Air Quality, Atmosphere & Health

, Volume 12, Issue 3, pp 317–325 | Cite as

Forecast of daily PM2.5 concentrations applying artificial neural networks and Holt–Winters models

  • Luciana Maria Baptista Ventura
  • Fellipe de Oliveira Pinto
  • Laiza Molezon Soares
  • Aderval S. Luna
  • Adriana GiodaEmail author


Fine particulate matter (PM2.5) has been considered one of the most harmful atmospheric pollutants to the health. PM2.5 has as its main origin vehicular emissions, a characteristic source in megacities. In order to predict pollution episodes in different areas (rural, industrial, and urban), two models were applied, Holt–Winters (HW) and artificial neural network (ANN), using PM2.5 concentration time series. PM2.5 samples were collected using Hi-Vol samplers during a period of 24 h, every 6 days, from January 2011 to December 2013, in Rio de Janeiro, Brazil. Meteorological data was also obtained for use in the models. The PM2.5 dataset was the longest obtained for this megacity and the Holt–Winters (HW) model was used, for the first time, to predict air quality. The results of the PM2.5 data series showed daily concentrations ranging from 1 to 65 μg m−3. The root mean square error (RMSE) was calculated for each model for the three sites. The HW model best explained the simulation of PM2.5 in the industrial area, since it presented the lowest RMSE (5.8 to 14.9 μg m−3). The ANN was the most appropriate model for urban and rural areas with RMSE between 4.2 to 9.3 μg m−3. Overall, both forecast models proved accurate enough to be considered useful tools for air quality management and can be applied in other world regions.


PM2.5 Artificial neural network Holt–Winter model Meteorological conditions 



The authors are grateful to the Environment Institute of Rio de Janeiro State (INEA) for providing PM2.5 concentrations and meteorological data and to the National Council for Scientific and Technological Development (CNPq) and Foundation for Research Support of the Rio de Janeiro State (FAPERJ) for financial support. A. S. L thanks to Programa Prociência, UERJ.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interests.

Supplementary material

11869_2018_660_MOESM1_ESM.doc (104 kb)
ESM 1 (DOC 104 kb)


  1. Baghyasree T, Kumar P, Janakiraman K, Seethalakshmi R (2014) Real-time variable bit rate video traffic using a simple and efficient prediction approach. World Appl Sci J 29:48–52. Google Scholar
  2. Bezerra C (2006) Evaluation of Holt-Winters models in the solid residua forecasting: a case study in the city of Toledo – PR. In: Third International Conference on Production Research – Americas’ Region, August 2006, Curitiba, BrazilGoogle Scholar
  3. Chattopadhyay S, Chattopadhyay G (2012) Modeling and prediction of monthly total ozone concentrations by use of an artificial neural network based on principal component analysis. Pure Appl Geophys 169:1891–1908. CrossRefGoogle Scholar
  4. CONAMA (2018) Padrões de qualidade do ar, RESOLUÇÃO Nº 491, DE 19 DE NOVEMBRO DE 2018, Brazilian Environmental Council, Brasília-DFGoogle Scholar
  5. Dantas TM, Oliveira FLC, Repolho HMV (2017) Air transportation demand forecast through bagging Holt Winters methods. J Air Transp Manag 59:116–123. CrossRefGoogle Scholar
  6. Díaz-Robles L, Ortega J, Fu J, Reed G, Chow J, Watson J, Moncada-Herrera J (2008) A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: the case of Temuco, Chile. Atmos Environ 42:8331–8340. CrossRefGoogle Scholar
  7. Gioda A, Ventura LMB, Ramos MB, Silva MPR (2016) Half century monitoring air pollution in a megacity: a case study of Rio de Janeiro. Water Air Soil Pollut 227:86–103. CrossRefGoogle Scholar
  8. Godoy ML, Soluri D, Godoy JM, Roldão LA, Donagemma R (2009) Coarse and fine aerosol source apportionment in Rio de Janeiro, Brazil. Atmos Environ 43:2366–2374. CrossRefGoogle Scholar
  9. Lim C, Chang C, Mcaleer M (2009) Forecasting h(m)otel guest nights in New Zealand. Int J Hosp Manag 28:228–235. CrossRefGoogle Scholar
  10. Liu JC, Peng RD (2018) Health effect of mixtures of ozone, nitrogen dioxide, and fine particulates in 85 US counties. Air Qual Atmos Health 11:311–324. CrossRefGoogle Scholar
  11. Luna A, Paredes M, Oliveira G, Correa S (2014) Prediction of ozone concentration in tropospheric levels using artificial neural networks and support vector machine at Rio de Janeiro, Brazil. Atmos Environ 98:98–104. CrossRefGoogle Scholar
  12. Mckendry I (2002) Evaluation of artificial neural networks for fine particulate pollution (PM10 and PM2.5) forecasting. J Air Waste Manage Assoc 52:1096–1101. CrossRefGoogle Scholar
  13. Mehdipour V, Stevenson DS, Memarianfard M, Sihag P (2018) Comparing different methods for statistical modeling of particulate matter in Tehran, Iran. Air Qual Atmos Health 11:1155–1165. CrossRefGoogle Scholar
  14. Muche T (2014) Optimal operation and forecasting policy for pump storage plants in day-ahead markets. Appl Energy 113:1089–1099. CrossRefGoogle Scholar
  15. Ordieres J, Vergara E, Capuz R, Salazar R (2005) Neural network prediction model for fine particulate matter (PM2.5) on the US–Mexico border in El Paso (Texas) and Ciudad Juarez (Chihuahua). Environ Model Softw 20:547–559. CrossRefGoogle Scholar
  16. Ospina R, Zamprogno B (2003) Comparação de Algumas Técnicas de Previsão em Análise de Séries Temporais. Revista Colombiana de Estadística 26:129–157Google Scholar
  17. Perez P (2012) Combined model for PM10 forecasting in a large city. Atmos Environ 60:271–276. CrossRefGoogle Scholar
  18. Perez P, Reyes J (2006) An integrated neural network model for PM10 forecasting. Atmos Environ 40:2845–2851. CrossRefGoogle Scholar
  19. Perez P, Trier A, Reyes J (2000) Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago, Chile. Atmos Environ 34:1189–1196. CrossRefGoogle Scholar
  20. Pope CA, Ezzati M, Cannon JB, Allen RT, Jerrett M, Burnett RT (2018) Mortality risk and PM2.5 air pollution in the USA: an analysis of a national prospective cohort. Air Qual Atmos Health 11:245–252. CrossRefGoogle Scholar
  21. R Development Core Team (2014) R: a language and environment for statistical computing. ISBN 3–900051–07-0. R Foundation for Statistical Computing, Viena, AustriaGoogle Scholar
  22. Relvas H, Miranda AI (2018) An urban air quality modeling system to support decision-making: design and implementation. Air Qual Atmos Health 11:815–824. CrossRefGoogle Scholar
  23. Ribeiro A, Seruca I, Durão N (2017) Improving organizational decision support: detection of outliers and sales prediction for a pharmaceutical distribution company. Procedia Computer Science 121:282–290. CrossRefGoogle Scholar
  24. Rodríguez-Cotto R, Ortiz-Martínez M, Rivera-Ramírez E, Mateus V, Amaral B, Jiménez-Vélez B, Gioda A (2014) Particle pollution in Rio de Janeiro, Brazil: increase and decrease of pro-inflammatory cytokines IL-6 and IL-8 in human lung cells. Environ Pollut 194:112–120. CrossRefGoogle Scholar
  25. Thomas S, Jacko R (2007) Model for forecasting expressway fine particulate matter and carbon monoxide concentration: application of regression and neural network models. J Air Waste Manage Assoc 57:480–488. CrossRefGoogle Scholar
  26. Tratar LF, Strmčnik E (2016) The comparison of Holt–Winters method and multiple regression method: a case study. Energy 109:266–276. CrossRefGoogle Scholar
  27. Ul-Saufie A, Yahaya A, Ramli N, Rosaida N, Hamid H (2013) Future daily PM10 concentrations prediction by combining regression models and feed forward back propagation models with principle component analysis (PCA). Atmos Environ 77:621–630. CrossRefGoogle Scholar
  28. Veiga C, Veiga CR, Catapan A, Tortato U, Silva W (2014) Demand forecasting in food retail: a comparison between the Holt-Winters and ARIMA models. WSEAS Trans Bus Econ 11:608–614Google Scholar
  29. Ventura LMB, Pinto FO, Soares LM, Luna AS, Gioda A (2017a) Evaluation of air quality in a megacity using statistics tools. Meteorog Atmos Phys 130:361–370. CrossRefGoogle Scholar
  30. Ventura LMB, Mateus VL, De Almeida ACSL, Wanderley KB, Taira FT, Saint’Pierre TD, Gioda A (2017b) Chemical composition of fine particles (PM2.5): water-soluble organic fraction and trace metals. Air Qual Atmos Health 10:845–852. CrossRefGoogle Scholar
  31. Voukantsis D, Karatzas K, Kukkonen J, Räsänen T, Karppinen A, Kolehmainen M (2011) Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki. Sci Total Environ 409:1266–1276. CrossRefGoogle Scholar
  32. WHO (2006) Air quality guidelines for particulate matter, ozone, nitrogen dioxide and sulphur dioxide. Global update 2005. Summary of Risk Assessment. World Health Organization, GenevaGoogle Scholar
  33. Winters P (1960) Forecasting sales by exponentially weighted moving averages. Manag Sci 6:324–342. CrossRefGoogle Scholar

Copyright information

© Springer Media B.V., onderdeel van Springer Nature 2019

Authors and Affiliations

  1. 1.Department of ChemistryPontifical Catholic University of Rio de Janeiro (PUC-Rio)Rio de JaneiroBrazil
  2. 2.Environment Institute of Rio de Janeiro State (INEA)Rio de JaneiroBrazil
  3. 3.University of Rio de Janeiro State (UERJ)Rio de JaneiroBrazil

Personalised recommendations