Development of Heavy Rain Damage Prediction Functions in the Seoul Capital Area Using Machine Learning Techniques

Authors:

Abstract
In this study, we developed heavy rain damage prediction functions using three machine learning techniques (support vector machine, decision tree, and random forest) for the Seoul Capital Area, South Korea. Data on damage caused by heavy rain were used as the dependent variable for the development of the heavy rain damage prediction function, and weather observation data were used as the independent variables. When we compared the results, the best function was the support vector machines based on weather observation data of the past two days. Compared to the linear regression model used primarily in previous studies, the results showed that the functions using machine learning techniques were mostly predictable. Therefore, it was judged that the machine learning techniques could be applied to disaster management areas. Also, it is believed that using the heavy rain damage prediction function developed in this study can help reduce damage through proper disaster management before the damage occurs.
Funding Information
  • Ministry of the Interior and Safety (MOIS-재난-2015-05)

This publication has 28 references indexed in Scilit: