Time Series Models for the Hourly Fine Particulate Matter (PM2.5) Concentrations in Pingtung City

碩士 === 國立屏東科技大學 === 工業管理系所 === 100 === From the traditional agricultural production to industrial society, Taiwan's environment and ecology is rapidly deteriorating. Due to a number of petrochemical and steel industries was established in southern Taiwan, resulting in Kaohsiung-Pingtung area ai...

Full description

Bibliographic Details
Main Authors: Chao-Hung Hsu, 許兆宏
Other Authors: Ji-Cheng Wu
Format: Others
Language:zh-TW
Published: 2012
Online Access:http://ndltd.ncl.edu.tw/handle/01528539435727559886
Description
Summary:碩士 === 國立屏東科技大學 === 工業管理系所 === 100 === From the traditional agricultural production to industrial society, Taiwan's environment and ecology is rapidly deteriorating. Due to a number of petrochemical and steel industries was established in southern Taiwan, resulting in Kaohsiung-Pingtung area air quality is relatively higher concentration than in other regions. Many studies had supported that fine particulates (PM2.5) suspended in the air are harmful to the human respiratory system and could further lead to severe cases of bronchitis. This study used published data obtained from the Environmental Protection Administration website that collected the concentration of PM2.5 at every hour at stations in Ping-Tung city from January 1st, 2005 to December 31st, 2011.The research constructed the quarterly, monthly and hourly ARIMA and Holt-Winters PM2.5 concentration prediction models based on the concept of time series. According to the fitted models, the hourly PM2.5concentration in Ping-Tung city were predicted in the first quarter of 2012, from January to April, 2012, and from April28st to 30st, 2012.The study found that under the mean absolute percentage error (MAPE) criteria, the Holt-Winters multiplicative model is superior to the ARIMA model for the quarterly and monthly time scales. However, the ARIMA model to predict the results is better than the Holt-Winters multiplicative model for the hourly time scale.