Air Quality Forecasting Using Machine Learning: Comparative Analysis and Ensemble Strategies for Enhanced Prediction
Water, Air, and Soil Pollution, vol.236, no.7, 2025 (SCI-Expanded, Scopus)
- Publication Type: Article / Article
- Volume: 236 Issue: 7
- Publication Date: 2025
- Doi Number: 10.1007/s11270-025-08122-8
- Journal Name: Water, Air, and Soil Pollution
- Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, ABI/INFORM, Agricultural & Environmental Science Database, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), Artic & Antarctic Regions, BIOSIS, Biotechnology Research Abstracts, CAB Abstracts, Chemical Abstracts Core, Chimica, Compendex, Environment Index, Geobase, Greenfile, Pollution Abstracts, Veterinary Science Database, Civil Engineering Abstracts
- Keywords: Air Quality Prediction, Bayesian Optimization, Machine Learning, Regression Models, SVR
- Yozgat Bozok University Affiliated: Yes
Abstract
Air pollution poses a critical challenge to environmental sustainability, public health, and urban planning. Accurate air quality prediction is essential for devising effective management strategies and early warning systems. This study utilized a dataset comprising hourly measurements of pollutants such as PM2.5, NOx, CO, and benzene, sourced from five metal oxide sensors and a certified analyzer in a polluted urban area, totaling 9,357 records collected over one year (March 2004–February 2005) from the Kaggle Air Quality Data Set. A comprehensive comparison of ten machine learning regression models XGBoost, LightGBM, Random Forest, Gradient Boosting, CatBoost, Support Vector Regression (SVR) with Bayesian Optimization, Decision Tree, K-Nearest Neighbors (KNN), Elastic Net, and Bayesian Ridge was conducted. Model performance was enhanced through Bayesian optimization and randomized cross-validation, with stacking employed to leverage the strengths of base models. Experimental results showed that hyperparameter optimization and ensemble strategies significantly improved accuracy, with the SVR model optimized via Bayesian optimization achieving the highest performance: an R2 score of 99.94%, MAE of 0.0120, and MSE of 0.0005. These findings underscore the methodology’s efficacy in precisely capturing the spatial and temporal dynamics of air pollution.