The details of these three methods are listed/presented in Table 1.
Tables 2 and 3 show the commonly used influencing factors and their possible processing methods.
The whole dataset is divided into two parts and the ratio oftraining dataset to testing dataset is not fixed (Table 4).
Methods for assessing landslide susceptibility can be divided into three basic types: knowledge-based methods, physical methods and data-based methods
The two main principles of SVM are: the optimal classification hyperplane and the use of a kernel function
There are two sampling techniques, namely the pixel-based method and object-based method
Two principles are used to evaluate whether the landslide susceptibility map generated based on the model meets the requirements (From: Review on landslide susceptibility mapping using support vector machines)