ABSTRACT
The air quality in cities is degrading as a result of a complex interaction between natural
and artificial environmental conditions. With the increase in urbanization and
industrialization and lack of control on emissions and use of catalytic converters, a great
amount of particulate and toxic gases are produced.
Urban air pollution prediction becomes an indispensable alternative to curb its
detrimental consequences. Modern studies in the field of environment science and
engineering show that deterministic models struggle to capture the relationship between
the concentration of atmospheric pollutants and their emission sources. The recent
advances in statistical modeling based on machine learning approaches have emerged as
solution to tackle these issues.
In this project, we implement different classification and regression techniques like
Random Forest Regression, Decision Tree Regression, Support Vector Regression and
Artificial Neural Networks, to forecast the Air Quality Index of major pollutants like
PM2.5, PM10, CO, NO2, SO2 and O3. The techniques are then evaluated using Mean
square error, Mean absolute error and R2, which show that Support Vector Regression
and Artificial Neural Networks is best suited for predicting the air quality in Indian cities.