Forecasting daily PM_10 concentration in Seoul Jong-no District by using various statistical techniques

Abstract

Interest in PM_10 concentration has been increased remarkably in Korea due to the people's interest in the environment and the severity of air pollution. In this paper, we forecast daily PM_10 concentration using air pollution and weather information by applying various statistical techniques. We consider nine models to forecast the daily PM_10, which include five regression models (Linear regression, Principal Component regression, Linear-Support Vector regression, Kernel-Support Vector regression, Radial Basis Function), and four categorical models (Linear Discriminant Analysis, Support Vector Machine, Randomforest, Logistic regression). From the results, we expect that the various advanced statistical methods can be applied to forecast PM_10 concentration, and improve the accuracy of the prediction.