Estimating Monthly PM2.5 Levels using Integrated Satellite and Meteorological Data: A Case Study of Suphan Buri Province, Thailand

PM2.5 is an air pollutant that causes respiratory diseases. However, in some areas of Suphan Buri Province, Thailand, there are no monitoring stations for early warning. This study integrated satellite data and meteorological data to develop a linear regression model for predicting monthly PM2.5 levels. The predictions were made for two grid sizes: 5×5 km and 10×10 km. The independent variables were satellite data and meteorological data, including Aerosol Optical Depth (AOD), hotspots, air temperature, and relative humidity. The dependent variable was PM2.5 data from five ground-based monitoring stations. After developing a multiple linear regression model, the results showed that the model had R-squared values of 0.665 and 0.760, respectively. Furthermore, model validation showed that the predicted PM2.5 had root mean square errors (RMSE) of 12.82 mg/m<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> and 11.53 mg/m<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> respectively.