Prediction of short and medium term PM₁₀ concentration using artificial neural networks

Abstract

Purpose There has been a growing concern about air quality because in recent years, industrial and vehicle emissions have resulted in unsatisfactory human health conditions. There is an urgent need for the measurements and estimations of particulate pollutants levels, especially in urban areas. As a contribution to this issue, the purpose of this paper is to use data from measured concentrations of particulate matter and meteorological conditions for the predictions of PM10. Design/methodology/approach The procedure included daily data collection of current PM10 concentrations for the city of São Carlos-SP, Brazil. These data series enabled to use an estimator based on artificial neural networks. Data sets were collected using the high-volume sampler equipment (VFA-MP10) in the period ranging from 1997 to 2006 and from 2014 to 2015. The predictive models were created using statistics from meteorological data. The models were developed using two neural network architectures, namely, perceptron multilayer (MLP) and non-linear autoregressive exogenous (NARX) inputs network. Findings It was observed that, over time, there was a decrease in the PM10 concentration rates. This is due to the implementation of more strict environmental laws and the development of less polluting technologies. The model NARX that used as input layer the climatic variables and the PM10 of the previous day presented the highest average absolute error. However, the NARX model presented the fastest convergence compared with the MLP network. Originality/value The presentation of a given PM10 concentration of the previous day improved the performance of the predictive models. This paper brings contributions with the NARX model applications.

Using an artificial neural network for estimating sustainable development goals index

“…Also, there are many examples of using ANN in environmental quality control (e.g. Bekkari and Zeddouri, 2019; Schornobay-Lui et al , 2019).…”

Investigation of PM10 prediction utilizing data mining techniques: Analyze by topic

“…In the feature selection process, the lagged PM was usually selected from raw data (Corani, 2005;Grivas & Chaloulakou, 2006;Konovalov et al, 2009;Nazif et al, 2018). In addition, the model creation process confirmed that models that included the lagged PM improved the model performance and better than the model excluding lagged PM (Cai et al, 2009;Chaloulakou et al, 2003;Schornobay-Lui et al, 2019;Wu et al, 2011).…”

“…Two popular ranges of data scaling were identified, that is, À1 to 1 (Brunelli et al, 2007;Dotse et al, 2018;Kr. Yadav et al, 2018;Popescu et al, 2013;Schornobay-Lui et al, 2019;Shekarrizfard et al, 2012;Souza et al, 2015), and 0 to 1 (Barai et al, 2009;Bisht & Seeja, 2018;Cai et al, 2009;Cortina-Januchs et al, 2015;De Mattos Neto et al, 2015;Liu et al, 2015;McKendry, 2002;Wu et al, 2011).…”

Development of the method of forecasting the atmospheric air pollution parameters based on error correction by neural-like structures of the model of successive geometric transformations

“…For example, in [12] the authors investigate a hybrid statistical-logistic model of carbon monoxide prediction. In [13], the authors have developed predictive models of air pollution based on statistics using two neural network architectures: a multilayer perceptron and a nonlinear autoregressive exogenous network. The study [14] deals with the comparison of the seasonal autoregressive integrated moving average, artificial neural network and three models of fuzzy time series using the mean absolute error and the mean square error.…”