Comparison of Selected Ensemble Supervised Learning Algorithms Used for Meteorological Normalisation of Particulate Matter (PM₁₀)

Air pollution, particularly PM10 particulate matter, poses significant health risks including respiratory and cardiovascular diseases as well as cancer. Accurate identification of PM10 reduction factors is therefore essential for developing effective sustainable development strategies. This study evaluated the performance of three machine learning algorithms - Decision Trees (CART), Random Forest, and Cubist Rule - in predicting PM10 concentrations and estimating long-term trends following meteorological normalisation. The research focused on Tarnów, Poland (2010-2022), with comprehensive consideration of meteorological variability. Results demonstrated superior accuracy for the Random Forest and Cubist models (R² ~0.88-0.89, RMSE ~14 μg/m³) compared to CART (RMSE 19.96 μg/m³). Air temperature and boundary layer height emerged as the most significant predictive variables across all algorithms. The Cubist algorithm proved particularly effective in detecting the impact of policy interventions, making it valuable for air quality trend analysis. While the study confirmed a statistically significant annual PM10 decrease (0.83-1.03 μg/m³), concentrations persistently exceeded both updated EU air quality standards (2024) and WHO guidelines (2021).