Skip Navigation Links
Journal of Environmental Accounting and Management
António Mendes Lopes (editor), Jiazhong Zhang(editor)
António Mendes Lopes (editor)

University of Porto, Portugal


Jiazhong Zhang (editor)

School of Energy and Power Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi Province 710049, China

Fax: +86 29 82668723 Email:

Comparative Analysis of Tree, Meta-learning and Function Classifiers to Predict the Atmospheric Concentration of NO2

Journal of Environmental Accounting and Management 8(1) (2020) 31--39 | DOI:10.5890/JEAM.2020.03.003

Adven Masih

Department of System Analysis and Decision Making, Ural Federal University, 19 Mira, Ekaterinburg, 620002, Sverdlovskaya oblast, Russian Federation

Download Full Text PDF



The concentration of airborne pollutants is rising in recent years. Due to serious health effects of NO2, SO2 etc. their constant monitoring is important for the policy makers, as it provides early pollution estimates before it crosses permissible limits set by the state. For air quality modelling, several statistical techniques based on Artificial Neural Networks have been applied, however, Tree and meta-learning based classifiers have rarely been adopted for air pollution prediction purpose. Thus, for this study, Tree (Random Forest, Reduces Error Pruning (REP) Tree), meta-learning (Bagging, Random Subspace) and Function (Multilayer Perceptron and Support Vector Machine) based classifiers have been employed to predict atmospheric concentrations of Nitrogen dioxide (NO2). The study uses 3 atmospheric pollutants; Sulphur dioxide (SO2), Carbon monoxide (CO), and Hydrochloric acid (HCl) and 5 meteorological parameters temperature, humidity, wind speed, wind direction and atmospheric pressure. Moreover, for validation of prediction models the performance of different classifiers were compared. The results obtained suggest that Tree classifiers in general and Random Forest in particular, can outperform Function (MLP and SVM) and meta-learning (Bagging and Random Subspace) classifiers to predict the atmospheric concentration of NO2.


  1. [1]  Alfaro, E., García, N., Gámez, M., and Elizondo, D. (2008), Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks, Decision Support Systems, 45, 110-122.
  2. [2]  Baawain, M.S. and Al-Serihi, A.S. (2014), Systematic approach for the prediction of ground-level air pollution (around an industrial port) using an artificial neural network, Aerosol and Air Quality Research, 14, 124-134.
  3. [3]  Bedoui, S., Gomri, S., Samet, H., and Kachouri, A. (2016), A prediction distribution of atmospheric pollutants using support vector machines, discriminant analysis and mapping tools (Case study: Tunisia), Pollution, 2, 11-23.
  4. [4]  Bell, M.D., Sickman, J.O., Bytnerowicz, A., Padgett, P.E., and Allen, E.B. (2014), Variation in isotopologues of atmospheric nitric acid in passively collected samples along an air pollution gradient in southern California, Atmospheric Environment, 94, 287-296.
  5. [5]  Brunelli, U., Piazza, V., Pignato, L., Sorbello, F., and Vitabile, S. (2007), Two-days ahead prediction of daily maximum concentrations of SO2, O3, PM10, NO2, CO in the urban area of Palermo, Italy, Atmospheric Environment, 41, 2967- 2995.
  6. [6]  Cannon, A.J. and Lord, E.R. (2000), Forecasting summertime surface-level ozone concentrations in the Lower Fraser Valley of British Columbia: An ensemble neural network approach, Journal of the Air and Waste Management Association, 50, 322-339.
  7. [7]  Capilla, C. (2014),Multilayer perceptron and regression modelling to forecast hourly nitrogen dioxide concentrations, WIT Transactions on Ecology and the Environment, 183, 39-48.
  8. [8]  Elangasinghe, M.A., Singhal, N., Dirks, K.N., and Salmond, J.A. (2014), Development of an ANN - based air pollution forecasting system with explicit knowledge through sensitivity analysis, Atmospheric Pollution Research, 5, 696-708.
  9. [9]  Fathima, A., Mangai, J.A., and Gulyani, B.B. (2014), An ensemble method for predicting biochemical oxygen demand in river water using data mining techniques, International Journal of River Basin Management, 12, 357-366.
  10. [10]  Gabralla, L.A. and Abraham, A. (2014), Prediction of oil prices using bagging and random subspace, Proceedings of the Fifth International Conference on Innovations in Bio-Inspired Computing and Applications IBICA 2014 (pp. 343-354).
  11. [11]  Gardner, M.W. and Dorling, S.R. (1998), Artificial neural networks (the multilayer perceptron) - a review of applications in the atmospheric sciences, Atmospheric Environment, 32, 2627-2636.
  12. [12]  Gardner, M.W. and Dorling, S.R. (1999), Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London, Atmospheric Environment, 33, 709-719.
  13. [13]  Gardner, M.W. and Dorling, S.R. (2000), Statistical surface ozone models: An improved methodology to account for non-linear behaviour, Atmospheric Environment, 34, 21-34.
  14. [14]  Jiang, N. and Riley, M.L. (2015), Exploring the utility of the random forest method for forecasting ozone pollution in SYDNEY, Journal of Environment Protection and Sustainable Development, 1, 245-254.
  15. [15]  Juhos, I., Makra, L., and Tóth, B. (2008), Forecasting of traffic origin NO and NO2 concentrations by Support Vector Machines and neural networks using Principal Component Analysis, Simulation Modelling Practice and Theory, 16, 1488-1502.
  16. [16]  Lu, W. Z., Fan, H.Y., and Lo, S.M. (2003), Application of evolutionary neural network method in predicting pollutant levels in downtown area of Hong Kong, Neurocomputing, 51, 387-400.
  17. [17]  Lu, W.Z., Wang, W.J., Wang, X.K., Xu, Z.B., and Leung, A.Y. (2003), Using improved neural network model to analyze RSP, NOx and NO2 levels in urban air in Mong Kok, Hong Kong, Environmental Monitoring and Assessment, 87, 235-254.
  18. [18]  Lu, W.Z. and Wang, D. (2014), Learning machines: Rationale and application in ground-level ozone prediction, Applied Soft Computing, 24, 135-141.
  19. [19]  Masih, A. (2018),Modelling the atmospheric concentration of carbon monoxide by using Ensemble Learning Techniques, CEUR Workshop Proceedings, 2298, 12.
  20. [20]  Masih, A. (2018), Thar coalfield: sustainable development and an open sesame to the energy security of Pakistan, IOP Conference Series: Journal of Physics, 989(1), 012004.
  21. [21]  Oprea, M.D. (2016), Particulate matter air pollutants forecasting using inductive learning approach, Revista de Chimie, 67, 2075-2081.
  22. [22]  Pires, J.C.,Martins, F.G., Sousa, S.I., Alvim-Ferraz, M.C., and Pereira, M.C. (2008), Selection and validation of parameters in multiple linear and principal component regressions, Environmental Modelling and Software, 23, 50-55.
  23. [23]  Rahimi, A. (2017), Short-term prediction of NO2 and NOx concentrations using multilayer perceptron neural network: a case study of Tabriz, Iran, Ecological Processes, 6(1), 4.
  24. [24]  Riga, M., Tzima, F.A., Karatzas, K., and Mitkas, P.A. (2009), Development and evaluation of data mining models for air quality prediction in Athens, Greece, In Information Technologies in Environmental Engineering (pp. 331-344).Springer.
  25. [25]  Russo, A. and Soares, A.O. (2014), Hybrid model for urban air pollution forecasting: A stochastic spatio-temporal approach, Mathematical Geosciences, 46, 75-93.
  26. [26]  Schlink, U., Dorling, S., Pelikan, E., Nunnari, G., Cawley, G., Junninen, H., Greig, A., Foxall, R., Eben, K., Chatterton, T., Vondracek, J., Richter, M., Dostal, M., Bertucco, L., Kolehmainen, M., and Doyle, M. (2003), A rigorous intercomparison of ground-level ozone predictions, Atmospheric Environment, 37, 3237-3253.
  27. [27]  Sfetsos, A. and Vlachogiannis, D. (2010), A new approach to discovering the causal relationship between meteorological patterns and PM10 exceedances, Atmospheric Research, 98, 500-511.
  28. [28]  Shaban, K.B., Kadri, A., and Rezk, E. (2016), Urban air pollution monitoring system with forecasting models, IEEE Sensors Journal, 16, 2598-2606.
  29. [29]  Shon, Z.H., Kim, K.H., and Song, S.K. (2011), Long-term trend in NO2 and NOx levels and their emission ratio in relation to road traffic activities in East Asia, Atmospheric Environment, 45, 3120-3131.
  30. [30]  Singh, K.P., Gupta, S., and Rai, P. (2013), Identifying pollution sources and predicting urban air quality using ensemble learning methods, Atmospheric Environment, 80, 426-437.
  31. [31]  Singh, K.P., Gupta, S., Kumar, A., and Shukla, S.P. (2012), Linear and nonlinear modeling approaches for urban air quality prediction, Science of the Total Environment, 426, 244-255.
  32. [32]  Van Loon, M., Vautard, R., Schaap, M., Bergström, R., Bessagnet, B., Brandt, J., Builtjes, P.J.H., Christensen, J.H., Cuvelier, C., Graff, A., Jonson, J.E., Krol, M., Langner, J., Roberts , P., Rouil, L., Stern, R., Tarrasón, L., Thunis, P., and Wind, P. (2007), Evaluation of long-term ozone simulations from seven regional air quality models and their ensemble, Atmospheric Environment, 41, 2083-2097.
  33. [33]  Wang, D. and Lu, W.Z. (2006), Interval estimation of urban ozone level and selection of influential factors by employing automatic relevance determination model, Chemospher, 62, 1600-1611.
  34. [34]  Wang, W., Men, C., and Lu, W. (2008), Online prediction model based on support vector machine Neurocomputing, 71, 550-558.
  35. [35]  Xie, Y., Zhao, L., Xue, J., Hu, Q., Xu, X., and Wang, H. (2016), A cooperative reduction model for regional air pollution control in China that considers adverse health effects and pollutant reduction costs, Science of the Total Environment, 573, 458-469.
  36. [36]  Yu, R., Yang, Y., Yang, L., Han, G., and Move, O.A. (2016), RAQ-a random forest approach for predicting air quality in urban sensing systems, Sensors, 16, 86.
  37. [37]  Zhan, Y.A. (2018), Spatiotemporal prediction of daily ambient ozone levels across China using random forest for human exposure assessment, Environmental Pollution, 233(2018), 464-473.
  38. [38]  Zito, P., Chen, H., and Bell, M.C. (2008), Predicting real-time roadside CO and NO2 concentrations using neural networks, IEEE Transactions on Intelligent Transportation Systems, 9, 514-522.