Leveraging Hybrid Regression Models for Urban Air Quality Assessment: Development of LIDGE

Combating air pollution has become a pressing international priority because of its serious environmental and health effects. This study offers a methodical framework for ranking cities by air pollution intensity and introduces an innovative hybrid predictive model, "Lidge," designed to enhance air precision projection’s accuracy. The model is extensively refined and evaluated using performance metrics like the R2 (rate of determination) and RMSE (root mean square error) using historical pollution data. Ensemble learning methodologies are further applied during the modeling procedure to enhance predictive accuracy.