Enhancing Air Quality Index Forecasting through Machine Learning Models

Air pollution poses serious health risks, including respiratory issues and hospitalization. This study focuses on predicting the Air Quality Index (AQI) in Delhi, leveraging data from monitoring stations and machine learning models like linear regression, support vector regression, and tree-based methods such as decision trees and random forests. Results show that the Decision Tree Regressor outperformed other models, achieving the lowest Root Mean Squared Error (RMSE) and highest R-squared (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>) values. Incorporating and advanced preprocessing enhanced accuracy, addressing seasonal variations in air quality data. The findings emphasize the value of machine learning in accurate AQI forecasting, supporting policy decisions, and improving urban air quality management. This research highlights the critical role of predictive models in mitigating air pollution’s impact and protecting public health while suggesting pathways for future advancements in real-world applications.