{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T22:57:48Z","timestamp":1785365868470,"version":"3.55.0"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Air pollution, driven by seasonal and meteorological variations, poses a significant threat to public health and urban sustainability. Despite numerous forecasting approaches, the influence of seasonal patterns on air pollutant levels remains underexplored. This study presents a computational framework utilizing the Nonlinear Autoregressive network with Exogenous inputs (NARX) model to predict concentrations of key pollutants SO\u2082, PM\u2081\u2080, NO, NOX, and O\u2083 in Esenyurt, one of the most industrialized districts in Istanbul, Turkey. Through systematic feature selection techniques, the study determines the most influential seasonal factors for each pollutant, reducing model complexity while improving predictive accuracy. The developed framework exhibits substantial improvements in predictive performance, with the optimal models achieving high determination coefficients (up to R\u00b2\u2009=\u20090.965 for O\u2083) and low error metrics across training and validation datasets. Particularly, the inclusion of seasonal variables considerably improved prediction accuracy for NO, NO\u2082, and PM\u2081\u2080, while SO\u2082 predictions performed best when utilizing comprehensive seasonal indicators. These results demonstrate that seasonal dynamics play a crucial role in governing pollutant behavior and highlight the importance of incorporating such variables in forecasting models. This research contributes significantly to the field by advancing methodological approaches in air quality prediction while providing an adaptable model for policymakers and environmental agencies to implement in proactive pollution management strategies. Through examination of seasonal dependencies in air pollutant patterns, the study delivers a practical tool for urban planning and public health applications in rapidly expanding metropolitan regions.<\/jats:p>","DOI":"10.1371\/journal.pone.0330716","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:22:51Z","timestamp":1760376171000},"page":"e0330716","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning framework for forecasting air pollution: Evaluating seasonal and climatic influences in Istanbul, Turkey"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8451-898X","authenticated-orcid":true,"given":"Nadia","family":"AL-Rousan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hazem","family":"Al-Najjar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ismail A.","family":"Elhaty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"issue":"7","key":"pone.0330716.ref001","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1016\/j.envsoft.2010.01.010","article-title":"Air pollution, economic activity and respiratory illness: evidence from Canadian cities, 1974\u20131994","volume":"25","author":"G Koop","year":"2019","journal-title":"Environ Model Softw"},{"key":"pone.0330716.ref002","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.envsoft.2015.04.017","article-title":"An optimization platform for Poland\u2019s power sector considering air pollution and health effects","volume":"74","author":"A Wyrwa","year":"2015","journal-title":"Environ Model Softw"},{"key":"pone.0330716.ref003","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.envsoft.2018.02.009","article-title":"The Environmental Benefits Mapping and Analysis Program\u2013Community Edition (BenMAP\u2013CE): A Tool to Estimate the Health and Economic Benefits of Reducing Air Pollution","volume":"104","author":"D Sacks","year":"2018","journal-title":"Environ Model Softw"},{"key":"pone.0330716.ref004","doi-asserted-by":"crossref","first-page":"104567","DOI":"10.1016\/j.envsoft.2019.104567","article-title":"Ensemble method based on Artificial Neural Networks to estimate air pollution health risks","volume":"123","author":"LN Araujo","year":"2020","journal-title":"Environ Model Softw"},{"issue":"2","key":"pone.0330716.ref005","first-page":"300","article-title":"Air quality regression analysis over Iraq during severe dust periods using GIS and remotely sensed PM2. 5","volume":"6","author":"QM Ajaj","year":"2025","journal-title":"DYSONA-Appl Sci"},{"issue":"4","key":"pone.0330716.ref006","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1097\/MAJ.0b013e31803b900f","article-title":"Outdoor air pollution: nitrogen dioxide, sulfur dioxide, and carbon monoxide health effects","volume":"333","author":"T-M Chen","year":"2007","journal-title":"Am J Med Sci"},{"issue":"16","key":"pone.0330716.ref007","doi-asserted-by":"crossref","first-page":"2871","DOI":"10.1016\/S1352-2310(01)00071-1","article-title":"Air pollution forecast in cities by an air pollution index highly correlated with meteorological variables","volume":"35","author":"E Cogliani","year":"2001","journal-title":"Atmos Environ"},{"key":"pone.0330716.ref008","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.atmosenv.2012.01.051","article-title":"Short-term effects of air pollution on lower respiratory diseases and forecasting by the group method of data handling","volume":"51","author":"W Zhu","year":"2012","journal-title":"Atmos Environ"},{"key":"pone.0330716.ref009","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.atmosenv.2015.02.030","article-title":"Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation","volume":"107","author":"X Feng","year":"2015","journal-title":"Atmos Environ"},{"key":"pone.0330716.ref010","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.atmosenv.2016.08.050","article-title":"Influence of synoptic and local atmospheric patterns on PM10 air pollution levels: a model application to Naples (Italy)","volume":"143","author":"A Fortelli","year":"2016","journal-title":"Atmos Environ"},{"key":"pone.0330716.ref011","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.atmosenv.2018.07.058","article-title":"Spatial estimation of urban air pollution with the use of artificial neural network models","volume":"191","author":"A Alimissis","year":"2018","journal-title":"Atmos Environ"},{"key":"pone.0330716.ref012","doi-asserted-by":"crossref","first-page":"117013","DOI":"10.1016\/j.atmosenv.2019.117013","article-title":"A fast forecasting method for PM2.5 concentrations based on footprint modeling and emission optimization","volume":"219","author":"M Yu","year":"2019","journal-title":"Atmos Environ"},{"key":"pone.0330716.ref013","doi-asserted-by":"crossref","first-page":"117200","DOI":"10.1016\/j.atmosenv.2019.117200","article-title":"An enhanced interval PM2.5 concentration forecasting model based on BEMD and MLPI with influencing factors","volume":"223","author":"Z Wang","year":"2020","journal-title":"Atmos Environ"},{"issue":"3","key":"pone.0330716.ref014","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.apr.2019.11.019","article-title":"Prediction of outdoor PM2.5 concentrations based on a three-stage hybrid neural network model","volume":"11","author":"H Liu","year":"2020","journal-title":"Atmos Pollution Res"},{"issue":"3","key":"pone.0330716.ref015","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1016\/j.apr.2019.12.010","article-title":"Comparison of three prediction strategies within PM2.5 and PM10 monitoring networks","volume":"11","author":"H He","year":"2020","journal-title":"Atmos Pollution Res"},{"issue":"4","key":"pone.0330716.ref016","doi-asserted-by":"crossref","first-page":"1326","DOI":"10.1016\/j.apr.2019.03.004","article-title":"Two-step-hybrid model based on data preprocessing and intelligent optimization algorithms (CS and GWO) for NO2 and SO2 forecasting","volume":"10","author":"S Zhu","year":"2019","journal-title":"Atmos Pollution Res"},{"key":"pone.0330716.ref017","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.envsci.2016.03.008","article-title":"Improving the prediction of air pollution peak episodes generated by urban transport networks","volume":"60","author":"M Catalano","year":"2016","journal-title":"Environ Sci Policy"},{"key":"pone.0330716.ref018","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1016\/j.apr.2016.05.008","article-title":"Forecasting O3 levels in industrial area surroundings up to 24\u2009h in advance, combining classification trees and MLP models","volume":"7","author":"M Durao","year":"2016","journal-title":"Atmos Pollution Res"},{"key":"pone.0330716.ref019","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.envsoft.2016.02.030","article-title":"Air pollution prediction via multi-label classification","volume":"80","author":"G Corani","year":"2016","journal-title":"Environ Model Softw"},{"issue":"3","key":"pone.0330716.ref020","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.46488\/NEPT.2022.v21i03.018","article-title":"Time series simulation and forecasting of air quality using in-situ and satellite-based observations over an urban region","volume":"21","author":"A Choudhary","year":"2022","journal-title":"Nat Env Poll Tech"},{"key":"pone.0330716.ref021","doi-asserted-by":"crossref","DOI":"10.3389\/fenvs.2023.1132159","article-title":"Evaluating air quality and criteria pollutants prediction disparities by data mining along a stretch of urban-rural agglomeration includes coal-mine belts and thermal power plants","volume":"11","author":"A Choudhary","year":"2023","journal-title":"Front Environ Sci"},{"key":"pone.0330716.ref022","doi-asserted-by":"crossref","first-page":"103849","DOI":"10.1016\/j.pce.2024.103849","article-title":"Spatio-temporal Variations and Forecast of PM2.5 concentration around selected Satellite Cities of Delhi, India using ARIMA model","volume":"138","author":"V Sharma","year":"2025","journal-title":"Physics and Chemistry of the Earth, Parts A\/B\/C"},{"key":"pone.0330716.ref023","doi-asserted-by":"crossref","first-page":"117239","DOI":"10.1016\/j.atmosenv.2019.117239","article-title":"Characteristics and meteorological mechanisms of transboundary air pollution in a persistent heavy PM2.5 pollution episode in Central-East China","volume":"223","author":"C Shi","year":"2020","journal-title":"Atmos Environ"},{"key":"pone.0330716.ref024","doi-asserted-by":"crossref","first-page":"117072","DOI":"10.1016\/j.atmosenv.2019.117072","article-title":"A novel framework for daily forecasting of ozone mass concentrations based on cycle reservoir with regular jumps neural networks","volume":"220","author":"Y Mo","year":"2020","journal-title":"Atmos Environ"},{"issue":"12","key":"pone.0330716.ref025","doi-asserted-by":"crossref","first-page":"3915","DOI":"10.1007\/s13762-015-0821-2","article-title":"Modelling sulphur dioxide levels of Konya city using artificial intelligent related to ozone, nitrogen dioxide and meteorological factors","volume":"12","author":"S Dursun","year":"2015","journal-title":"Int J Environ Sci Technol"},{"issue":"4","key":"pone.0330716.ref026","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1016\/j.apr.2016.12.014","article-title":"Recursive neural network model for analysis and forecast of PM10 and PM2.5","volume":"8","author":"F Biancofiore","year":"2017","journal-title":"Atmos Pollution Res"},{"issue":"5","key":"pone.0330716.ref027","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1016\/j.apr.2017.01.003","article-title":"A novel hybrid-Garch model based on ARIMA and SVM for PM 2.5 concentrations forecasting","volume":"8","author":"P Wang","year":"2017","journal-title":"Atmos Pollution Res"},{"key":"pone.0330716.ref028","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.atmosenv.2012.06.004","article-title":"Assessment and prediction of air quality using fuzzy logic and autoregressive models","volume":"60","author":"JJ Carbajal-Hern\u00e1ndez","year":"2012","journal-title":"Atmos Environ"},{"issue":"5","key":"pone.0330716.ref029","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1016\/j.apr.2018.02.006","article-title":"Discovering relationships and forecasting PM10 and PM2.5 concentrations in Bogot\u00e1, Colombia, using Artificial Neural Networks, Principal Component Analysis, and k-means clustering","volume":"9","author":"F Franceschi","year":"2018","journal-title":"Atmos Pollution Res"},{"key":"pone.0330716.ref030","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1016\/j.envpol.2018.11.088","article-title":"The contribution of the Beijing, Tianjin and Hebei region\u2019s iron and steel industry to local air pollution in winter","volume":"245","author":"H Yang","year":"2019","journal-title":"Environ Pollut"},{"key":"pone.0330716.ref031","unstructured":"State Institute of Statistics, Republic of Turkey. Retrieved from http:\/\/www.turkstat.gov.tr\/Start.do in March 9, 2020."},{"issue":"3","key":"pone.0330716.ref032","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.5194\/gmd-7-1247-2014","article-title":"Root mean square error (RMSE) or mean absolute error (MAE)? \u2013 Arguments against avoiding RMSE in the literature","volume":"7","author":"T Chai","year":"2014","journal-title":"Geosci Model Dev"},{"key":"pone.0330716.ref033","doi-asserted-by":"crossref","first-page":"79","DOI":"10.3354\/cr030079","article-title":"Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance","volume":"30","author":"C Willmott","year":"2005","journal-title":"Clim Res"},{"key":"pone.0330716.ref034","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1016\/B978-0-12-809633-8.20351-8","article-title":"Performance measures for classification and regression","author":"D Berrar","year":"2019","journal-title":"Encyclopedia of bioinformatics and computational biology"},{"issue":"3","key":"pone.0330716.ref035","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.5194\/acp-11-1101-2011","article-title":"Anthropogenic sulfur dioxide emissions: 1850\u20132005","volume":"11","author":"SJ Smith","year":"2011","journal-title":"Atmos Chem Phys"},{"issue":"2","key":"pone.0330716.ref036","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1590\/S0103-50531998000200004","article-title":"Formation of ozone in urban air by photochemical oxidation of hydrocarbons: captive air experiments in Porto Alegre, RS","volume":"9","author":"E Grosjean","year":"1998","journal-title":"J Braz Chem Soc"},{"issue":"3","key":"pone.0330716.ref037","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s11869-009-0040-4","article-title":"Determination of nitrogen dioxide, sulfur dioxide, ozone, and ammonia in ambient air using the passive sampling method associated with ion chromatographic and potentiometric analyses","volume":"2","author":"AA Salem","year":"2009","journal-title":"Air Qual Atmos Health"},{"key":"pone.0330716.ref038","doi-asserted-by":"crossref","first-page":"3552","DOI":"10.1016\/j.trpro.2017.05.288","article-title":"Identifying the correlation between rainfall, traffic flow performance and air pollution concentration in Seoul using a path analysis","volume":"25","author":"H-Y Kwak","year":"2017","journal-title":"Transp Res Procedia"},{"issue":"12","key":"pone.0330716.ref039","first-page":"125006","article-title":"Investigation of the impact mechanisms and patterns of meteorological factors on air quality and atmospheric pollutant concentrations during extreme weather events in Zhengzhou city, Henan Province","volume":"4","author":"W Zeng","year":"2022","journal-title":"Environ Res Commun"},{"key":"pone.0330716.ref040","first-page":"118261","article-title":"Air pollution forecasting using machine learning models with meteorological data","volume":"248","author":"Y Zhang","year":"2021","journal-title":"Atmos Environ"},{"key":"pone.0330716.ref041","first-page":"105303","article-title":"Seasonal prediction of PM2.5 using ensemble deep learning models","volume":"149","author":"H Li","year":"2022","journal-title":"Environ Model Softw"},{"issue":"16","key":"pone.0330716.ref042","first-page":"19613","article-title":"Prediction of urban air quality using machine learning with climate factors","volume":"27","author":"M Ahmed","year":"2020","journal-title":"Environ Sci Pollution Res"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:22:59Z","timestamp":1760376179000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330716"}},"subtitle":[],"editor":[{"given":"Mahmud Iwan","family":"Solihin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":42,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0330716","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]}}}