Comparative Analysis Of Machine Learning Algorithms On Landslide

EasyChair Preprint 2898

Abstract

Landslide is one of the continuous geological disorders during rainy season, which make property damage and economic losses in all part of the world. In worldwide natural disorders landslide take the responsible is 17%. The frequent landslide occurrence has been increased by global climate change which causes losses and damages are increased. Therefore, automatic and accurate prediction of landslide occurrence is important to reduce the damages and losses of property. Various studies on landslide prediction and reduction in landslide damage have been performed and consequently, much of the recent progress has been in these areas. Landslide incidences are taken as dataset along with associated triggers. We apply Decision Tree (DT) and Random Forest Classifier (RF) and through our experimental evaluations find the suitable algorithm for the proposed work.

Keyphrases: Decision Tree, Random Forest, data visualisation, landslide prediction, landslide trigger, machine learning

@booklet{EasyChair:2898,
  author    = {Deeba Kannan and Trayambak Kumar and Sagar Krishna Kashyap},
  title     = {Comparative Analysis Of Machine Learning Algorithms On Landslide},
  howpublished = {EasyChair Preprint 2898},
  year      = {EasyChair, 2020}}