{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T14:04:05Z","timestamp":1773324245975,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia, I.P., Portugal","doi-asserted-by":"publisher","award":["UID\/AMB\/04085\/2020"],"award-info":[{"award-number":["UID\/AMB\/04085\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CENSE","award":["UID\/AMB\/04085\/2020"],"award-info":[{"award-number":["UID\/AMB\/04085\/2020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Atmosphere"],"abstract":"<jats:p>Despite the levels of air pollution in Macao continuing to improve over recent years, there are still days with high-pollution episodes that cause great health concerns to the local community. Therefore, it is very important to accurately forecast air quality in Macao. Machine learning methods such as random forest (RF), gradient boosting (GB), support vector regression (SVR), and multiple linear regression (MLR) were applied to predict the levels of particulate matter (PM10 and PM2.5) concentrations in Macao. The forecast models were built and trained using the meteorological and air quality data from 2013 to 2018, and the air quality data from 2019 to 2021 were used for validation. Our results show that there is no significant difference between the performance of the four methods in predicting the air quality data for 2019 (before the COVID-19 pandemic) and 2021 (the new normal period). However, RF performed significantly better than the other methods for 2020 (amid the pandemic) with a higher coefficient of determination (R2) and lower RMSE, MAE, and BIAS. The reduced performance of the statistical MLR and other ML models was presumably due to the unprecedented low levels of PM10 and PM2.5 concentrations in 2020. Therefore, this study suggests that RF is the most reliable prediction method for pollutant concentrations, especially in the event of drastic air quality changes due to unexpected circumstances, such as a lockdown caused by a widespread infectious disease.<\/jats:p>","DOI":"10.3390\/atmos13091412","type":"journal-article","created":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T21:27:17Z","timestamp":1662067637000},"page":"1412","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["Using Machine Learning Methods to Forecast Air Quality: A Case Study in Macao"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7726-8820","authenticated-orcid":false,"given":"Thomas M. T.","family":"Lei","sequence":"first","affiliation":[{"name":"Institute of Science and Environment, University of Saint Joseph, Macau 999078, China"}]},{"given":"Shirley W. I.","family":"Siu","sequence":"additional","affiliation":[{"name":"Institute of Science and Environment, University of Saint Joseph, Macau 999078, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5399-995X","authenticated-orcid":false,"given":"Joana","family":"Monjardino","sequence":"additional","affiliation":[{"name":"CENSE-Center for Environmental and Sustainability Research, NOVA School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5011-9868","authenticated-orcid":false,"given":"Luisa","family":"Mendes","sequence":"additional","affiliation":[{"name":"Department of Sciences and Environmental Engineering, NOVA School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5815-2136","authenticated-orcid":false,"given":"Francisco","family":"Ferreira","sequence":"additional","affiliation":[{"name":"CENSE-Center for Environmental and Sustainability Research, NOVA School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,1]]},"reference":[{"key":"ref_1","unstructured":"WHO (2021). World Health Statistics 2021: Monitoring Health for the SDGs, Sustainable Development Goals, WHO."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"81","DOI":"10.14316\/pmp.2018.29.3.81","article-title":"Effect of Particulate Matter on Human Health, Prevention, and Imaging Using PET or SPECT","volume":"29","author":"Zaheer","year":"2018","journal-title":"Prog. Med. Phys."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"139085","DOI":"10.1016\/j.scitotenv.2020.139085","article-title":"The impact of COVID-19 partial lockdown on the air quality of the city of Rio de Janeiro, Brazil","volume":"729","author":"Dantas","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"138813","DOI":"10.1016\/j.scitotenv.2020.138813","article-title":"Indirect effects of COVID-19 on the environment","volume":"728","author":"Ruano","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"781309","DOI":"10.3389\/fdata.2022.781309","article-title":"Development of a Machine Learning Approach for Local-Scale Ozone Forecasting: Application to Kennewick, WA","volume":"5","author":"Fan","year":"2022","journal-title":"Front. Big Data"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"822573","DOI":"10.3389\/fdata.2022.822573","article-title":"Data-Driven Framework for Understanding and Predicting Air Quality in Urban Areas","volume":"5","author":"Saheer","year":"2022","journal-title":"Front. Big Data"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"842455","DOI":"10.3389\/fdata.2022.842455","article-title":"Deep Learning Approach for Assessing Air Quality During COVID-19 Lockdown in Quito","volume":"5","author":"Chau","year":"2022","journal-title":"Front. Big Data"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"103208","DOI":"10.1016\/j.jece.2019.103208","article-title":"Prediction of air pollution index (API) using support vector machine (SVM)","volume":"8","author":"Leong","year":"2020","journal-title":"J. Environ. Chem. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1016\/j.procs.2020.04.221","article-title":"Forecasting Air Pollution Particulate Matter (PM2.5) Using Machine Learning Regression Models","volume":"171","author":"Doreswamy","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Liang, Y.C., Maimury, Y., Chen, A.H.L., and Juarez, J.R.C. (2020). Machine learning-based prediction of air quality. Appl. Sci., 10.","DOI":"10.3390\/app10249151"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez, N.M., Montes, L.M., Mura, I., and Franco, J.F. (2018, January 1\u20133). Machine Learning Techniques for PM 10 Levels Forecast in Bogot\u00e1. Proceedings of the 2018 ICAI Workshops (ICAIW), Bogota, Colombia.","DOI":"10.1109\/ICAIW.2018.8554995"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Juarez, E.K., and Petersen, M.R. (2022). A Comparison of Machine Learning Methods to Forecast Tropospheric Ozone Levels in Delhi. Atmosphere, 13.","DOI":"10.3390\/atmos13010046"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Su, Y. (2020, January 23\u201325). Prediction of air quality based on Gradient Boosting Machine Method. Proceedings of the 2020 International Conference on Big Data and Informatization Education (ICBDIE), Zhangjiajie, China.","DOI":"10.1109\/ICBDIE50010.2020.00099"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/s10661-021-09333-2","article-title":"Forecasts of tropospheric ozone in the Metropolitan Area of Rio de Janeiro based on missing data imputation and multivariate calibration techniques","volume":"193","author":"Cunha","year":"2021","journal-title":"Environ. Monit. Assess."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1016\/j.mcm.2011.04.017","article-title":"Application of an SVM-based regression model to the air quality study at local scale in the Avil\u00e9s urban area (Spain)","volume":"54","year":"2011","journal-title":"Math. Comput. Model."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1007\/s11869-019-00721-9","article-title":"Macao air quality forecast using statistical methods","volume":"12","author":"Lei","year":"2019","journal-title":"Air Qual. Atmos. Health"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lei, M.T., Monjardino, J., Mendes, L., Gon\u00e7alves, D., and Ferreira, F. (2020). Statistical Forecast of Pollution Episodes in Macao during National Holiday and COVID-19. Int. J. Environ. Res. Public Health, 17.","DOI":"10.3390\/ijerph17145124"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"826517","DOI":"10.3389\/fdata.2022.826517","article-title":"Air Quality Forecast by Statistical Methods: Application to Portugal and Macao","volume":"5","author":"Mendes","year":"2022","journal-title":"Front. Big Data"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Rybarczyk, Y., and Zalakeviciute, R. (2018). Machine learning approaches for outdoor air quality modelling: A systematic review. Appl. Sci., 8.","DOI":"10.3390\/app8122570"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, Q., Yu, D., and Gu, Y. (2019). Air quality index and air pollutant concentration prediction based on machine learning algorithms. Appl. Sci., 9.","DOI":"10.3390\/app9194069"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"030001","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":"AIP Conf. Proc."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e2020GL091202","DOI":"10.1029\/2020GL091202","article-title":"Assessing the COVID-19 Impact on Air Quality: A Machine Learning Approach","volume":"48","author":"Rybarczyk","year":"2021","journal-title":"Geophys. Res. Lett."},{"key":"ref_23","first-page":"145","article-title":"Forecasting Air Quality in Taiwan by Using Machine Learning","volume":"10","author":"Lee","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, B.C., Binaykia, A., Chang, P.C., Tiwari, M.K., and Tsao, C.C. (2017). Urban air quality forecasting based on multidimensional collaborative Support Vector Regression (SVR): A case study of Beijing-Tianjin-Shijiazhuang. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0179763"},{"key":"ref_25","first-page":"120","article-title":"Prediction of PM 10 using Support Vector Regression","volume":"6","author":"Arampongsanuwat","year":"2011","journal-title":"Int. Conf. Inf. Electron. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"8049504","DOI":"10.1155\/2020\/8049504","article-title":"A Machine Learning Approach to Predict Air Quality in California","volume":"2020","author":"Castelli","year":"2020","journal-title":"Complexity"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.neucom.2017.11.077","article-title":"Feature selection in machine learning: A new perspective","volume":"300","author":"Cai","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1016\/j.procs.2016.07.111","article-title":"A Survey on Feature Selection","volume":"91","author":"Miao","year":"2016","journal-title":"Procedia Comput. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.jfds.2021.02.001","article-title":"Pairwise acquisition prediction with SHAP value interpretation","volume":"7","author":"Futagami","year":"2021","journal-title":"J. Financ. Data Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"752558","DOI":"10.3389\/frai.2021.752558","article-title":"SHAP and LIME: An Evaluation of Discriminative Power in Credit Risk","volume":"4","author":"Gramegna","year":"2021","journal-title":"Front. Artif. Intell."}],"container-title":["Atmosphere"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-4433\/13\/9\/1412\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:21:59Z","timestamp":1760142119000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-4433\/13\/9\/1412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"references-count":30,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["atmos13091412"],"URL":"https:\/\/doi.org\/10.3390\/atmos13091412","relation":{},"ISSN":["2073-4433"],"issn-type":[{"value":"2073-4433","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,1]]}}}