Forecasting air quality time series using deep learning

References

• Abadi, M., A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mané, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viégas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng (2015) TensorFlow: Large-scale machine learning on heterogeneous systems. tensorflow.org (accessed January 16, 2018).
   Google Scholar
• Abdul-Wahab, S.A. 2001. IER photochemical smog evaluation and forecasting of short-term ozone pollution levels with artificial neural networks. Process Saf. Environ. Prot. 79 (2):117–128. doi:10.1205/09575820151095201.
   Google Scholar
• Achcar, J.A., E.R. Rodrigues, and G. Tzintzun. 2011. Modeling the time between ozone exceedances. Braz. J. Probab. Stat. 25 (2):183–204. doi:10.1214/10-BJPS116.
   Google Scholar
• Al-Alawi, S.M., S.A. Abdul-Wahab, and C.S. Bakheit. 2008. Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone. Environ. Modell. Software 23 (4):396–403. doi:10.1016/j.envsoft.2006.08.007.
   Web of Science ®Google Scholar
• Al-Rfou, R., G. Alain, A. Almahairi, C. Angermueller, D. Bahdanau, N. Ballas, F. Bastien, J. Bayer, A. Belikov, A. Belopolsky, et al. 2016, May. Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints abs/1605.02688.
   Google Scholar
• Amann, M., D. Derwent, B. Forsberg, O. Hnninen, F. Hurley, M. Krzyzanowski, F.D. Leeuw, S.J. Liu, C. Mandin, J. Schneider, P. Schwarze, and D. Simpson (2008). Health risks of ozone from long-range transboundary air pollution. Report, WHO Regional Office for Europe. http://www.euro.who.int/__data/assets/pdf_file/0005/78647/E91843.pdf (accessed January 17, 2018).
   Google Scholar
• Arhami, M., N. Kamali, and M.M. Rajabi. 2013. Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations. Environ. Sci. Pollut. Res. 20 (7):4777–4789. doi:10.1007/s11356-012-1451-6.
   PubMed Web of Science ®Google Scholar
• Beck, J., M. Krzyzanowski, and B. Koffi (1998). Tropospheric ozone in the European Union: The consolidated report. Report, European Environment Agency. https://publications.europa.eu/en/publication-detail/-/publication/3cacc7e4-1113-44e4-810d-ac630234fd76 (accessed January 17, 2018).
   Google Scholar
• Bei, N., G. Li, Z. Meng, Y. Weng, M. Zavala, and L. Molina. 2014. Impacts of using an ensemble Kalman filter on air quality simulations along the California-Mexico border region during Cal-Mex 2010 field campaign. Sci. Total Environ. 499 (Supplement C):141–153. doi:10.1016/j.scitotenv.2014.07.121.
   PubMedGoogle Scholar
• Bengio, Y. (2012). Practical recommendations for gradient-based training of deep architectures. CoRR 1206.5533. http://arxiv.org/abs/1206.5533.
   Google Scholar
• Biancofiore, F., M. Busilacchio, M. Verdecchia, B. Tomassetti, E. Aruffo, S. Bianco, S. Di Tommaso, C. Colangeli, G. Rosatelli, and P. Di Carlo. 2017. Recursive neural network model for analysis and forecast of PM10 and PM2:5. Atmos. Pollut. Res. 8 (4):652–659. doi:10.1016/j.apr.2016.12.014.
   Web of Science ®Google Scholar
• Biancofiore, F., M. Verdecchia, P. Di Carlo, B. Tomassetti, E. Aruffo, M. Busilacchio, S. Bianco, S. Di Tommaso, and C. Colangeli. 2015. Analysis of surface ozone using a recurrent neural network. Sci. Total Environ. 514:379–387. doi:10.1016/j.scitotenv.2015.01.106.
   PubMed Web of Science ®Google Scholar
• Brown, S. S., and J. Stutz. 2012. Nighttime radical observations and chemistry. Chem. Soc. Rev. 41 (19):6405–6447. doi:10.1039/C2CS35181A.
   PubMed Web of Science ®Google Scholar
• Calvert, J., J. Orlando, W. Stockwell, and T. Wallington. 2015. The mechanisms of reactions influencing atmospheric ozone. New York, NY: Oxford University Press. ISBN: 978-0-19-023302-0.
   Google Scholar
• Central Intelligence Agency (2015). CIA World Factbook: Middle East: Kuwait. https://www.cia.gov/library/publications/the-world-factbook/geos/ku.html. (accessed January 26, 2018)
   Google Scholar
• Chai, T., and R.R. Draxler. 2014. Root mean square error (RMSE) or mean absolute error (MAE)?-Arguments against avoiding RMSE in the literature. Geosci. Model Dev. doi:10.5194/gmd-7-1247-2014.
   Web of Science ®Google Scholar
• Chatterjee, S. K., S. Das, K. Maharatna, E. Masi, L. Santopolo, I. Colzi, S. Mancuso, and A. Vitaletti. 2017. Comparison of decision tree based classification strategies to detect external chemical stimuli from raw and filtered plant electrical response. Sens. Actuators, B 249 (Supplement C):278–295. doi:10.1016/j.snb.2017.04.071.
   Google Scholar
• Che, Z., S. Purushotham, K. Cho, D. Sontag, and Y. Liu (2016). Recurrent neural networks for multivariate time series with missing values. CoRR abs/1606.01865. http://arxiv.org/abs/1606.01865.
   Google Scholar
• Cho, J.H., and P.U. Kurup. 2011. Decision tree approach for classification and dimensionality reduction of electronic nose data. Sens. Actuators, B 160 (1):542–548. doi:10.1016/j.snb.2011.08.027.
   Web of Science ®Google Scholar
• Chollet, F. et al. 2015. Keras: Deep learning library for Theano and Tensor ow. github.com/fchollet/keras. http://github.com/fchollet/keras.(accessed February 12, 2018).
   Google Scholar
• Cooper, O.R., A. Stohl, M. Trainer, A.M. Thompson, J.C. Witte, S.J. Oltmans, G. Morris, K. E. Pickering, J.H. Crawford, G. Chen, R.C. Cohen, T.H. Bertram, P. Wooldridge, A. Perring, W.H. Brune, J. Merrill, J.L. Moody, D. Tarasick, P. Ndlec, G. Forbes, M.J. Newchurch, F.J. Schmidlin, B.J. Johnson, S. Turquety, S.L. Baughcum, X. Ren, F.C. Fehsenfeld, J.F. Meagher, N. Spichtinger, C. C. Brown, S.A. Mc-Keen, I.S. McDermid, and T. Leblanc. 2006. Large upper tropospheric ozone enhancements above midlatitude North America during summer: In situ evidence from the IONS and MOZAIC ozone measurement network. Journal of Geophysical Research: Atmospheres 111 (D24). doi:10.1029/2006JD007306.
   Web of Science ®Google Scholar
• Crosman, E.T., and J.D. Horel. 2010. Sea and lake breezes: A review of numerical studies. Boundary Layer Meteorol. 137 (1):1–29. doi:10.1007/s10546-010-9517-9.
   Web of Science ®Google Scholar
• CSB (2016). Chapter 3 population. Report, State of Kuwait Central Statistic Bureau. https://www.csb.gov.kw/Socan_Statistic_EN.aspx?ID=67.(accessed February 12, 2018).
   Google Scholar
• Cuxart, J., M.A. Jimnez, M.T. Prtenjak, and B. Grisogono. 2014. Study of a sea-breeze case through momentum, temperature, and turbulence budgets. J. Appl. Meteorol. Climatol. 53 (11):2589–2609. doi:10.1175/JAMC-D-14-0007.1.
   Web of Science ®Google Scholar
• de Oña, J., and C. Garrido. 2014. Extracting the contribution of independent variables in neural network models: A new approach to handle instability. Neural Comput. Appl. 25 (3):859–869. doi:10.1007/s00521-014-1573-5.
   Web of Science ®Google Scholar
• Dozat, T. (2016). Incorporating Nesterov momentum into ADAM. In 4th International Conference on Learning Representations. https://openreview.net/pdf?id=OM0jvwB8jIp57ZJjtNEZ.(accessed February 12, 2018).
   Google Scholar
• Duchi, J., E. Hazan, and Y. Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12:2121–2159. http://dl.acm.org/citation.cfm?id=1953048.2021068.
   Web of Science ®Google Scholar
• Elangasinghe, M.A., N. Singhal, K.N. Dirks, J.A. Salmond, and S. Samarasinghe. 2014. Complex time series analysis of PM10 and PM2:5 for a coastal site using artificial neural network modelling and k-means clustering. Atmos. Environ. 94:106–116. doi:10.1016/j.atmosenv.2014.04.051.
   Web of Science ®Google Scholar
• Ettouney, R.S., F.S. Mjalli, J.G. Zaki, M.A. ElRifai, and H.M. Ettouney. 2009. Forecasting of ozone pollution using artificial neural networks. Manage. Environ. Qual. Int. J. 20 (6):668–683. doi:10.1108/14777830910990843.
   Google Scholar
• Fan, J., Q. Li, J. Hou, X. Feng, H. Karimian, and S. Lin (2017). A spatiotemporal prediction framework for air pollution based on deep RNN. In 2nd International Symposium on Spatiotemporal Computing, Volume V-4/W2, pp. 15–22. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. DOI:10.5194/isprs-annals-IV-4-W2-15-2017.
   Google Scholar
• Feng, Y., W. Zhang, D. Sun, and L. Zhang. 2011. Ozone concentration forecast method based on genetic algorithm optimized back propagation neural networks and support vector machine data classification. Atmos. Environ. 45 (11):1979–1985. doi:10.1016/j.atmosenv.2011.01.022.
   Web of Science ®Google Scholar
• Finlayson-Pitts, B., and J.J.N. Pitts. 1993. Atmospheric chemistry of tropospheric ozone formation: Scientific and regulatory implications. Air Waste 43 (8):1091–2100. doi:10.1080/1073161X.1993.10467187.
   Google Scholar
• Freeman, B., B. Gharabaghi, J. Thé, M. Munshed, S. Faisal, M. Abdullah, and A.A. Aseed. 2017a. Mapping air quality zones for coastal urban centers. J. Air Waste Manage. Assoc. 67 (5):565–581. doi:10.1080/10962247.2016.1265025.
   PubMed Web of Science ®Google Scholar
• Freeman, B., E. McBean, B. Gharabaghi, and J. Thé. 2017b. Evaluation of air quality zone classification methods based on ambient air concentration exposure. J. Air Waste Manage. Assoc. 67 (5):550–564. doi:10.1080/10962247.2016.1263585.
   PubMed Web of Science ®Google Scholar
• Gal, Y., and Z. Ghahramani 2016. A theoretically grounded application of dropout in recurrent neural networks. ArXiv e-prints 1512.05287. https://arxiv.org/abs/1512.05287v5.
   Google Scholar
• Gardner, M.W., and S.R. Dorling. 1998. Artificial neural networks (the multilayer perceptron) A review of applications in the atmospheric sciences. Atmos. Environ. 32 (1415):2627–2636. doi:10.1016/S1352-2310(97)00447-0.
   Google Scholar
• Gheyas, I.A., and L.S. Smith. 2011. A novel neural network ensemble architecture for time series forecasting. Neurocomputing 74 (18):3855–3864. doi:10.1016/j.neucom.2011.08.005.
   Web of Science ®Google Scholar
• Glavas, S.D., and E. Sazakli. 2011. Ozone long-range transport in the Balkans. Atmos. Environ. 45 (8):1615–1626. doi:10.1016/j.atmosenv.2010.11.030.
   Web of Science ®Google Scholar
• Gomez, P., Nebot, Angela, Ribeiro, Sabrine, Alquézar, René, Mugica, Francisco,Wotawa and Franz. 2003. Local maximum ozone concentration prediction using soft computing methodologies. Syst. Anal. Modell. Simul. 43 (8):1011–1031. doi:10.1080/0232929031000081244.
   Google Scholar
• Goodfellow, I., Y. Bengio, and A. Courville. 2016. Deep Learning. Cambridge, MA: MIT Press. ISBN: 9780262035613.
   Google Scholar
• Graves, A. (2013). Generating sequences with recurrent neural networks. CoRR abs/1308.0850. http://arxiv.org/abs/1308.0850.
   Google Scholar
• Graves, A., A. Mohamed, and G.E. Hinton 2013. Speech recognition with deep recurrent neural networks. CoRR abs/1303.5778. http://arxiv.org/abs/1303.5778.
   Google Scholar
• Hinton, G.E., and S. Osindero. 2006, July. A fast learning algorithm for deep belief nets. Neural Comput. 18(7):1527–1554. doi:10.1162/neco.2006.18.7.1527.
   PubMed Web of Science ®Google Scholar
• Hochreiter, S., and J. Schmidhuber. 1997. Long short-term memory. Neural Comput. 9 (8):1735–1780. doi:10.1162/neco.1997.9.8.1735.
   PubMed Web of Science ®Google Scholar
• Hyndman, R., and G. Athanasopoulos. 2013. Forecasting: Principles and practice, Chapter 8.7 ARIMA modelling in R. Melbourne. Australia: OTexts.
   Google Scholar
• Junger, W.L., and A. Ponce De Leon. 2015. Imputation of missing data in time series for air pollutants. Atmos. Environ. 102:96–104. doi:10.1016/j.atmosenv.2014.11.049.
   Web of Science ®Google Scholar
• Junninen, H., H. Niska, K. Tuppurainen, J. Ruuskanen, and M. Kolehmainen. 2004. Methods for imputation of missing values in air quality data sets. Atmos. Environ. 38 (18):2895–2907. doi:10.1016/j.atmosenv.2004.02.026.
   Web of Science ®Google Scholar
• KAMCO 2013. State of Kuwait: Economic & financial facts. Report, KIPCO Asset Management Company KSC. http://www.kamconline.com/Temp/Reports/48218661-476e-43f1-8d12-ecc124e90e93.pdf.(accessed February 12, 2018).
   Google Scholar
• KEPA. 2017, June. Decree no. 8 of 2017 Promulgating the bylaws in accordance with the protection of external air against pollution. Kuwait: Kuwait Al Yom. 1345.
   Google Scholar
• Kingma, D.P., and J. Ba. 2014. Adam: A method for stochastic optimization. CoRR abs/1412.6980. http://arxiv.org/abs/1412.6980. (accessed February 18, 2018).
   Google Scholar
• Kuhlbusch, T.A.J., P. Quincey, G.W. Fuller, F. Kelly, I. Mudway, M. Viana, X. Querol, A. Alastuey, K. Katsouyanni, E. Weijers, A. Borowiak, R. Gehrig, C. Hueglin, P. Bruckmann, O. Favez, J. Sciare, B. Hoffmann, K. EspenYttri, K. Torseth, U. Sager, C. Asbach, and U. Quass. 2014. New directions: The future of European urban air quality monitoring. Atmos. Environ. 87:258–260. doi:10.1016/j.atmosenv.2014.01.012.
   Web of Science ®Google Scholar
• Kurt, A., B. Gulbagci, F. Karaca, and O. Alagha. 2008. An online air pollution forecasting system using neural networks. Environ. Int. 34 (5):592–598. doi:10.1016/j.envint.2007.12.020.
   PubMed Web of Science ®Google Scholar
• Le, H.Q., S.A. Batterman, and R.L. Wahl. 2007. Reproducibility and imputation of air toxics data. J. Environ. Monit. 9 (12):1358–1372. doi:10.1039/B709816B.
   PubMedGoogle Scholar
• Lelieveld, J., and F. Dentener. 2000. What controls tropospheric ozone? J. Geophys. Res. 105 (D3):3531–3551. doi:10.1029/1999JD901011.
   Web of Science ®Google Scholar
• Liu, P.-W.G. 2007. Establishment of a Box-Jenkins multivariate timeseries model to simulate ground-level peak daily one-hour ozone concentrations at Ta-Liao in Taiwan. J. Air Waste Manage. Assoc. 57 (9):1078–1090. doi:10.3155/1047-3289.57.9.1078.
   Web of Science ®Google Scholar
• Loh, W.-Y. 2011. Classification and regression trees. Data Min. Knowl. Discovery 1 (1):14–23. doi:10.1002/widm.8.
   Web of Science ®Google Scholar
• Lu, W.Z., and W.J. Wang. 2005. Potential assessment of the support vector machine method in forecasting ambient air pollutant trends. Chemosphere 59 (5):693–701. doi:10.1016/j.chemosphere.2004.10.032.
   PubMed Web of Science ®Google Scholar
• Luna, A.S., M.L.L. Paredes, G.C.G. de Oliveira, and S.M. Corra. 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. doi:10.1016/j.atmosenv.2014.08.060.
   Web of Science ®Google Scholar
• Malley, C.S., D.K. Henze, J.C. Kuylenstierna, H.W. Vallack, Y. Davila, S.C. Anenberg, M.C. Turner, and M.R. Ashmore. 2017. Updated global estimates of respiratory mortality in adults >30 years of age attributable to long-term ozone exposure. Environ. Health Perspect. 125 (8). doi:10.1289/EHP1390.
   PubMedGoogle Scholar
• Narang, S., G. Diamos, S. Sengupta, and E. Elsen, 2017. Exploring sparsity in recurrent neural networks. CoRR abs/1704.05119. http://arxiv.org/abs/1704.05119.
   Google Scholar
• Nesterov, Y. 1983. A method of solving a convex programming problem with convergence rate O(1/k2). Sov. Math. Dokl. 27 (2):372–376. https://arxiv.org/pdf/1510.08740.pdf.
   Google Scholar
• Papaleonidas, A., and L. Iliadis. 2013. Neurocomputing techniques to dynamically forecast spatiotemporal air pollution data. Evolving Syst. 4 (4):221–233. doi:10.1007/s12530-013-9078-5.
   Google Scholar
• Pascanu, R., T. Mikolov, and Y. Bengio 2013. On the difficulty of training recurrent neural networks. In 30th International Conference on Machine Learning, Volume 28. W&CP., http://proceedings.mlr.press/v28/pascanu13.pdf.
   Google Scholar
• Pedregosa, F., G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011, November. Scikit-learn: Machine learning in python. J. Mach. Learn. Res. 12:2825–230. http://dl.acm.org/citation.cfm?id=1953048.2078195.
   Web of Science ®Google Scholar
• Prybutok, V.R., J. Yi, and D. Mitchell. 2000. Comparison of neural network models with ARIMA and regression models for prediction of Houston’s daily maximum ozone concentrations. Eur. J. Oper. Res. 122 (1):31–40. doi:10.1016/S0377-2217(99)00069-7.
   Web of Science ®Google Scholar
• Raa, P., G. Aneiros, and J.M. Vilar. 2015. Detection of outliers in functional time series. Environmetrics 26 (3):178–191. doi:10.1002/env.2327.
   Web of Science ®Google Scholar
• Raschka, S. 2016. Python machine learning. Birmingham UK: Packt Publishing. ISBN: 978-1-78355-513-0.
   Google Scholar
• Silipo, R., I. Adae, A. Hart, and M. Berthold 2014. Seven techniques for data dimensionality reduction. Report, KNIME.com AG. January 12, 2018).
   Google Scholar
• Singh, K.P., S. Gupta, A. Kumar, and S.P. Shukla. 2012. Linear and nonlinear modeling approaches for urban air quality prediction. Sci. Total Environ. 426 (Supplement C):244–255. doi:10.1016/j.scitotenv.2012.03.076.
   PubMedGoogle Scholar
• Singh, K.P., S. Gupta, and P. Rai. 2013. Identifying pollution sources and predicting urban air quality using ensemble learning methods. Atmos. Environ. 80 (Supplement C):426–437. doi:10.1016/j.atmosenv.2013.08.023.
   Google Scholar
• Song, F., J. Young Shin, R. Jusino Atresino, and Y. Gao. 2011. Relationships among the springtime ground level NOx, O3 and NO3 in the vicinity of highways in the US East Coast. Atmos. Pollut. Res. 2 (3):374–383. doi:10.5094/APR.2011.042.
   Web of Science ®Google Scholar
• Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014, January. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15 (1):1929–1958. http://dl.acm.org/citation.cfm?id=2627435.2670313.
   Google Scholar
• Sutskever, I., J. Martens, G. Dahl, and G. Hinton 2013. On the importance of initialization and momentum in deep learning. In Proceedings of the 30th International Conference on Machine Learning, Volume 28. http://www.datascienceassn.org/content/importanceinitialization-and-momentum-deep-learning. (accessed February 28, 2018).
   Google Scholar
• Tarasick, D., and R. Slater. 2008. Ozone in the troposphere: Measurements, climatology, budget, and trends. Atmos. Ocean 46 (1):93–115. doi:10.3137/ao.460105.
   Web of Science ®Google Scholar
• Taspnar, F. 2015. Improving artificial neural network model predictions of daily average PM10 concentrations by applying principle component analysis and implementing seasonal models. J. Air Waste Manage. Assoc. 65 (7):800–809. doi:10.1080/10962247.2015.1019652.
   Web of Science ®Google Scholar
• Theano Development Team 2016. Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints abs/1605.02688. http://arxiv.org/abs/1605.02688.
   Google Scholar
• Thornton Joel A., Kercher, James P., Riedel, Theran P., Wagner, Nicholas L., Cozic, Julie, Holloway, John S.,  Dube, William P., Wolfe, Glenn M., Quinn, Patricia K., Middlebrook, Ann M., Alexander, Becky, Brown, Steven S. 2010. A large atomic chlorine source inferred from mid continental reactive nitrogen chemistry. Nature 464: 271–274. doi: 10.1038/nature08905.
   Google Scholar
• Tieleman, T., and G. Hinton 2012. Lecture 6.5 - RMSprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning, 4. http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf (accessed February 12, 2018).
   Google Scholar
• Vlachogianni, A., P. Kassomenos, A. Karppinen, S. Karakitsios, and J. Kukkonen. 2011. Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki. Sci. Total Environ. 409 (8):1559–1571. doi:10.1016/j.scitotenv.2010.12.040.
   PubMed Web of Science ®Google Scholar
• Voukantsis, D., K. Karatzas, J. Kukkonen, T. Rasanen, A. Karppinen, and M. Kolehmainen. 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 (7):1266–1276. doi:10.1016/j.scitotenv.2010.12.039.
   PubMed Web of Science ®Google Scholar
• Walid, and Alamsyah. 2017. Recurrent neural network for forecasting time series with long memory pattern. J. Phys. Conf. Ser. 824 (1):012038. http://stacks.iop.org/1742-6596/824/i=1/a=012038.
   Google Scholar
• Wang, D., and W.-Z. Lu. 2006. Ground-level ozone prediction using multilayer perceptron trained with an innovative hybrid approach. Ecol. Modell. 198 (34):332–340. doi:10.1016/j.ecolmodel.2006.05.031.
   Google Scholar
• Wang, P., Y. Liu, Z. Qin, and G. Zhang. 2015. A novel hybrid forecasting model for PM10 and SO2 daily concentrations. Sci. Total Environ. 505 (Supplement C):1202–1212. doi:10.1016/j.scitotenv.2014.10.078.
   PubMedGoogle Scholar
• Wang, Y., X. Ma, and M.J. Joyce. 2016. Reducing sensor complexity for monitoring wind turbine performance using principal component analysis. Renew. Energy 97:444–456. doi:10.1016/j.renene.2016.06.006.
   Web of Science ®Google Scholar
• Welch, E., X. Gu, and L. Kramer. 2005. The effects of ozone action day public advisories on train ridership in Chicago. Transp. Res. Part D: Transp. Environ. 10 (6):445–458. doi:10.1016/j.trd.2005.06.002.
   Web of Science ®Google Scholar
• Willmott, C.J., and K. Matsuura. 2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 30 (1):79–82. doi:10.3354/cr030079.
   Web of Science ®Google Scholar
• Wirtz, D.S., M.G. El-Din, A.G. El-Din, and A. Idriss. 2005. Systematic development of an artificial neural network model for real-time prediction of ground-level ozone in Edmonton, Alberta, Canada. J. Air Waste Manage. Assoc. 55 (12):1847–1857. doi:10.1080/10473289.2005.10464780.
   Web of Science ®Google Scholar
• Zickus, M., A.J. Greig, and M. Niranjan. 2002. Comparison of four machine learning methods for predicting PM10 concentrations in Helsinki, Finland. Water Air Soil Pollut. Focus 2 (5–6):717–729. doi:10.1023/A:1021321820639.
   Google Scholar