Modeling PM2.5 Air Quality Index in Kemayoran, Jakarta, with Meteorological Factors Using ARFIMAX

Abstract

Poor air quality that significantly impacts on health due to fine particles PM2.5 has become one of the serious problems in urban areas such as Kemayoran, Jakarta. This study aims to predict the Air Quality Index of PM2.5 pollutant in Kemayoran, Jakarta, with the ARFIMAX model which will be compared with the ARFIMA model. The ARFIMAX modeling involves meteorological factors as exogenous variables. The research results showed that the ARFIMAX(1,0,33,1) model with significant exogenous variables, namely minimum temperature, average temperature, and wind direction at maximum speed provides better prediction accuracy with a Mean Absolute Percentage Error (MAPE) value of 23.69%, compared to ARFIMA with a MAPE value of 25.76%. This decrease in MAPE value indicates that the addition of exogenous variables in the model can improve the accuracy of air quality forecast.