Predicting Air Quality Using Machine Learning Models: A Comparative Study on Pollution Data from Urban Environments

This research explores the prediction of air pollution levels through machine learning models, utilizing publicly available datasets containing parameters such as PM2.5, PM10, NO2, CO2, temperature, and humidity. The study implements Random Forest, XGBoost, and Linear Regression to compare their predictive performance. The findings highlight the efficiency of machine learning techniques in forecasting air quality and suggest potential applications in urban environmental monitoring.