pm2.5_classifier

As air pollution is a complex mixture of toxic components with considerable impact on humans, forecasting air pollution concentration emerges as a priority for improving life quality. The research activity described in this paper concerns the study of the phenomena responsible for the urban and suburban air pollution. In this study, air quality data (observational and numerical) were used to produce daily average spot concentration forecasts of particulate matter 2.5 (PM2.5), for two stations across Delhi – Shadipur and NSIT, Dwaraka. PM2.5 refers to atmospheric particulate matter (PM) that has a diameter of less than 2.5 micrometers, which is about 3% the diameter of a human hair. The study analyzed the air-pollution principal causes and identified the best subset of features (meteorological data and air pollutants concentrations) for PM2.5 in order to predict its concentration. Overall, this study has demonstrated the potential application value of systematically collecting and analyzing datasets using machine learning techniques for the prediction of submicron sized ambient air pollutants. Various forecast models for PM2.5 were built using Linear Regression, Support Vector Machine algorithm, Multi layer perceptron neural networks (MLP NN) and XGBoost (Extreme Gradient Boosting) algorithm. The XGBoost method is also compared with the random forest algorithm, linear regression, decision tree algorithm and support vector machines using computational results. The results demonstrate that the XGBoost algorithm outperforms other methods.