Air pollution poses significant health and environmental challenges, particularly in rapidly urbanizing regions. An international research team led by Ömer Ekmekçioğlu, Kayhan Bayhan, and Sena Gençoğlu from Istanbul Technical University has conducted a groundbreaking study on the utilization of artificial intelligence techniques for air quality prediction.
The study employs machine learning (ML) models to enhance the accuracy of air quality index (AQI) predictions, analyzing the complex interactions between atmospheric pollutants, meteorological variables, and environmental factors. Advanced algorithms, including XGBoost, Random Forest, Light Gradient Boosting Machine (LGBM), and deep learning models, were used to forecast future air quality conditions more precisely.
Researchers evaluated the impact of PM10, PM2.5, temperature, humidity, wind speed, and precipitation on AQI, identifying the most critical variables affecting air quality. The results indicate that machine learning models hold significant potential for improving air pollution forecasting accuracy. Notably, the XGBoost algorithm performed the best, while LGBM showed lower predictive accuracy compared to other methods.
This study could contribute to enhancing air quality predictions and supporting urban planning, environmental management, and public health policies through more robust data analytics systems. Future research will focus on integrating deep learning and AI-based hybrid models for real-time air quality forecasting.
Access the full article here: [DOI: 10.1016/B978-0-443-23816-1.00003-3]