{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T01:27:03Z","timestamp":1792891623823,"version":"4.5.0"},"reference-count":31,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T00:00:00Z","timestamp":1600128000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>\n                    Amidst recent industrialization in South Korea, Seoul has experienced high levels of air pollution, an issue that is magnified due to a lack of effective air pollution prediction techniques. In this study, the Prophet forecasting model (PFM) was used to predict both short-term and long-term air pollution in Seoul. The air pollutants forecasted in this study were PM\n                    <jats:sub>2.5<\/jats:sub>\n                    , PM\n                    <jats:sub>10<\/jats:sub>\n                    , O\n                    <jats:sub>3<\/jats:sub>\n                    , NO\n                    <jats:sub>2<\/jats:sub>\n                    , SO\n                    <jats:sub>2<\/jats:sub>\n                    , and CO, air pollutants responsible for numerous health conditions upon long-term exposure. Current chemical models to predict air pollution require complex source lists making them difficult to use. Machine learning models have also been implemented however their requirement of meteorological parameters render the models ineffective as additional models and infrastructure need to be in place to model meteorology. To address this, a model needs to be created that can accurately predict pollution based on time. A dataset containing three years worth of hourly air quality measurements in Seoul was sourced from the Seoul Open Data Plaza. To optimize the model, PFM has the following parameters: model type, change points, seasonality, holidays, and error. Cross validation was performed on the 2017\u201318 data; then, the model predicted 2019 values. To compare the predicted and actual values and determine the accuracy of the model, the statistical indicators: mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), and coverage were used. PFM predicted PM\n                    <jats:sub>2.5<\/jats:sub>\n                    and PM\n                    <jats:sub>10<\/jats:sub>\n                    with a MAE value of 12.6 \u00b5g\/m\n                    <jats:sup>3<\/jats:sup>\n                    and 19.6 \u00b5g\/m\n                    <jats:sup>3<\/jats:sup>\n                    , respectively. PFM also predicted SO\n                    <jats:sub>2<\/jats:sub>\n                    and CO with a MAE value of 0.00124 ppm and 0.207 ppm, respectively. PFM\u2019s prediction of PM\n                    <jats:sub>2.5<\/jats:sub>\n                    and PM\n                    <jats:sub>10<\/jats:sub>\n                    had a MAE approximately 2 times and 4 times less, respectively, than comparable models. PFM\u2019s prediction of SO\n                    <jats:sub>2<\/jats:sub>\n                    and CO had a MAE approximately five times and 50 times less, respectively, than comparable models. In most cases, PFM\u2019s ability to accurately forecast the concentration of air pollutants in Seoul up to one year in advance outperformed similar models proposed in literature. This study addresses the limitations of the prior two PFM studies by expanding the modelled air pollutants from three pollutants to six pollutants while increasing the prediction time from 3 days to 1 year. This is also the first research to use PFM in Seoul, Korea. To achieve more accurate results, a larger air pollution dataset needs to be implemented with PFM. In the future, PFM should be used to predict and model air pollution in other regions, especially those without advanced infrastructure to model meteorology alongside air pollution. In Seoul, Seoul\u2019s government can use PFM to accurately predict air pollution concentrations and plan accordingly.\n                  <\/jats:p>","DOI":"10.7717\/peerj.9961","type":"journal-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T03:14:53Z","timestamp":1600139693000},"page":"e9961","source":"Crossref","is-referenced-by-count":82,"title":["Prophet forecasting model: a machine learning approach to predict the concentration of air pollutants (PM\n                    <sub>2.5<\/sub>\n                    , PM\n                    <sub>10<\/sub>\n                    , O\n                    <sub>3<\/sub>\n                    , NO\n                    <sub>2<\/sub>\n                    , SO\n                    <sub>2<\/sub>\n                    , CO) in Seoul, South Korea"],"prefix":"10.7717","volume":"8","author":[{"given":"Justin","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davesh","family":"Valagolam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serena","family":"McCalla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2020,9,15]]},"reference":[{"issue":"3","key":"10.7717\/peerj.9961\/ref-1","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1080\/19475683.2015.1057225","article-title":"Measurement and modelling of nitrogen dioxide (NO2) emissions: a marker for traffic-related air pollution in Doha, Qatar","volume":"21","author":"Al-Naimi","year":"2015","journal-title":"Annals of GIS"},{"key":"10.7717\/peerj.9961\/ref-2","article-title":"South Korea analysis: air pollution cuts lives short by more than a year","author":"Air Quality Life Index (AQLI)","year":"2019"},{"issue":"3","key":"10.7717\/peerj.9961\/ref-3","doi-asserted-by":"publisher","first-page":"162","DOI":"10.4081\/jphia.2018.813","article-title":"Global burden of diseases attributable to air pollution","volume":"9","author":"Babatola","year":"2018","journal-title":"Journal of Public Health in Africa"},{"issue":"4","key":"10.7717\/peerj.9961\/ref-4","doi-asserted-by":"publisher","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":"Chen","year":"2007","journal-title":"The American Journal of the Medical Sciences"},{"key":"10.7717\/peerj.9961\/ref-5","article-title":"Monitoring ground-level ozone from space","author":"Comis","year":"2011"},{"key":"10.7717\/peerj.9961\/ref-6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2017\/5106045","article-title":"Modeling PM2.5 urban pollution using machine learning and selected meteorological parameters","volume":"2017","author":"Deters","year":"2017","journal-title":"Journal of Electrical and Computer Engineering"},{"issue":"2","key":"10.7717\/peerj.9961\/ref-7","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/s0002-9343(99)80398-2","article-title":"Warehouse workers\u2019 headache: emergency evaluation and management of 30 patients with carbon monoxide poisoning","volume":"98","author":"Ely","year":"1995","journal-title":"The American Journal of Medicine"},{"key":"10.7717\/peerj.9961\/ref-8","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.eja.2018.06.002","article-title":"Ozone effects on crops and consideration in crop models","volume":"100","author":"Emberson","year":"2018","journal-title":"European Journal of Agronomy"},{"issue":"8","key":"10.7717\/peerj.9961\/ref-9","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1080\/10962247.2018.1459956","article-title":"Forecasting air quality time series using deep learning","volume":"68","author":"Freeman","year":"2018","journal-title":"Journal of the Air Waste Management Association"},{"issue":"9","key":"10.7717\/peerj.9961\/ref-10","doi-asserted-by":"publisher","first-page":"1431","DOI":"10.1016\/s1352-2310(01)00580-5","article-title":"An empirical approach for the prediction of daily mean PM10 concentrations","volume":"36","author":"Fuller","year":"2002","journal-title":"Atmospheric Environment"},{"issue":"2","key":"10.7717\/peerj.9961\/ref-11","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1177\/003335490712200202","article-title":"Carbon monoxide: the case for environmental public health surveillance","volume":"122","author":"Graber","year":"2007","journal-title":"Public Health Reports"},{"issue":"5","key":"10.7717\/peerj.9961\/ref-12","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1080\/10473289.2000.10464105","article-title":"Application of artificial neural networks to modeling and prediction of ambient ozone concentrations","volume":"50","author":"Hadjiiski","year":"2000","journal-title":"Journal of the Air and Waste Management Association"},{"issue":"1","key":"10.7717\/peerj.9961\/ref-13","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1063\/1.5064879","article-title":"Random forests models of particulate matter PM10: a case study","volume":"2025","author":"Ivanov","year":"2018","journal-title":"American Institue of Physics Conference Proceedings"},{"key":"10.7717\/peerj.9961\/ref-14","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.jenvman.2018.03.094","article-title":"The use of random forests in modelling short-term air pollution effects based on traffic and meteorological conditions: a case study in Wroc\u0142aw","volume":"217","author":"Kami\u0144ska","year":"2018","journal-title":"Journal of Environmental Management"},{"issue":"1","key":"10.7717\/peerj.9961\/ref-15","doi-asserted-by":"publisher","first-page":"150","DOI":"10.3390\/atmos6010150","article-title":"Variations in PM10, PM2.5 and PM1.0 in an urban area of the sichuan basin and their relation to meteorological factors","volume":"6","author":"Li","year":"2015","journal-title":"Atmosphere"},{"issue":"1","key":"10.7717\/peerj.9961\/ref-16","doi-asserted-by":"publisher","first-page":"E41","DOI":"10.3978\/j.issn.2072-1439.2016.01.18","article-title":"The effect of pollutional haze on pulmonary function","volume":"8","author":"Liu","year":"2016","journal-title":"Journal of Thoracic Disease"},{"key":"10.7717\/peerj.9961\/ref-17","volume-title":"Air pollution XXIII","author":"Longhurst","year":"2015"},{"issue":"5","key":"10.7717\/peerj.9961\/ref-18","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1016\/j.chemosphere.2004.10.032","article-title":"Potential assessment of the \u201csupport vector machine\u201d method in forecasting ambient air pollutant trends","volume":"59","author":"Lu","year":"2005","journal-title":"Chemosphere"},{"issue":"6","key":"10.7717\/peerj.9961\/ref-19","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1007\/s10098-019-01709-w","article-title":"Air pollution prediction by using an artificial neural network model","volume":"21","author":"Maleki","year":"2019","journal-title":"Clean Technologies and Environmental Policy"},{"issue":"5","key":"10.7717\/peerj.9961\/ref-20","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1111\/resp.13531","article-title":"Air pollution in the Asia-Pacific Region","volume":"24","author":"North","year":"2019","journal-title":"Respirology"},{"key":"10.7717\/peerj.9961\/ref-21","volume-title":"Artificial neural networks for pollution forecast","author":"Pasero","year":"2010"},{"key":"10.7717\/peerj.9961\/ref-22","doi-asserted-by":"publisher","first-page":"104887","DOI":"10.1016\/j.envint.2019.05.081","article-title":"Human exposure to NO2 in school and office indoor environments","volume":"130","author":"Salonen","year":"2019","journal-title":"Environment International"},{"key":"10.7717\/peerj.9961\/ref-23","doi-asserted-by":"publisher","DOI":"10.1145\/3355402.3355417","article-title":"Time series based air pollution forecasting using SARIMA and prophet model","author":"Samal","year":"2019"},{"issue":"3","key":"10.7717\/peerj.9961\/ref-24","doi-asserted-by":"publisher","first-page":"653","DOI":"10.4209\/aaqr.2013.07.0259","article-title":"Comparing the performance of statistical models for predicting PM10 concentrations","volume":"14","author":"Sayegh","year":"2014","journal-title":"Aerosol and Air Quality Research"},{"issue":"5","key":"10.7717\/peerj.9961\/ref-25","doi-asserted-by":"publisher","first-page":"2931","DOI":"10.1029\/2018gl081856","article-title":"How global warming changes the difficulty of synoptic weather forecasting","volume":"46","author":"Scher","year":"2019","journal-title":"Geophysical Research Letters"},{"issue":"8","key":"10.7717\/peerj.9961\/ref-26","doi-asserted-by":"publisher","first-page":"2598","DOI":"10.1109\/jsen.2016.2514378","article-title":"Urban air pollution monitoring system with forecasting models","volume":"16","author":"Shaban","year":"2016","journal-title":"IEEE Sensors Journal"},{"key":"10.7717\/peerj.9961\/ref-27","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1289\/ehp.7929131","article-title":"Asthma and respiratory irritants (ozone)","volume":"29","author":"Silverman","year":"1979","journal-title":"Environmental Health Perspectives"},{"issue":"1","key":"10.7717\/peerj.9961\/ref-28","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1080\/00031305.2017.1380080","article-title":"Forecasting at Scale","volume":"72","author":"Taylor","year":"2017","journal-title":"The American Statistician"},{"key":"10.7717\/peerj.9961\/ref-29","doi-asserted-by":"publisher","DOI":"10.1109\/soli.2015.7367615","article-title":"A comprehensive evaluation of air pollution prediction improvement by a machine learning method","author":"Xi","year":"2015"},{"issue":"1","key":"10.7717\/peerj.9961\/ref-30","doi-asserted-by":"publisher","first-page":"E69","DOI":"10.3978\/j.issn.2072-1439.2016.01.19","article-title":"The impact of PM2.5 on the human respiratory system","volume":"8","author":"Xing","year":"2016","journal-title":"Journal of Thoracic Disease"},{"key":"10.7717\/peerj.9961\/ref-31","doi-asserted-by":"publisher","first-page":"05001","DOI":"10.1051\/e3sconf\/201913605001","article-title":"Air pollutants prediction in shenzhen based on arima and prophet method","volume":"136","author":"Ye","year":"2019","journal-title":"E3S Web of Conferences"}],"container-title":["PeerJ"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/9961.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/9961.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/9961.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/9961.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T03:14:59Z","timestamp":1600139699000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/9961"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,15]]},"references-count":31,"alternative-id":["10.7717\/peerj.9961"],"URL":"https:\/\/doi.org\/10.7717\/peerj.9961","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2167-8359"],"issn-type":[{"value":"2167-8359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,15]]},"article-number":"e9961"}}