characteristic curve (ROC) and rank probability score were used to validate and compare the comprehensive predictive capabilities of three models involving uncertainty. Results showed that ANN model achieved higher prediction capability, proving its advantage of solve nonlinear and complex problems. Comparing the estimated landslide susceptibility map with the ground-truth one, the high-prone area tends to be located in the middle area with multiple fault distributions and the steeply sloped hill.