Study on landslide susceptibility mapping based on rock–soil characteristic factors

Abstract

This study introduces four rock–soil characteristics factors, that is, Lithology, Rock Structure, Rock Infiltration, and Rock Weathering, which based on the properties of rock formations, to predict Landslide Susceptibility Mapping (LSM) in Three Gorges Reservoir Area from Zigui to Badong. Logistic regression, artificial neural network, support vector machine is used in LSM modeling. The study consists of three main steps. In the first step, these four factors are combined with the 11 basic factors to form different factor combinations. The second step randomly selects training (70% of the total) and validation (30%) datasets out of grid cells corresponding to landslide and non-landslide locations in the study area. The final step constructs the LSM models to obtain different landslide susceptibility index maps and landslide susceptibility zoning maps. The specific category precision, receiver operating characteristic curve, and 5 other statistical evaluation methods are used for quantitative evaluations. The evaluation results show that, in most cases, the result based on Rock Structure are better than the result obtained by traditional method based on Lithology, have the best performance. To further study the influence of rock–soil characteristic factors on the LSM, these four factors are divided into “Intrinsic attribute factors” and “External participation factors” in accordance with the participation of external factors, to generate the LSMs. The evaluation results show that the result based on Intrinsic attribute factors are better than the result based on External participation factors, indicating the significance of Intrinsic attribute factors in LSM. The method proposed in this study can effectively improve the scientificity, accuracy, and validity of LSM.

Investigating causative factors and selecting optimal machine learning algorithms for landslide susceptibility assessment in Lom Kao area, northern Thailand

“…The landslide susceptibility map plays an essential role in spatial landslide assessment in order to prepare mitigation plans and landslide prevention [19]. In landslide assessment, the causative factors are significant since they control landslide occurrence.…”

“…A positive resulting PCC value indicates a positive correlation, and a negative value suggests a negative correlation. If the value of PCC is greater than 0.7 or less than -0.7, showing a strong positive and negative correlation between those two factors, respectively [19].…”

“…The multicollinearity analysis evaluates the correlation between landslide causative factors and historical landslide (inventory) datasets [19]. The results of multicollinearity analysis are variance inflation factor (VIF) and tolerance (TOL), which are reciprocal.…”

Comparative study on landslide susceptibility mapping based on unbalanced sample ratio

“…It is necessary to perform a multilinear analysis before using the landslide factor dataset to train the model. The selection of evaluation factors directly affects the accuracy and reliability of LSM 36 . Multicollinearity analysis refers to judging whether an independent variable or multiple independent variables can be linearly combined into one independent variable, usually using Variance Inflation Factor (VIF) or Tolerance (TOL) to evaluate the evaluation factor multicollinearity.…”

Landslide Susceptibility Mapping Using Machine Learning Approach: A Case Study of Baglung District, Nepal

“…Land cover with different soil characteristics has diverse effects in the occurrence of landslides. It does not only affect the development degree of landslides in the areas, but also determines the type and scale of landslide (XIanyu Yu, 2021). The soil of study area was classified into 4 types in which 46 landslide point were within soil type of Dystrochrepts, Halpumbrepts, Haplustalfscalcarious soil Materials.…”