Development and Evaluation of Statistical Models Based on Machine Learning Techniques for Estimating Particulate Matter (PM2.5 and PM10) Concentrations

Meteorological variability and predictive forecasting of atmospheric particulate pollution

Due to increasingly documented health effects associated with airborne particulate matter (PM), challenges in forecasting and concern about their impact on climate change, extensive research has been conducted to improve understanding of their variability and accurately forecasting them. This study shows that atmospheric PM10 concentrations in Brunei-Muara district are influenced by meteorological conditions and they contribute to the warming of the Earth's atmosphere. PM10 predictive forecasting models based on time and meteorological parameters are successfully developed, validated and tested for prediction by multiple linear regression (MLR), random forest (RF), extreme gradient boosting (XGBoost) and artificial neural network (ANN). Incorporation of the previous day's PM10 concentration (PM10,t-1) into the models significantly improves the models' predictive power by 57-92%. The MLR model with PM10,t-1 variable shows the greatest capability in capturing the seasonal variability of daily PM10 (RMSE = 1.549 μg/m3; R2 = 0.984). The next day's PM10 can be forecasted more accurately by the RF model with PM10,t-1 variable (RMSE = 5.094 μg/m3; R2 = 0.822) while the next 2 and 3 days' PM10 can be forecasted more accurately by ANN models with PM10,t-1 variable (RMSE = 5.107 μg/m3; R2 = 0.603 and RMSE = 6.657 μg/m3; R2 = 0.504, respectively).