Forecast of Hourly Tropospheric Ozone Concentration in Quang Ninh using MLP and SVM
Main Article Content
Abstract
Support vector machine (SVM) and multilayer perceptron (MLP) were used to forecast hourly tropospheric ozone concentration at three locations of Quang Ninh, namely Cao Xanh, Uong Bi and Phuong Nam. Data used to train the models are the hourly concentrations of gaseous pollutants (O3, NO, NO2, CO) and meteorological parameters including wind direction, wind speed, temperature, atmospheric pressure, relative humidity measured in the 2016. Both models accurately forecast tropospheric ozone levels compared to the observation data. The correlation coefficients (r) of the models applied for the three locations range from 0.85 to 0.91. In addition, SVM exhibits a more accurate prediction than MLP, especially for those with large variations, i.e. high standard deviations.
References
[2] I.S. Isaksen, Tropospheric Ozone: Regional and Global Scale Interactions, Springer Science & Business Media, New York, 2012.
[3] H.J. Seinfeld, N.S Pandis, Atmospheric chemistry and physics: from air pollution to climate, John Wiley & Sons Inc, New Jersey, 2016.
[4] S. Al-Alawi, S. Abdul-Wahab, Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks, Environmental Modelling & Software 17 (2002) 219–228. https://doi.org/10.1016/S1364-8152 (01) 00077-9.
[5] A. Abri, S. Eman, Modelling Atmospheric Ozone Concentration Using Machine Learning Algorithms, Loughborough University, Loughborough, 2016.
[6] EPA, Guidelines for Developing an Air Quality (Ozone and PM2.5) Forecasting Program, North Carolina, 2003.
[7] M. Awad, R. Khanna, Efficient Learning Machines: Theories, Concepts, and Applications for Engineers and System Designers, New York Apress, Berkeley, CA, 2015.
[8] H.Q. Bang, H.D. Nguyen, K. Vu, V.T. Hien, Photochemical Smog Modelling Using the Air Pollution Chemical Transport Model (TAPM-CTM) in Ho Chi Minh City, Vietnam, Environ Model Assess 24 295–310 (2019). https://doi. org/10.1007/s10666-018-9613-7
[9] H.Q. Bang, N.T. Tam, V.H.N Khue, A study on the development of ozone pollution map and ozone pollution regime in Can Tho city to propose solutions to reduce ozone pollution, Journal of Science and Technology Development 1(6) (2017) 247- 257. https://doi.org/10.32508/stdjns.v1i6.635
[10] L.H. Nghiem,N.T.K. Oanh, Comparative analysis of maximum daily ozone levels in urban areas predicted by different statistical models, Science Asia 35(3) (2009) 276–283. https://doi.org/10. 2306/scienceasia1513-1874.2009.35.276.
[11] M.D. Hung, N.T. Dung, H.X. Co, Application of machine learning to fill in the missing monitoring data of air quality, Vietnam Journal of Science and Technology 56 (2C) (2018) 104-110. https://doi. org/10.15625/2525-2518/56/2C/13036.
[12] A. Smola and S.V.N. Vishwanathan, Introduction to Machine Learning, Cambridge University Press, Cambridge, 2008.
[13] W.Z. Lu, D. Wang, Learning machines: Rationale and application in ground-level ozone prediction, Applied Soft Computing 24 (2014) 135-141. https: //doi.org/10.1016/j.asoc.2014.07.008.