Spatial Prediction of Landslide Susceptibility Based on GIS and Discriminant Functions

Abstract

The areas where landslides occur frequently pose severe threats to the local population, which necessitates conducting regional landslide susceptibility mapping (LSM). In this study, four models including weight-of-evidence (WoE) and three WoE-based models, which were linear discriminant analysis (LDA), Fisher’s linear discriminant analysis (FLDA), and quadratic discriminant analysis (QDA), were used to obtain the LSM in the Nanchuan region of Chongqing, China. Firstly, a dataset was prepared from sixteen landslide causative factors, including eight topographic factors, three distance-related factors, and five environmental factors. A landslide inventory map including 298 landslide locations was also constructed and randomly divided with a ratio of 70:30 as training and validation data. Subsequently, the WoE method was used to estimate the relationship between landslides and the landslide causative factors, which assign a weight value to each class of causative factors. Finally, four models were applied using the training dataset, and the predictive performance of each model was compared using the validation datasets. The results showed that FLDA had a higher performance than the other three models according to the success rate curve (SRC) and prediction rate curve (PRC), illustrating that it could be considered a promising approach for landslide susceptibility mapping in the study area.

Novel Ensemble Approach of Deep Learning Neural Network (DLNN) Model and Particle Swarm Optimization (PSO) Algorithm for Prediction of Gully Erosion Susceptibility

“…It is a statistical analysis and is able to find two variables of high correlation in a multiple regression study. Thus, it is very much essential to analyze the multi-collinearity of a model to obtain better results through removing the high multi-collinearity factors and minimizing the bias of the model [ 37 ]. Several researchers throughout the world have used multi-collinearity analysis in different fields such as GES mapping [ 21 ], floods [ 38 ], and landslide susceptibility mapping [ 39 ].…”

Novel Machine Learning Approaches for Modelling the Gully Erosion Susceptibility

“…Multi-collinearity occurs when there is a very high correlation between variables and the accuracy of the result is reduced [31]. Therefore, high multi-collinearity factors need to be removed from the entire analysis in order to achieve better results [76]. Various researchers throughout the world have been used in multi-collinearity analysis to get better output by using machine learning models, i.e., in the field of GESM [28], landslide susceptibility mapping [77], etc.…”

Combining Evolutionary Algorithms and Machine Learning Models in Landslide Susceptibility Assessments

“…In the present study, the distance from faults was classified into five classes: <150 m, 151-300 m, 301-450 m, 451-600 m, and > 601 m (Figure 7a). The spatial distribution of the river network influences the surface runoff and degree of ground water infiltration, which are processes that may create the appropriate conditions to cause landslides [102]. The distance from the river network was classified into five classes: <200 m, 201-400 m, 401-600 m, 601-800 m, The geo-morphological parameters of elevation, slope angle, slope aspect, plan curvature, profile curvature, curvature, TWI, and SPI were derived using specific geo-processing tools found in the ArcGIS suite from an ASTER GDEM with 30 m resolution [63,84,90].…”

“…In the present study, the distance from faults was classified into five classes: <150 m, 151-300 m, 301-450 m, 451-600 m, and > 601 m (Figure 7a). The spatial distribution of the river network influences the surface runoff and degree of ground water infiltration, which are processes that may create the appropriate conditions to cause landslides [102]. The distance from the river network was classified into five classes: <200 m, 201-400 m, 401-600 m, 601-800 m, and >801 m (Figure 7b).…”