Modelling of PM10 Pollution in Karatay District of Konya with Artificial Neural Networks

Abstract

Air pollution is one of the most significant issues of human being faced nowadays because it can create adverse effects on both health of human and other livings. There are several air pollutants which are considered as dangerous such as sulphur dioxide (SO₂), nitrous oxide (NO_x), carbon monoxide (CO), volatile organic compounds (VOC) and particulate matter (PM). Particulate matter is one the most significant air pollutants because it may create respiratory, cardiological and pulmonary problems by inhalation by nose on humans. Also, heavy metals and hydrocarbons may be adsorbed on PM surface, so it is considered as carcinogenic by World Health Organization (WHO). When all these negative effects of PM are taken into consideration, it is important that PM future concentration should be determined for taking precautions. PM is classified according to the diameter of the particles and PM₁₀ is described as particulates which has diameter smaller than 10 micrometres. In this study, PM₁₀ pollution was predicted with artificial neural network (ANN) for Karatay district of Konya. ANN includes interconnected structures that can make parallel computations. Several meteorological factors and air pollutant concentrations was provided by database of Ministry of Environment and Urbanisation belonging to autumn period of 2016 such as SO₂ concentration, NO concentration, NO_x concentration, NO₂ concentration, CO concentration, O₃ concentration, wind speed, temperature, relative humidity, air pressure, wind direction and previous day’s PM₁₀ concentration. These parameters were used in the model as input parameters and PM₁₀ concentration for one day later was used as an output parameter. Prediction performance of the obtained model was very promising when the similar studies are examined.

Keywords

• Artificial neural network,modelling,air pollution,PM10,factor

References

1. Akkoyunlu A, Yetilmezsoy K, Erturk F, Oztemel E, (2010) A neural network-based approach for the prediction of urban SO2 concentrations in the Istanbul metropolitan area, Int. J. Environment and Pollution, 40, No. 4, 301-321.
2. Alsugair AM, Al-Qudrah AA, (1998) Artificial neural network approach for pavement maintenance, J. Comput. Civil Eng. ASCE, 2 (4), 249–255.
3. Arabacı M., Bayram M., Yüceer M. and Karadurmuş E., (2010) Tuğla Ve Kiremit Fabrikalarının Hava Kirliliğine Katkılarının Yapay Sinir Ağı Modellemesi İle Araştırılması, UKMK- 9 – Gazi Üniversitesi, 22-25 Haziran.
4. Basheer IA, Hajmeer M, (2000) Artificial neural networks: fundamentals, computing, design, and application, Journal of Microbiological Methods, 43(1), 3-31.
5. Burden F, Winkler D, (2008) Bayesian regularization of neural networks, Methods Mol Biol., 458, 25-44.
6. Chelani AB, Chalapati Rao CV, Phadke KM, Hasan MZ, (2001) Prediction of sulphur dioxide concentration using artificial neural networks, Environmental Modelling & Software, 17, 161–168.
7. Dursun S, Kunt F, Taylan O, (2015) Modelling sulphur dioxide levels of Konya city using artificial intelligent related to ozone, nitrogen dioxide and meteorological factors, International Journal of Environmental Science and Technology, 12(12), 3915-3928.
8. Gardner MW, Dorling SR, (1998) Artificial neural networks (the multilayer perceptron) - a review of applications in the atmospheric sciences, Atmospheric Environment, 32(14–15), 2627-2636.

9. Gavin HP, (2017) The Levenberg-Marquardt method for nonlinear least squares curve-fitting problems, Department of Civil and Environmental Engineering Duke University, web page: http://people.duke.edu/~hpgavin/ce281/lm.pdf, retrieval date: 08.09.2017.
10. Güngör A, (2013) Isparta İlindeki Atmosferde Bulunan Kükürtdioksit (SO2) ve Partikül Madde (PM) Konsantrasyonunun Çoklu Doğrusal Regresyon Yöntemi İle Modellenmesi, Yüksek Lisans Tezi, Isparta/Türkiye. Karakaş B, (2015) İç ve Dış Hava Ortamlarında Partiküler Madde (PM10, PM2,5 ve PM1) Konsantrasyonlarının Değerlendirilmesi, Hacettepe Üniversitesi, Fen Bilimleri enstitüsü, Yüksek Lisans Tezi, Ankara.
11. Møller MF, (1990) A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning, Computer Science Department University of Aarhus Denmark, web page: ftp://ftp.dca.fee.unicamp.br/pub/docs/vonzuben/ia353_1s07/papers/moller_90.pdf, retrieval date: 15.09.2017.
12. Özdemir H, Borucu G, Demir G, Yiğit S, Ak N, (2010) İstanbul'daki Çocuk Oyun Parklarında Partikül Madde (PM2,5 ve PM10) Kirliliğinin İncelenmesi, Ekoloji 20, 77, 72-79.
13. Ozturk ZC, (2015) Modelling of Atmospheric SO2 Pollution in Seydişehir Town by Artificial Neural Networks, Master of Science Thesis, Selçuk University, The Graduate School of Natural and Applied Sciences.
14. Pham DT, Pham PTN, (1999) Artificial intelligence in engineering, International Journal of Machine Tools and Manufacture, 39(6), 937-949.
15. Resmî Gazete, (2008) Hava Kalitesi Değerlendirme ve Yönetimi Yönetmeliği, Çevre ve Orman Bakanlığı, Number: 26898, 06 June 2008, Ankara.
16. Rozlach Z, (2015) Data-driven Modelling in River Channel Evolution Research: Review of Artificial Neural Networks, J. Int. Environmental Application & Science, 10(4), 384-398.
17. Sarle W, (1997) Neural network frequently asked questions, web page: ftp://ftp.sas.com/pub/neural/FAQ.html, retrieval date: 12.09.2017.
18. Şekerel BE, Gemicioğlu B., Soriano J. B., (2006) Asthma insights and reality in Turkey(AIRET) study, Respiratory Medicine, 100(10), 1850-1854.
19. Tecer LH, (2007) Prediction of SO2 and PM Concentrations in a Coastal Mining Area (Zonguldak, Turkey) Using an Artificial Neural Network, Polish J. of Environ. Stud., 16(4), 633-638.
20. Wang SC, (2003) Artificial Neural Network, The Springer International Series in Engineering and Computer Science, Volume 743, 81-100.
21. Yüksek GA, Bircan H, Zontul M, Kaynar O, (2007) Sivas İlinde Yapay Sinir Ağları ile Hava Kalitesi Modelinin Oluşturulması Üzerine Bir Uygulama, C.Ü. İktisadi ve İdari Bilimler Dergisi, 8, 97-112.
22. Zannetti P, (1990) Air Pollution Modeling Theories, Computational Methods and Available Software, Springer Science + Business Media, LLC, AeroVironment Inc. Monrovia, California, 3-20.