search for




 

Forecasting daily PM10 concentration in Seoul Jong-no District by using various statistical techniques
Journal of the Korean Data & Information Science Society 2020;31:187-98
Published online January 31, 2020;  https://doi.org/10.7465/jkdi.2020.31.1.187
© 2020 Korean Data and Information Science Society.

Soyoung An1 · Yaeji Lim2

12 Department of Statistics, Chung-Ang University
Correspondence to: Assistant professor, Department of Statistics, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Korea. E-mail: yaeji.lim@gmail.com
This work was supported by the Chung-Ang University Research Scholarship Grants in 2018.
Received September 19, 2019; Revised November 2, 2019; Accepted November 15, 2019.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Interest in PM10 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 PM10 concentration using air pollution and weather information by applying various statistical techniques. We consider nine models to forecast the daily PM10, 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 PM10 concentration, and improve the accuracy of the prediction.
Keywords : Air pollution, machine-learning methods, PM10 concentration, PM10 prediction.