© 2020 IIETA. This article is published by IIETA and is licensed under the CC BY 4.0 license (http://creativecommons.org/licenses/by/4.0/).
OPEN ACCESS
Roadside air pollution is a major issue due to its adverse effects on human health and the environment. This highlights the need for parsimonious and robust forecasting tools that help vulnerable members of the public reduce their exposure to harmful air pollutants. Recent results in air pollution forecasting applications include the use of hybrid models based on non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable inputs (NARX) and wavelet decomposition techniques. However, attempts employing both methods into one hybrid modelling system have not been widely made. Hence, this work further investigates the utilisation of wavelet-based NARX-ANN models in the shortand long-term prediction of hourly NO2 concentration levels. The models were trained using emissions and meteorological data collected from a busy roadside site in Central London, United Kingdom from January to December 2015. A discrete wavelet transformation technique was then implemented to address the highly variable characteristic of the collected NO2 concentration data. Overall results exhibit the superiority of the wavelet-based NARX-ANN models improving the accuracy of the benchmark NARX-ANN model results by up to 6% in terms of explained variance. The proposed models also provide fairly accurate long-term forecasts, explaining 68–76% of the variance of actual NO2 data. In conclusion, the findings of this study demonstrate the high potential of wavelet-based NARX-ANN models as alternative tools in short- and long-term forecasting of air pollutants in urban environments.
artificial neural networks, air pollution, air pollution forecasting, NARX, wavelet transform
[1] Baklanov, A. et al., Integrated systems for forecasting urban meteorology, air pollution and population exposure. Atmospheric Chemistry and Physics, 7, pp. 855–874, 2007.
[2] Dunea, D., Pohoata, A., & Iordache, S., Using wavelet–feedforward neural networks to improve air pollution forecasting in urban environments. Environmental Monitoring and Assessment, 187(7), 2015.
[3] Moustris, K. P., Ziomas, I. C. & Paliatsos, A. G., 3-day-ahead forecasting of regional pollution index for the pollutants NO2, CO, SO2, and O3 using artificial neural networks in Athens, Greece. Water Air Soil Pollution, 209(1–4), pp. 29–43, 2010.
[4] Bishop, C. M., Neural Networks for Pattern Recognition. New York, NY: Oxford University Press, Inc., 1995.
[5] Ordieres, J. B., Vergara, E. P., Capuz, R. S. & Salazar, R. E., Neural network prediction model for fine particulate matter (PM2.5) on the US–Mexico border in El Paso (Texas) and Ciudad Juárez (Chihuahua). Environmental Model Software, 20(5), pp. 547–559, 2005.
[6] Capilla, C., Multilayer perceptron and regression modelling to forecast hourly nitrogen dioxide concentrations. WIT Transactions on Ecology and the Environment, 183, pp. 39–48, 2014.
[7] Cabaneros, S. M. S., Calautit, J. K. S. & Hughes, B. R., Hybrid Artificial Neural Network Models for Effective Prediction and Mitigation of Urban Roadside NO2 Pollution. Energy Procedia, 142, pp. 3524–3530, 2017.
[8] Catalano, M., Galatioto, F., Bell, M., Namdeo, A. & Bergantino, A. S., Improving the prediction of air pollution peak episodes generated by urban transport networks. Environmental Science & Policy, 60, pp. 69–83, 2016.
[9] Gong, B. & Ordieres-Meré, J., Prediction of daily maximum ozone threshold exceedances by preprocessing and ensemble artificial intelligence techniques: Case study of Hong Kong. Environmental Model Software, 84, pp. 290–303, 2016.
[10] Li, C., Liang, M. & Wang, T., Criterion fusion for spectral segmentation and its application to optimal demodulation of bearing vibration signals. Mechanical Systems and Signal Processing, 64–65, pp. 132–148, 2015.
[11] Hagan, M. T., Demuth, H. B. & Beale, M. H., Neural Network Design, Vol. 2. PWS: Boston, MA, p. 734, 1995.
[12] Siwek, K. & Osowski, S., Engineering Applications of artificial intelligence improving the accuracy of prediction of PM 10 pollution by the wavelet transformation and an en semble of neural predictors. Engineering Applications of Artificial Intelligence, 25(6), pp. 1246–1258, 2012.
[13] Bai, Y., Li, Y., Wang, X., Xie, J. & Li, C., Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions. Atmospheric Pollution Research, 7(3), pp. 557–566, 2016.
[14] F. & R. A. (Defra) webmaster@defra.gsi.gov.u. Department for Environment. Automatic Urban and Rural Network (AURN) – Defra, UK. 2017.
[15] The Guardian. London breaches annual air pollution limit for 2017 in just five days | Environment | The Guardian. 2017. [Online]. Available at https://www.theguardian.com/environment/2017/jan/06/london-breaches-toxic-air-pollution-limit-for-2017-injust- five-days, (accessed 26 March 2019).
[16] World Health Organization. Health Aspects of Air Pollution with Particulate Matter, Ozone and Nitrogen Dioxide Report on a WHO Working Group Ozone-adverse effects Nitrogen Dioxide-adverse effects Air Pollutants, Environmental-adverse effects Metaanalysis Air-standards Guidelines, 2003.
[17] Santos, P. J. Martins, A. G. & Pires, A. J., Designing the input vector to ANN-based models for short-term load forecast in electricity distribution systems. Electrical Power & Energy Systems, 29, pp. 338–347, 2007.
[18] Li, K. H., Le, N. H. U. D., Sun, L. I. & Zidek, J. V, Spatial-temporal models for ambient hourly PM 10 in Vancouver. Environmetrics, 338, 1999.
[19] Mallat, S. G., A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(7), pp. 674–693, 1989.
[20] Daubechies, I., Ten Lectures on Wavelets. Philadelphia, PA: SIAM Press, 1988.
[21] Osowski, S. & Garanty, K., Forecasting of the daily meteorological pollution using wavelets and support vector machine. Engineering Applications of Artificial Intelligence, 20(6), pp. 745–755, 2007.
[22] Hornik, K., Stinchcombe, M. & White, H., Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), pp. 359–366, 1989.
[23] The MathWorks, I., MATLAB Documentation – MathWorks United Kingdom. [Online]. Available at https://uk.mathworks.com/help/matlab/index.html (accessed 27 February 2019).
[24] Turias, I. J., González, F. J., Martin, M. L. & Galindo, P. L., Prediction models of CO, SPM and SO2 concentrations in the Campo de Gibraltar Region, Spain: a multiple comparison strategy. Environmental Monitoring and Assessment, 143(1–3), pp. 131–146, 2008.
[25] Solaiman, T. A., Coulibaly, P., & Kanaroglou, P., Ground-level ozone forecasting using data-driven methods. Air Quality, Atmosphere and Health, 1(4), pp. 179–193, 2008.