Applying regression model to create air quality map in Tien Giang province

Abstract

Air pollution can cause many health problems, such as asthma, lung cancer, heart disease and stroke. Causes of air pollution include airborne contaminants, which can be solid particles, liquid droplets, or gases. Pollutants are often of natural or man-made origin. Therefore, assessing the quality of the environment in general and the air environment in particular is an urgent issue that needs attention and timely solutions. The approach in this article is to use a combination of remote sensing and GIS to calculate the correlation coefficient, thereby establishing a regression equation between the air quality index at measuring stations and the radiation value of the spectrum channels on Landsat 8 satellite images. The result is to find a univariate third-order linear regression equation with the coefficient R2=0.511137922. Testing the regression equation with 4 monitoring stations, the results achieved accuracy with RMSE=2.5.

Key words: Correlation – Regression; air pollution; Air Quality Index (AQI); GIS; Landsat.