Comprehensive evaluation of machine learning models for real-world air quality prediction and health risk assessment by AirQ+
| dc.contributor.author | Koçak, Ebru | |
| dc.date.accessioned | 2025-07-08T07:41:19Z | |
| dc.date.available | 2025-07-08T07:41:19Z | |
| dc.date.issued | 2025 | |
| dc.department | Mühendislik Fakültesi | |
| dc.description.abstract | This 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. | |
| dc.identifier.doi | 10.1007/s12145-025-01941-7 | |
| dc.identifier.issue | 3 | |
| dc.identifier.scopus | 105007856533 | |
| dc.identifier.scopusquality | Q2 | |
| dc.identifier.uri | https://dx.doi.org/10.1007/s12145-025-01941-7 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12451/13196 | |
| dc.identifier.volume | 18 | |
| dc.identifier.wos | 001507048600001 | |
| dc.identifier.wosquality | Q2 | |
| dc.indekslendigikaynak | Scopus | |
| dc.indekslendigikaynak | Web of Science | |
| dc.institutionauthor | Koçak, Ebru | |
| dc.language.iso | en | |
| dc.publisher | Springer Science and Business Media Deutschland GmbH | |
| dc.relation.ispartof | Earth Science Informatics | |
| dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.subject | Air Quality | |
| dc.subject | Health Risk Assessment | |
| dc.subject | Machine Learning | |
| dc.subject | Predictive Modelling | |
| dc.subject | Random Forest | |
| dc.subject | Regression | |
| dc.title | Comprehensive evaluation of machine learning models for real-world air quality prediction and health risk assessment by AirQ+ | |
| dc.type | Article |
