Identification and Mitigation Process for the Air Quality Using Machine Learning Techniques

The quality of air is a precious resource. The Environmental Protection Agency (EPA) keeps an eye on the adulterants that are typically considered to be criteria levels, such as nitrogen dioxide, particulates (PM10 and PM2.5), carbon monoxide, sulfur dioxide, and ground-position ozone (O3) Nitrogen dioxide (NO2). The air quality index (AQI), a frequently used indicator that depicts how clean or polluted the air is currently. It will display the local air quality in real time, and the higher its value, the worse the local air quality is. It is simple to divide the AQI indicator into six categories and a variety of bracket norms. In the existing system, the AQI values increases if there is a higher concentration of SO2 or NO2 and it also grounded the variables PM10 and PM2.5. We proposed KNN algorithm, which is a function of SO2, NO2, RSPM, and SPM. It contains two basic steps, firstly it will calculate the AQI then based on AQI value it will present the quality of air. In the second step it will analyze AQI value and it recommended the composition control mechanisms to maintain good air quality.