Estimation of Air Pollution in Delhi Using Machine Learning Techniques

Urban air pollution prediction becomes an indispensable alternative to curb its detrimental consequences. Numerous machine learning techniques have been adopted to forecast the air quality. In this paper, we implemented different classification and regression techniques like Linear Regression, SDG Regression, Random Forest Regression, Decision Tree Regression, Support Vector Regression, Artificial Neural Networks, Gradient Boosting Regression and Adaptive Boosting Regression to forecast the Air Quality Index of major pollutants like PM2.5, PM10, CO, NO
2
, SO
2
and O
3
. The techniques are then evaluated using Mean square error, Mean absolute error and R
²
, which show that Support Vector Regression and Artificial Neural Networks are best suited for predicting the air quality in New Delhi.