The Analysis of Pollutant Concentrations Before and During Movement Control at Quarry Areas Using an Artificial Intelligent Technique

Abstract This paper investigated the influence and interactions of air pollution concentrations by using stochastic boosted regression trees between variables for each station impact COVID-19 Movement Control Order at Ipoh City quality station. The one-hour data were gathered from Department Environment January until June 2019 2020. Two thousand two hundred thirty-one particles, gases (Nitrogen oxides, Sulphur Dioxide, Ozone, Carbon Monoxide) meteorological (wind speed, wind directions, temperature, relative humidity) captured. BRT model development process with an algorithm a comprehensive package, R Software its packages to understand variability trends. It was found that relationship number samples ( nt ) 4372 oob best iterations obtained. performance boosting assessed FAC2 0.91, 2 values above 0.56 (R = 0.74), Index Agreements (IOA) 0.67, which fall ranges are within acceptable performance. Relative Variable Importance (RVI) influenced PM 2.5 non-MCO CO (18.9% ), SO (14.6 %), O 3 (12.9 wd (10.66 %) while (22.6%), RH (13.4%), 14.7% (12.1%) RVI factors PM2.5 during MCO periods. Estimating strength interaction effects (SIE) 0.24 CO-wind followed 0.19 ozone-wind speeds 0.15 NO -CO. Results showed developed range could be used particles identify important parameters particle concentrations.