Machine Learning Approach for Predicting Air Quality Index

Air pollution has become one of the most detrimental environmental issues in the modern world. Urbanization, industrialization, and development are the foremost factors to escalate air pollution. Polluted air can create negative impacts on human health and environmental well-being. Therefore, many countries around the world are interested in assessing air quality in their living areas. Air Quality Index (AQI) values are used as metrics to evaluate daily air quality. Various machine learning algorithms are now widely used to research forecasting, predicting, and classification tasks. This paper addresses the comparative analysis of various Machine Learning Algorithms like Decision Tree, Random Forest, Support Vector Machine (SVM), and Artificial Neural Network (ANN) for predicting AQI using major pollutants: NO, NO2, CO, SO2, O-3, NH3, NOX, PM2.5, Mho, Benzene, Toluene, and Xylene. The results prove that machine-learning algorithms can be utilized appropriately to predict the AQI.