One Step Ahead Prediction of Ozone Concentration for Determination of Outdoor Air Quality Level

Year 2021, Volume: 9 Issue: 1, 45 - 54, 30.06.2021

Waleed Mahmood , Ercan Avşar

https://doi.org/10.51354/mjen.869736

Cited By: 2

Abstract

With the rapid spread of urbanization, competent authorities become increasingly anxious from air pollution risks and effect on citizens especially those with respiratory diseases. In this work, performances of six machine learning methods were analyzed for prediction of maximum ozone (O_3) concentration for the next-day. The models make the prediction using concentrations of six atmospheric components (PM2.5, PM10, Ozone (O3), Sulfur Dioxide (SO2), Nitrogen Dioxide (NO2), and Carbon Monoxide (CO)). The utilized machine learning methods are multilayer perception (MLP), Support Vector Regression (SVM), k-Nearest Neighbor (K-NN), Random Forests (RF), Gradient Boosting (GB), and Elastic Net (EN). After the predictions made by these models, the predicted values were further processed to be classified into one of the six air quality levels defined by United States Environmental Protection Agency. The prediction performances of the models as well as their corresponding classification results were analyzed. It was shown that MLP model gives the lowest RMSE of 2246 for prediction step while SVR achieved the highest accuracy score of 0.790.

Keywords

machine learning, time-series forecasting, regression methods, sequence-to-sequence, air quality index.

References

• [1] Niall McCarthy, “Air Pollution Contributed to More Than 6 Million Deaths in 2016, Data journalist covering technological”, societal and media topics, 2016.
• [2] P.Rafaj, G.Kiesewetter , T.Gul, W.Schoppa, J.Cofala, Z.Klimont, P.Purohit, C.Heyes, M.Amann, J.Borken-Kleefeld, L.Cozzi. Outlook for clean air in the context of sustainable development goals. : Global Environmental Change, September 2018.
• [3] OECD (2012), OECD Environmental Outlook to 2050, OECD PUBLISHING. https://dx.doi.org/10.1787/9789264122246-en.
• [4] Aloke Ghoshal, Pradyut Waghray, George Dsouza, Mahip Saluja, Mayank Agarwal, Ashish Goyal, Sneha Limaye, Akash Balki, Sudhir Bhatnagar, Manish Jain, Sharad Tikkiwal, Abhijit Vaidya, Meena Lopez, Rashmi Hegde, Jaideep Gogtay, “Real-world evaluation of the clinical safety and efficacy of fluticasone/formoterol FDC via the Revolizer in patients with persistent asthma in India”, On 25 November 2019, 10.1016/j.pupt.2019.101869.
• [5] Burden of disease from ambient air pollution for 2016, 1211 Geneva 27, World Health Organization 2018. https://www.who.int.
• [6] World Health Organization, Ambient air pollution: a global assessment of exposure and burden of disease, 2016, https://apps.who.int/iris/handle/10665/250141.
• [7] X. Li, Ling Jin, and H. Kan, Air pollution: a global problem needs local fixes, 25 JUNE 2019, china, https://doi.org/10.1038/d41586-019-01960-7.
• [8] Blondeau, P., Iordache, V., Poupard, O., Genin, D., Allard, F., 2005. Relationship between outdoor and indoor air quality in eight French schools. Indoor Air 15, 2–12, 10.1111/j.1600-0668.2004.00263.
• [9] Brian S. Freeman, G. Taylor, B. Gharabaghi, and Jesse Thé, forecasting air quality time series using deep learning, 24 May 2018. https://doi.org/10.1080/10962247.2018.1459956.
• [10] Nesreen K. Ahmed, Amir F. Atiya , N.El Gayar &H. El-Shishiny, An Empirical Comparison of Machine Learning Models for Time Series Forecasting, 15 Sep 2010. https://doi.org/10.1080/07474938.2010.481556.
• [11] Ping-Feng Pai, Kuo-Ping Lin, Chi-Shen Lin, and Ping-Teng Chang, Time series forecasting by a seasonal support vector regression model, June 2010, https://doi.org/10.1016/j.eswa.2009.11.076.
• [12] Francisco S. de Albuquerque Filho, Francisco Madeiro e Sérgio M. M. Fernandes, Paulo S. G., de Mattos Neto, and Tiago A. E. Ferreira, Time-series forecasting of pollutant concentration levels using particle swarm optimization and artificial neural networks, Paulo 2013. http://dx.doi.org/10.1590/S0100-40422013000600007.
• [13] James R. Lloyd, GEFCom2012 hierarchical load forecasting: Gradient boosting machines and Gaussian processes, 16 August 2013. https://doi.org/10.1016/j.ijforecast.2013.07.002.
• [14] H.Tyralis, and G.Papacharalampous, Variable Selection in Time Series Forecasting Using Random Forests, 4 October 2017. https://doi.org/10.3390/a10040114.
• [15] M. M. Dedovic, S. Avdakovic, I. Turkovic, N. Dautbasic, and T. Konjic, Forecasting PM10 concentrations using neural networks and system for improving air quality, 08 December 2016, 10.1109/BIHTEL.2016.7775721.
• [16] Bing-Chun Liu, A. Binaykia, P. Chang, M.K. Tiwari, C.-C. Tsao, urban air quality forecasting based on multi-dimensional collaborative Support Vector Regression (SVR): A case study of Beijing-Tianjin-Shijiazhuang. July 14, 2017, https://doi.org/10.1371/journal.pone.0179763.
• [17] H.Zheng ,H. Li, X. Lu, and T. Ruan, A Multiple Kernel Learning Approach for Air Quality Prediction, 12 Jun 2018, https://doi.org/10.1155/2018/3506394.
• [18] F. Martínez, M. P. Frías, F. Charte and A. J. Rivera, Time Series Forecasting with KNN in R: the tsfknn Package, December 2019, ISSN 2073-4859.
• [19] K.Maheshwari and S. Lamba, Air Quality Prediction using Supervised Regression Model, 03 February 2020, 10.1109/ICICT46931.2019.8977694.
• [20] Fang Shen, Jing Liu, and Kai Wu, Multivariate Time Series Forecasting based on Elastic Net and High-Order Fuzzy Cognitive Maps: A Case Study on Human Action Prediction through EEG Signals, 29 May 2020. 10.1109/TFUZZ.2020.299851.
• [21] World's Air Pollution: Real-time Air Quality Index, http://waqi.info/.
• [22] Eusebio Jarauta-Bragulat, Carme Hervada-Sala, Juan Jose Egozcue, Air Quality Index Revisited from a Compositional Point of View, published online: 23 May 2015 © International Association for Mathematical Geosciences 2015 .
• [23] A. Sanjivanrao More, D.Sunil Ranaware, B. D. Wamane, and G. S. Salunkhe, Enhancement in Financial Time Series Prediction with Feature Extraction in Text Mining Techniques, Nov 2019, 2395-0056, International Research Journal of Engineering and Technology (IRJET).
• [24] V. N. Vapnik, An overview of statistical learning theory, Sept. 1999.10.1109/72.788640.
• [25] N. I. Pankevych, R.Sankar, Time Series Prediction Using Support Vector Machines: A Survey, 24 April 2009. 10.1109/MCI.2009.932254.
• [26] M. Awad, R.Khanna, Efficient Learning Machines (chapter: Support Vector Regression, Pages 67-80), 27 April 2015. https://doi.org/10.1007/978-1-4302-5990-9
• [27] F.Martínez, M. P. Frías, M. D. Pérez, and A. J. Rivera, a methodology for applying k-nearest neighbor to time series forecasting, 21 NOV 2019. https://doi.org/10.1007/s10462-017-9593-z.
• [28] J. Kukkonen, L. Partanen, A. Karppinen, J. Ruuskanen, H. Junninen, M. Kolehmainen, H. Niska, S. Dorling, T. Chatterton, R. Foxall, and G.Cawle, extensive evaluation of neural network models for the prediction of NO2 and PM10 concentrations, compared with a deterministic modelling system and measurements in central Helsinki, 22 Aug 2003. https://doi.org/10.1016/S1352-2310(03)00583-1.
• [29] S. Touzani, J. Granderson, and S. Fernandes, Gradient boosting machine for modelling the energy consumption of commercial buildings, Nov 2017. https://doi.org/10.1016/j.enbuild.2017.11.039.
• [30] Max Kuhn, Kjell Johnson, Applied Predictive Modeling, New York 2013, https://doi.org/10.1007/978-1-4614-6849-3.
• [31] Hui Zou, and Trevor Hasti, Regularization and variable selection via the elastic net, 09 March 2005, https://doi.org/10.1111/j.1467-9868.2005.00503.x.
• [32] Z. Yu, and Z. Niu; W. Tang, Deep Learning for Daily Peak Load Forecasting—A Novel Gated Recurrent Neural Network Combining Dynamic Time Warping, 29 January 2019, 10.1109/ACCESS.2019.2895604.
• [33] C. S. Malley, D. K. Henze, Johan C.I. Kuylenstierna, H. W. Vallack, Y. Davila, S. C. Anenberg, M. C. Turner, and M. R. Ashmore, Updated Global Estimates of Respiratory Mortality in Adults ≥30 Years of Age Attributable to Long-Term Ozone Expos, 28 August 2017, https://doi.org/10.1289/EHP1390.
• [34] Nan-Hung Hsieh, Chung-Min Liao, Fluctuations in air pollution give risk warning signals of asthma hospitalization, August 2013, https://doi.org/10.1016/j.atmosenv.2013.04.043.
• [35] S. Du, T. Li, and Shi-Jinn Horng,Time Series Forecasting Using Sequence-to-Sequence Deep Learning Framework, 02 May 2019, 10.1109/PAAP.2018.00037.
• [36] T.Liu, A. K. H. Lau, K. Sandbrink, J. C. H. Fung,Time Series Forecasting of Air Quality Based On Regional Numerical Modeling in Hong Kong, 24 March 2018, https://doi.org/10.1002/2017JD028052.
• [37] NICOLÒ BALDON, Time series Forecast of Call volume in Call Centre using Statistical and Machine Learning Methods, Sweden 2019, urn:nbn:se:kth:diva-265002.
• [38] S. G. Gocheva-Ilieva, A. V. Ivanov, D. S.Voynikova, and D. T. Boyadzhiev, Time series analysis and forecasting for air pollution in small urban area: an SARIMA and factor analysis approach, 25 September 2013, https://doi.org/10.1007/s00477-013-0800-4.
• [39] G. Papacharalampous, H. Tyralis, and D. Koutsoyiannis, Univariate Time Series Forecasting of Temperature and Precipitation with a Focus on Machine Learning algorithms: a Multiple-Case Study from Greece, 29 November 2018, https://doi.org/10.1007/s11269-018-2155-6.