Prediction and analysis of particulate matter (PM2.5 and PM10) concentrations using machine learning techniques

The National Capital Region (NCR) encircling the capital of India is the one of the most polluted regions in the world. Poor air quality is a cause of a number of diseases and reduction in life span. Particulate matter (PM) is the most significant as well as the most hazardous air pollutant in this region. This work proposes to build models to analyze and forecast PM concentrations at a location in the NCR. The correlation between PM concentrations in different seasons and with meteorological parameters and other air pollutants is studied to determine the most suitable explanatory variables for building the forecast models. The performance of the proposed models is evaluated with the help of variable importance ranking (VIR), partial plots and measures such as mean error, absolute mean error and root mean square error.