Journal of Earth System Science

, Volume 125, Issue 5, pp 997–1006 | Cite as

Forecasting ozone concentrations in the east of Croatia using nonparametric Neural Network Models



Ozone is one of the most significant secondary pollutants with numerous negative effects on human health and environment including plants and vegetation. Therefore, more effort is made recently by governments and associations to predict ozone concentrations which could help in establishing better plans and regulation for environment protection. In this study, we use two Artificial Neural Network based approaches (MPL and RBF) to develop, for the first time, accurate ozone prediction models, one for urban and another one for rural area in the eastern part of Croatia. The evaluation of actual against the predicted ozone concentrations revealed that MLP and RBF models are very competitive for the training and testing data in the case of Kopački Rit area whereas in the case of Osijek city, MLP shows better evaluation results with 9% improvement in the correlation coefficient. Furthermore, subsequent feature selection process has improved the prediction power of RBF network.


Ozone PM10 rural and urban area prediction models artificial neural networks 



The authors gratefully acknowledge the financial support given to the project by the Croatian Ministry of Science, Education and Sports. The authors also thank Meteorological and Hydrological Service of Croatia and the Ministry of Environmental and Nature Protection.


  1. Agirre E et al. 2012 Forecasting ozone levels using artificial neural networks; In: Forecasting Models – Methods & Applications (ed.) Zhu J, Hong-Kong, iConcept Press Ltd., Chapter 14, pp. 207–219.Google Scholar
  2. Alebić-Juretić A et al. 2007 Atmospheric particulate matter and ozone under heat-wave conditions: Do they cause an increase of mortality in Croatia? Bull. Environ. Contam. Toxicol. 79 468–471.CrossRefGoogle Scholar
  3. Alexis N et al. 2004 Health effects of air pollution; J. Allergy Clin. Immunol. 114 1116–1123.CrossRefGoogle Scholar
  4. Bytnerowicz A et al. 2007 Integrated effects of air pollution and climate change on forests: A northern hemisphere perspective; Environ. Pollut. 147 438–445.CrossRefGoogle Scholar
  5. Cape J N 2008 Surface ozone concentrations and ecosystem health: Past trends and a guide to future projections; Sci. Tot. Environ. 400 257–269.CrossRefGoogle Scholar
  6. Chen R et al. 2010 Ambient air pollution and hospital admission in Shanghai, China; J. Hazard. Mater. 181 234–240.CrossRefGoogle Scholar
  7. Directive 2002/3/EC of the European parliament and of the council of 12 February 2002 relating to ozone in ambient air, 2002.Google Scholar
  8. Directive 2008/50/EC of the European parliament and of the council on ambient air quality and cleaner air for Europe, 2008.Google Scholar
  9. Faris H et al. 2014 Artificial neural networks for surface ozone prediction: Models and analysis; Pol. J. Environ. Stud. 23 341–348.Google Scholar
  10. Kalabokas P D et al. 2007 Vertical ozone measurements in the troposphere over the eastern Mediterranean and comparison with central Europe; Atmos. Chem. Phys. Discuss. 7 2249–2274.CrossRefGoogle Scholar
  11. Katsouyanni K et al. 2001 Confounding and effect modification in the short-term effects of ambient particles on total mortality: Results from 29 European cities within the APHEA2 project; Epidemiology 12 521– 531.CrossRefGoogle Scholar
  12. Kohavi R and John G H 1997 Wrappers for feature subset selection; Artificial Intelligence 97 273–324.CrossRefGoogle Scholar
  13. Kovač-Andrić E et al. 2013 Assessment of variations of O 3 concentrations in Kopački Rit Nature Park, Eastern Croatia; Croat. Chem. Acta 86 109–115.CrossRefGoogle Scholar
  14. Ministry of Environmental Protection, ‘Physical planning and environmental action plan’ 2002.Google Scholar
  15. Paoletti E 2009 Ozone and urban forests in Italy; Environ. Pollut. 157 1506–1512.CrossRefGoogle Scholar
  16. Pastor-Bárcenas O et al. 2005 Unbiased sensitivity analysis and pruning techniques in neural networks for surface ozone modelling; Ecol. Modell. 182 149–158.CrossRefGoogle Scholar
  17. Percy K E and Ferretti M 2004 Air pollution and forest health: Toward new monitoring concepts; Environ. Pollut. 130 113–126.CrossRefGoogle Scholar
  18. Pope C A III et al. 2002 Lung cancer, cardiopulmonary mortality, and long-term exposure to fine particulate air pollution; J. Amer. Med. Assoc. 297 1132–1141.CrossRefGoogle Scholar
  19. Prajapati S K and Triphati B D 2008 Seasonal variation of leaf dust accumulation and pigment content in plant species to urban particulates pollution; J. Environ. Quality 37 865–870.CrossRefGoogle Scholar
  20. Prybutok V R et al. 2000 Comparison of neural network models with ARIMA and regression models for prediction of houston’s daily maximum ozone concentrations; European J. Oper. Res. 122 31–40.CrossRefGoogle Scholar
  21. Saeys Y et al. 2007 A review of feature selection techniques in bioinformatics; Bioinformatics 23 2507–2517.CrossRefGoogle Scholar
  22. Sahu L K 2012 Volatile organic compounds and their measurements in the troposphere; Curr. Sci. 102 1645–1649.Google Scholar
  23. Sahu L K and Saxena P 2015 High time and mass resolved PTR-TOF-MS measurements of VOCs at an urban site of India during winter: Role of anthropogenic, biomass burning, biogenic and photochemical sources; Atmos. Res. 164–165 84–94.CrossRefGoogle Scholar
  24. Salam T M et al. 2005 Birth outcomes and prenatal exposure to ozone, carbon monoxide, and particulate matter: Results from the Children’s Health Study; Environ. Health Perspect. 113 1638–1644.CrossRefGoogle Scholar
  25. Sánchez-Lorenzo A et al. 2008 Spatial and temporal trends in sunshine duration over western Europe (1938–2004); J. Climate 21 6089–6098.CrossRefGoogle Scholar
  26. Stedman J R 2004 The predicted number of air pollution related deaths in the UK during the August 2003 heat wave; Atmos. Environ. 38 1087–1090.CrossRefGoogle Scholar
  27. UNESCO, Convention concerning the protection of the world structural and natural heritage, vol. 38, 2001.Google Scholar
  28. Wittig V E et al. 2009 Quantifying the impact of current and future tropospheric ozone on tree biomass, growth, physiology and biochemistry: A quantitative meta-analysis; Global Change Biol. 15 396–424.CrossRefGoogle Scholar
  29. Yang W and Omaye S T 2009 Air pollutants, oxidative stress and human health; Mutation Research 674 45–54.CrossRefGoogle Scholar

Copyright information

© Indian Academy of Sciences 2016

Authors and Affiliations

    • 1
    Email author
    • 2
    • 3
    • 1
  1. 1.Department of ChemistryUniversity of J. J. StrossmayerOsijekCroatia
  2. 2.Computers and Systems DepartmentElectronics Research InstituteGizaEgypt
  3. 3.King Abdullah II School for Information TechnologyThe University of JordanAmmanJordan

Personalised recommendations