An Application of Artificial Neural Network to Evaluate the Influence of Weather Conditions on the Variation of PM2.5-Bound Carbonaceous Compositions and Water-Soluble Ionic Species

Previous studies have determined biomass burning as a major source of air pollutants in the ambient Thailand. To analyse impacts meteorological parameters on variation carbonaceous aerosols and water-soluble ionic species (WSIS), numerous statistical models, including apportionment analysis with assistance principal component (PCA), hierarchical cluster (HCA), artificial neural networks (ANNs), were employed this study. A total 191 sets PM2.5 samples collected from three monitoring stations Chiang-Mai, Bangkok, Phuket July 2020 to June 2021. Hotspot numbers other obtained using NOAA-20 weather satellites coupled Global Land Data Assimilation System. Although PCA revealed that crop residue wildfires are two main sources PM2.5, ANNs highlighted importance wet deposition depletion mechanism particulate WSIS aerosols. Additionally, Mg2+ Ca2+ deeply connected albedo, plausibly owing their strong hygroscopicity CCNs responsible for cloud formation.