AQMP: Air Quality Monitoring and Prediction using Machine Learning

In light of current human concerns, air quality monitoring is an essential step. Carbon dioxide, nitrogen dioxide, carbon monoxide, and other air pollutants are emitted when coal, wood, and natural gas are burned, as well as when automobiles, factories, and other sources of energy are burned. Air pollution can result in fatalities as well as serious illnesses including brain damage and lung cancer. The air quality index is determined with the aid of machine learning techniques. Numerous studies are being conducted in this area; however the findings are still imprecise. Air quality monitoring sites and Kaggle provide datasets that are split into two categories: training and testing. The machine learning algorithms used in this are: Support Vector Machine, Artificial Neural Network, Decision Tree, Random Forest, and Linear Regression. In this research, we provide a comparative analysis to identify the optimal model for accurately forecasting air quality with respect to data quantity and processing time. We conducted pollution prediction using four sophisticated regression techniques. We have used several datasets for pollution estimation.