Landslide Susceptibility Assessment using Skyline Operator and Majority Voting

Abstract

Landslide susceptibility assessment is the problem of determining the likelihood of a landslide to occur in a particular area based on the geological and morphological properties of the area. In this study we propose a method wherein skyline operator is used to model landslides and majority voting is used to assess landslide susceptibility. Experiments conducted on a real life data set show that the proposed method achieves 83.07% classification accuracy and is superior over logistic regression, support vector machine and neural network based approaches and achieves similar results when compared to a decision trees-based model.