Prediction And Analysis of Air Pollution Using Machine Learning Algorithms

In the process of making countries developed, the environment is often neglected. Various inventions made to help as well as provide comfort to mankind such as automobiles, air conditioners, etc. led to the deterioration of the environment and the air quality. The major air pollutants are Carbon Monoxide (CO), Nitrogen Dioxide (NO
2
), particulate materials (PM
2.5
, SPM, and RSPM), Sulphur Dioxide (SO
2
), greenhouse gases, and Ozone(O
3
). These gases cause various respiratory diseases (such as asthma, and pulmonary cancer), Leukemia, Mesothelioma (a type of lung cancer), and premature deaths. In this paper, we have analyzed the datasets of previous years containing the values of various air pollutants such as SO
2
, NO
2
, SPM, RSPM, and PM
2.5
of years ranging from 1998 to 2020. The air quality indices (AQI) are then calculated using these values of air pollutants in the dataset to determine the air quality indices of future years in different cities of India. Supervised machine learning algorithms such as Linear Regression, Logistic Regression, Decision Tree, and Random Forest are used for model training and determination of the air quality in future years.