Forecast of daily PM 2.5 concentrations applying artificial neural networks and Holt–Winters models Luciana Maria Baptista Ventura 1,2 & Fellipe de Oliveira Pinto 2 & Laiza Molezon Soares 3 & Aderval S. Luna 3 & Adriana Gioda 1 Received: 5 November 2018 /Accepted: 21 December 2018 # Springer Media B.V., onderdeel van Springer Nature 2019 Abstract Fine particulate matter (PM 2.5 ) has been considered one of the most harmful atmospheric pollutants to the health. PM 2.5 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 PM 2.5 concentration time series. PM 2.5 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 PM 2.5 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 PM 2.5 data series showed daily concentrations ranging from 1 to 65 μgm -3 . The root mean square error (RMSE) was calculated for each model for the three sites. The HW model best explained the simulation of PM 2.5 in the industrial area, since it presented the lowest RMSE (5.8 to 14.9 μgm -3 ). The ANN was the most appropriate model for urban and rural areas with RMSE between 4.2 to 9.3 μgm -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. Keywords PM2.5 . Artificial neural network . Holt–Winter model . Meteorological conditions Introduction Fine particle (PM 2.5 ) concentrations in the air contribute to harmful health effects (Rodríguez-Cotto et al. 2014). In November 2019, the Brazilian Environmental Council (CONAMA 2018) updated air quality standards, including the standard for PM 2.5 . This update, however, will be imple- mented in steps. Initially, the intermediate standard for PM 2.5 will be 20 μgm -3 per year and 60 μgm -3 in 24 h. The final standard will meet the World Health Organization (WHO) recommendations, i.e., 10 μgm -3 or 25 μgm -3 per day. In this study, we will compare PM 2.5 levels with the guidelines recommended by the WHO. Rio de Janeiro state has the oldest air quality monitoring network in Brazil and one of the oldest in Latin America, having been in operation since the 1960s (Gioda et al. 2016). However, only in 2010 did the Rio de Janeiro network start PM 2.5 monitoring (Ventura et al. 2017a, b). Due to the mortality and morbidity caused by PM 2.5 , air pollution controls have become urgent (Liu and Peng 2018; Pope et al. 2018). Making predictions based on time series prediction techniques is fundamental to the analysis and sup- port needed for environmental agencies to make decisions (Relvas and Miranda 2018; Mehdipour et al. 2018). Statistical models of air quality forecasting have been sparsely used in South America to predict critical pollution episodes, hampering the ability to control emissions on crit- ical days (Perez 2012). There are many statistical models available to predict air pollutant concentrations, such as prin- cipal component analysis with multiple linear regression (PCA-MLR) (e.g., Ul-Saufie et al. 2013), autoregressive in- tegrated moving average (ARIMA) (e.g., Díaz-Robles et al. 2008), nearest neighbor model (NNM) (e.g., Perez 2012), Electronic supplementary material The online version of this article (https://doi.org/10.1007/s11869-018-00660-x) contains supplementary material, which is available to authorized users. * Adriana Gioda agioda@puc-rio.br 1 Department of Chemistry, Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Marquês de São Vicente Street, 225, Gávea, Rio de Janeiro, RJ 22451-900, Brazil 2 Environment Institute of Rio de Janeiro State (INEA), Rio de Janeiro, Brazil 3 University of Rio de Janeiro State (UERJ), Rio de Janeiro, RJ, Brazil Air Quality, Atmosphere & Health https://doi.org/10.1007/s11869-018-00660-x