Forecasting the Air Quality Index by Utilizing Several Meteorological Factors Using the ARIMAX Method (Case Study: Central Jakarta City)

Abstract

Today's society really pays attention to air quality because the impact of exposure to pollutants in the air is starting to be felt. PM 2.5 pollutants are very dangerous because their small size can penetrate the alveoli of human lungs. The value calculation of the Air Quality Index (AQI) is important to prepare mitigation and defensive measures to reduce the negative impact of air quality and as a basis for future policymaking. Several method comparisons have been carried out by researchers to predict AQI. However, researchers have not studied much regarding the use of meteorological factors in the form of average air temperature (°C), average air humidity (percent), and average wind speed (m/s) in forecasting AQI values, even though meteorological factors have a significant link, according to previous researchers. This research forecasts AQI using the ARIMAX method, which includes meteorological factors as exogenous variables, using daily AQI PM 2.5 data in Central Jakarta. The best modeling of the data is ARIMA (1,1,1) without X and ARIMAX (1,1,1). Based on the calculation of AIC, BIC, RMSE, and MAPE values, ARIMAX (1,1,1) modeling produces better forecasting, so it can be concluded that forecasting involving meteorological factors can make forecasting more precise. Predicting AQI using ARIMAX with upcoming meteorological factors is beneficial, as precise prediction results can assist in policy-making to prevent the adverse impacts of air quality on public health. In future research, other meteorological factors could be studied and combined with other modeling besides ARIMA.

Integrating winter’s method and white noise for advanced air quality forecasting: a case study of Indore, India

“…Nevertheless, its linear assumptions frequently constrain performance when addressing intricate, non-linear pollutant dynamics. In another study, Muzakki et al [23] adapted the Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) method to forecast the AQI. Vijaya [24] observed that the MLR models delineate correlations between contaminants and meteorological factors.…”

Integrating winter’s method and white noise for advanced air quality forecasting: a case study of Indore, India

“…Nevertheless, its linear assumptions frequently constrain performance when addressing intricate, non-linear pollutant dynamics. In another study, Muzakki et al [23] adapted the Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) method to forecast the AQI. Vijaya [24] observed that the MLR models delineate correlations between contaminants and meteorological factors.…”

Integrating winter’s method and white noise for advanced air quality forecasting: a case study of Indore, India

“…Nevertheless, its linear assumptions frequently constrain performance when addressing intricate, non-linear pollutant dynamics. In another study, Muzakki et al [23] adapted the Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) method to forecast the AQI. Vijaya [24] observed that the MLR models delineate correlations between contaminants and meteorological factors.…”

Integrating winter’s method and white noise for advanced air quality forecasting: a case study of Indore, India

“…Nevertheless, its linear assumptions frequently constrain performance when addressing intricate, non-linear pollutant dynamics. In another study, Muzakki et al [23] adapted the Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) method to forecast the AQI. Vijaya [24] observed that the MLR models delineate correlations between contaminants and meteorological factors.…”