Comparative study of ambient air quality prediction system using machine learning to predict air quality in smart city

Abstract

It is a herculean task to predict air quality of a particular area due to indefinite characteristics. As air pollution is a complex mixture of toxic air components that include ozone (O3), particulate matter 2.5_m (PM2:5), SO2, RSPM, SPM and nitrogen dioxide (NO2). These small particles penetrate deep into the alveoli as far as the bronchioles, interfering with a gas exchange within the lungs. Though research is being conducted in environmental science to evaluate the severe impact of particulate matters on public health. The capital city of Maharashtra, Nagpur is used as a case study since nearly ten thousand motor vehicles are being registered in Nagpur on a monthly basis contributing exponentially to air pollution. Various machine Learning-based algorithms are checked to compare and to find out the predictive analysis using available dataset. After comparing seven different machine learning algorithms, Boosted Random Forest algorithm was found out to be the most accurate predictive algorithm, with the maximum coefficient of determination and less mean absolute error.