Koçak, Ebru2025-07-082025-07-082025https://dx.doi.org/10.1007/s12145-025-01941-7https://hdl.handle.net/20.500.12451/13196This study extensively examines five distinct machine learning models used to predict hourly air particulate matter concentrations. The study used real-world data, including pollutant levels and various meteorological parameters, for model training and evaluation, making the study more reliable and effective. The study focused on capturing short-term trends in pollutant concentrations and meteorological conditions. Results showed varied model performances. The Ridge Regression model exhibited a moderate R2 value of 0.44 for PM2.5 prediction and an impressive R2 of 0.91 for PM10 prediction. Support Vector Regression showed strength in PM2.5 prediction (R2 = 0.83) but faced challenges in forecasting PM10. Random Forest and Extra Trees Regression demonstrated robust overall performance, particularly in PM10 forecasting (R2 = 0.75). Extreme Gradient Boosting displayed competitive results for both PM2.5 and PM10 (R2 = 0.80 and 0.81). Each model's identified strengths and limitations provide valuable insights for air quality management, offering a foundation for future research and the development of machine learning models in the continuous pursuit of accurate and timely air quality predictions. The AirQ+ model was used to estimate the health effects of PM2.5 exposure and predict the long-term mortality rates associated with PM2.5. The average estimated attributable proportion for all years is 10.2% (with a range of 6.5% to 13.2%). The results show differing trends in estimated mortality rates, underscoring the need for targeted interventions to reduce the public health risks associated with exposure to polluted air.eninfo:eu-repo/semantics/openAccessAir QualityHealth Risk AssessmentMachine LearningPredictive ModellingRandom ForestRegressionArticle18310.1007/s12145-025-01941-7105007856533Q2001507048600001Q2