{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:42:21Z","timestamp":1775245341566,"version":"3.50.1"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Air quality is directly affected by pollutant emission from vehicles, especially in large cities and metropolitan areas or when there is no compliance check for vehicle emission standards. Particulate Matter (PM) is one of the pollutants emitted from fuel burning in internal combustion engines and remains suspended in the atmosphere, causing respiratory and cardiovascular health problems to the population. In this study, we analyzed the interaction between vehicular emissions, meteorological variables, and particulate matter concentrations in the lower atmosphere, presenting methods for predicting and forecasting PM2.5.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Meteorological and vehicle flow data from the city of Curitiba, Brazil, and particulate matter concentration data from optical sensors installed in the city between 2020 and 2022 were organized in hourly and daily averages. Prediction and forecasting were based on two machine learning models: Random Forest (RF) and Long Short-Term Memory (LSTM) neural network. The baseline model for prediction was chosen as the Multiple Linear Regression (MLR) model, and for forecast, we used the naive estimation as baseline.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>RF showed that on hourly and daily prediction scales, the planetary boundary layer height was the most important variable, followed by wind gust and wind velocity in hourly or daily cases, respectively. The highest PM prediction accuracy (99.37%) was found using the RF model on a daily scale. For forecasting, the highest accuracy was 99.71% using the LSTM model for 1-h forecast horizon with 5 h of previous data used as input variables.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The RF and LSTM models were able to improve prediction and forecasting compared with MLR and Naive, respectively. The LSTM was trained with data corresponding to the period of the COVID-19 pandemic (2020 and 2021) and was able to forecast the concentration of PM2.5 in 2022, in which the data show that there was greater circulation of vehicles and higher peaks in the concentration of PM2.5. Our results can help the physical understanding of factors influencing pollutant dispersion from vehicle emissions at the lower atmosphere in urban environment. This study supports the formulation of new government policies to mitigate the impact of vehicle emissions in large cities.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fdata.2024.1412837","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T12:16:09Z","timestamp":1717071369000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Particulate matter forecast and prediction in Curitiba using machine learning"],"prefix":"10.3389","volume":"7","author":[{"given":"Marianna Gon\u00e7alves Dias","family":"Chaves","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adriel Bilharva","family":"da Silva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Em\u00edlio Graciliano Ferreira","family":"Mercuri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steffen Manfred","family":"Noe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,5,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.atmosenv.2017.05.014","article-title":"Air pollution abatement performances of green infrastructure in open road and built-up street canyon environments a review","volume":"162","author":"Abhijith","year":"2017","journal-title":"Atmos. Environ"},{"key":"B2","doi-asserted-by":"publisher","first-page":"5283","DOI":"10.1016\/j.atmosenv.2003.05.005","article-title":"Tailpipe, resuspended road dust, and brake-wear emission factors from on-road vehicles","volume":"37","author":"Abu-Allaban","year":"2003","journal-title":"Atmos. Environ"},{"key":"B3","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/s11869-010-0104-5","article-title":"Vehicle emissions and PM2.5 mass concentrations in six Brazilian cities","volume":"5","author":"Andrade","year":"2012","journal-title":"Air Quality, Atmosph. Health"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41612-020-0115-3","article-title":"Designing vegetation barriers for urban air pollution abatement: a practical review for appropriate plant species selection","volume":"3","author":"Barwise","year":"2020","journal-title":"NPJ Climate Atmosp. Sci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-021-00548-1","article-title":"Air-pollution prediction in smart city, deep learning approach","volume":"8","author":"Bekkar","year":"2021","journal-title":"J. Big Data"},{"key":"B6","unstructured":"Vehicle fleet - 2023; [frota de veiculos- 2023]2023"},{"key":"B7","doi-asserted-by":"publisher","first-page":"4173","DOI":"10.1021\/acs.est.7b05381","article-title":"Predicting daily urban fine particulate matter concentrations using a random forest model","volume":"52","author":"Brokamp","year":"2018","journal-title":"Environm. Sci. Technol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1960","DOI":"10.1016\/j.atmosenv.2006.10.041","article-title":"What are the sources and conditions responsible for exceedences of the 24h PM10 limit value (50\u03bcg m- 3) at a heavily trafficked london site?","volume":"41","author":"Charron","year":"2007","journal-title":"Atmos. Environ"},{"key":"B9","doi-asserted-by":"publisher","first-page":"264","DOI":"10.3390\/en17010264","article-title":"Wind power short-term time-series prediction using an ensemble of neural networks","volume":"17","author":"Ciechulski","year":"2024","journal-title":"Energies"},{"key":"B10","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s11869-020-00915-6","article-title":"Exploring a deep lstm neural network to forecast daily PM2.5 concentration using meteorological parameters in Kathmandu valley, Nepal","volume":"14","author":"Dhakal","year":"2021","journal-title":"Air Quality, Atmosph. Health"},{"key":"B11","doi-asserted-by":"publisher","first-page":"13765","DOI":"10.55905\/cuadv15n11-047","article-title":"Em curitiba, se anda como?","volume":"15","author":"Fochesatto","year":"2023","journal-title":"Cuadernos de Educaci\u00f3n y Desarrollo"},{"key":"B12","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1090\/conm\/112\/1087101","article-title":"Improvements of the naive approach to estimation in nonlinear errors-in-variables regression models","volume":"112","author":"Gleser","year":"1990","journal-title":"Contemp. Math"},{"key":"B13","doi-asserted-by":"publisher","first-page":"17079","DOI":"10.5194\/acp-21-17079-2021","article-title":"Investigation of near-global daytime boundary layer height using high-resolution radiosondes: first results and comparison with ERA5, MERRA-2, JRA-55, and NCEP-2 reanalyses","volume":"21","author":"Guo","year":"2021","journal-title":"Atmosph. Chem. Phys"},{"key":"B14","doi-asserted-by":"publisher","first-page":"132179","DOI":"10.1016\/j.jclepro.2022.132179","article-title":"Monitoring and modelling of PM2.5 concentration at subway station construction based on iot and LSTM algorithm optimization","volume":"360","author":"Guo","year":"2022","journal-title":"J. Clean. Prod"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41612-017-0010-8","article-title":"Urban atmospheric chemistry: a very special case for study","volume":"1","author":"Harrison","year":"2018","journal-title":"NPJ Climate Atmosph. Sci"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1002\/qj.3803","article-title":"The ERA5 global reanalysis","volume":"146","author":"Hersbach","year":"2020","journal-title":"Q. J. R. Meteorol. Soc"},{"key":"B17","doi-asserted-by":"publisher","first-page":"3279","DOI":"10.1016\/j.atmosenv.2005.01.050","article-title":"A neural network forecast for daily average PM10 concentrations in belgium","volume":"39","author":"Hooyberghs","year":"2005","journal-title":"Atmos. Environ"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2220","DOI":"10.3390\/s18072220","article-title":"A deep CNN-LSTM model for particulate matter (PM2.5) forecasting in smart cities","volume":"18","author":"Huang","year":"2018","journal-title":"Sensors"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1016\/j.jhydrol.2019.05.079","article-title":"Evaluation of random forest and regression tree methods for estimation of mass first flush ratio in urban catchments","volume":"575","author":"Jeung","year":"2019","journal-title":"J. Hydrol"},{"key":"B20","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.atmosenv.2012.03.028","article-title":"Size-segregated composition of particulate matter (PM) in major roadways and surface streets","volume":"55","author":"Kam","year":"2012","journal-title":"Atmos. Environ"},{"key":"B21","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 wroclaw","volume":"217","author":"Kami\u0144ska","year":"2018","journal-title":"J. Environ. Manage"},{"key":"B22","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1016\/j.scitotenv.2018.09.196","article-title":"A random forest partition model for predicting NO2 concentrations from traffic flow and meteorological conditions","volume":"651","author":"Kami\u0144ska","year":"2019","journal-title":"Sc. Total Environm"},{"key":"B23","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1016\/j.jes.2022.02.035","article-title":"Real-world and bottom-up methodology for emission inventory development and scenario design in medium-sized cities","volume":"127","author":"Khazini","year":"2023","journal-title":"J. Environm. Sci"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.3390\/atmos14091330","article-title":"Climatology of planetary boundary layer height over Jiangsu, China, based on ERA5 reanalysis data","volume":"14","author":"Li","year":"2023","journal-title":"Atmosphere"},{"key":"B25","doi-asserted-by":"publisher","first-page":"121975","DOI":"10.1016\/j.jclepro.2020.121975","article-title":"High temporal resolution prediction of street-level PM2.5 and NOX concentrations using machine learning approach","volume":"268","author":"Li","year":"2020","journal-title":"J. Clean. Prod"},{"key":"B26","doi-asserted-by":"publisher","first-page":"41","DOI":"10.3390\/atmos10020041","article-title":"Performance assessment of a low-cost PM2.5 sensor for a near four-month period in Oslo, Norway","volume":"10","author":"Liu","year":"2019","journal-title":"Atmosphere"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00477-023-02411-6","article-title":"Analysing and predicting the fine-scale distribution of traffic particulate matter in urban nonmotorized lanes by using wavelet transform and random forest methods","volume":"2023","author":"Luo","year":"2023","journal-title":"Stochastic Environm. Res. Risk Assessm"},{"key":"B28","first-page":"7","article-title":"\u201cPrediction of particulate matter concentration in urban environment using random forest,\u201d","volume-title":"Proceedings of the 1st International Workshop on Advances in Environmental Sensing Systems for Smart Cities, EnvSys '23","author":"Mercuri","year":"2023"},{"key":"B29","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.atmosenv.2013.04.028","article-title":"Estimation of the contribution of road traffic emissions to particulate matter concentrations from field measurements: a review","volume":"77","author":"Pant","year":"2013","journal-title":"Atmos. Environ"},{"key":"B30","doi-asserted-by":"publisher","first-page":"100608","DOI":"10.1016\/j.uclim.2020.100608","article-title":"PM2.5 forecasting in coyhaique, the most polluted city in the Americas","volume":"32","author":"Perez","year":"2020","journal-title":"Urban Climate"},{"key":"B31","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41586-019-0912-1","article-title":"Deep learning and process understanding for data-driven earth system science","volume":"566","author":"Reichstein","year":"2019","journal-title":"Nature"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1384240","DOI":"10.3389\/fdata.2024.1384240","article-title":"Tradescantia response to air and soil pollution, stamen hair cells dataset and ann colour classification","volume":"7","author":"Rodrigues","year":"2024","journal-title":"Front. Big Data"},{"key":"B33","doi-asserted-by":"publisher","first-page":"57","DOI":"10.2478\/fsmu-2023-0005","article-title":"Air pollution monitoring with hybrid and optical sensors in Curitiba and Arauc\u00e1ria, Brazil","volume":"78","author":"Rodrigues","year":"2023","journal-title":"Forest. Stud"},{"key":"B34","doi-asserted-by":"publisher","first-page":"139278","DOI":"10.1016\/j.jclepro.2023.139278","article-title":"PM2.5 air pollution prediction through deep learning using meteorological, vehicular, and emission data: a case study of New Delhi, India","volume":"427","author":"Shakya","year":"2023","journal-title":"J. Clean. Prod"},{"key":"B35","doi-asserted-by":"publisher","first-page":"3043","DOI":"10.1016\/j.scitotenv.2018.10.193","article-title":"A novel model for hourly PM2.5 concentration prediction based on CART and EELM","volume":"651","author":"Shang","year":"2019","journal-title":"Sci. Total Environm"},{"key":"B36","doi-asserted-by":"crossref","DOI":"10.1002\/9781118387023","volume-title":"Budgeting Basics and Beyond, Volume 574","author":"Shim","year":"2011"},{"key":"B37","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.envint.2019.01.016","article-title":"Estimation of daily PM10 and PM2.5 concentrations in Italy, 2013-2015, using a spatiotemporal land-use random-forest model","volume":"124","author":"Stafoggia","year":"2019","journal-title":"Environ. Int"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10661-020-8118-4","article-title":"Field performance of a low-cost sensor in the monitoring of particulate matter in Santiago, Chile","volume":"192","author":"Tagle","year":"2020","journal-title":"Environ. Monit. Assess"},{"key":"B39","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1016\/j.scitotenv.2008.06.007","article-title":"Sources and properties of non-exhaust particulate matter from road traffic: a review","volume":"400","author":"Thorpe","year":"2008","journal-title":"Sci. Total Environm"},{"key":"B40","volume-title":"World urbanization prospects: The 2018 revision. Technical report, Department of Economic and Social Affairs, Population Division","year":"2019"},{"key":"B41","unstructured":"The SDS011 Air Quality Sensor Experiment: Real-Time Air Quality Readings from the SDS0112008"},{"key":"B42","doi-asserted-by":"publisher","first-page":"20988","DOI":"10.1038\/s41598-020-77757-w","article-title":"An improved deep learning model for predicting daily PM2.5 concentration","volume":"10","author":"Xiao","year":"2020","journal-title":"Sci. Rep"},{"key":"B43","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.atmosenv.2019.04.011","article-title":"An advanced spatio-temporal model for particulate matter and gaseous pollutants in Beijing, China","volume":"211","author":"Xu","year":"2019","journal-title":"Atmos. Environ"},{"key":"B44","doi-asserted-by":"publisher","first-page":"2091","DOI":"10.1016\/j.procs.2020.03.257","article-title":"Optimizing LSTM for time series prediction in Indian stock market","volume":"167","author":"Yadav","year":"2020","journal-title":"Procedia Comput. Sci"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1412837\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T12:16:17Z","timestamp":1717071377000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1412837\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":44,"alternative-id":["10.3389\/fdata.2024.1412837"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2024.1412837","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,30]]},"article-number":"1412837"}}