Application of information gain in the selection of factors for regional slope stability evaluation

Xueping Li, Jinxin Chong, Yaobang Lu, Zhigang Li

Bulletin of Engineering Geology and the Environment(2022)

Cited 1|Views0
No score
Abstract
This paper adopted the feature selection method for information gain calculation to screen factors for landslide hazard susceptibility evaluation in Wushan County, the reservoir area of the Three Gorges Reservoir Hub. A comparative experimental study of evaluation factor screening was conducted via the Bayesian information criterion method and information gain method. The following conclusions could be drawn: in the selection of regional landslide susceptibility evaluation factors, the information gain value could be used as a screening index. The screening method steps are as follows: the information gain value of each factor is calculated, and the corresponding evaluation factors are selected based on the order of the information gain values. The percentage of the information gain value of a single factor to the sum of the information gain values of all factors could be used as an evaluation factor screening criterion. Since the information gain value provides a clear meaning and is easy to calculate in terms of the contribution of each evaluation factor to the evaluation model accuracy, this index could play an important role in the screening process of landslide susceptibility evaluation factors.
More
Translated text
Key words
Information gain, Regional slope, Susceptibility, Evaluation factor, Screening method
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined