Journals / Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi / 2026 / Cilt: 21 Sayı: 2

MODELING OF TROPHOSPHERIC OZONE (O3) CONCENTRATIONS USING CELLULAR NEURAL NETWORKS

İSTANBUL İLİ TROPSOFERİK OZON (O3) KONSANTRASYONLARININ HÜCRESEL YAPAY SİNİR AĞ YÖNTEMİYLE MODELLENMESİ

Pages
239–245
Publication Date
2013-03-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result, CNN model results represent the seasonal increment and decrement of observed Ozone and CNN can be considered as a compromising approach in ozone prediction modeling.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In the recent years, formation of photochemical smog is common in metropolitan areas ozone is the most important pollution which causes photochemical smog.
📊
Key Findings & Data:We have used various real data parameters observed in 6 different air pollution and 8 meteorological parameters.
💡
Conclusion & Impact:As a result, CNN model results represent the seasonal increment and decrement of observed Ozone and CNN can be considered as a compromising approach in ozone prediction modeling.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Troposferik ozon · hava kirliliği · HYSA.

Abstract

In the recent years, formation of photochemical smog is common in metropolitan areas ozone is the most important pollution which causes photochemical smog. So, many studies focus on the air quality modeling accounted ozone and ozone precursors. In this paper, we have applied Cellular Neural Network for future prediction of ozone concentration in the European parts of Istanbul. We have used various real data parameters observed in 6 different air pollution and 8 meteorological parameters. As a result, CNN model results represent the seasonal increment and decrement of observed Ozone and CNN can be considered as a compromising approach in ozone prediction modeling.

Özet

Son yıllarda özellikle büyük şehirlerde, artan nüfus ve endüstrileşmeyle fotokimyasal smog oluşumu da artmaktadır. Fotokimyasal smog oluşumunda en önemli kirletici ozon gazıdır. Bu yüzden pek çok çalışma ozon ve ozon öncülerini hesaba katan hava kalitesi modellemesi üzerinde yoğunlaşmaktadır. Bu çalışmada 6 farklı kirletici parametre ve 8 meteorolojik faktör dikkate alınarak, İstanbul ili troposferik ozon konsantrasyonları Hücresel Yapay Sinir Ağ Yöntemiyle modellenmiştir. HYSA modeli ile birlikte istatiksel indisler hesaplanmış ve model performansı kontrol edilmiştir. Sonuç olarak, model çıktıları ve istatiksel değerler incelendiğinde HYSA yapısının ozon konsantrasyonu modellemelerinde kullanılabileceği görülmüştür.

🔖

Cite This Article

Özcan, H., Şahin, Ü., Bayat, C., Uçan, O. (2013). MODELING OF TROPHOSPHERIC OZONE (O3) CONCENTRATIONS USING CELLULAR NEURAL NETWORKS. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, Cilt: 21 Sayı: 2, 239–245. https://ajindex.com/articles/1078976

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (62)

  1. Eryılmaz, E., İstanbul’da Gece Ozonu, Yüksek
  2. Lisans Tezi İstanbul Teknik Üniversitesi Fen
  3. Bilimleri Enstitüsü, 2001.
  4. Tecer, L., İstanbul Kenti Fotokimyasal Smog
  5. Mekanizmasının Modellenmesi Doktora Tezi,
  6. Cumhuriyet Üniversitesi, 2000.
  7. Tirabassi, T., Pelliccioni, A. ve Garazzo, C.,
  8. “Coupling of Neural Network and Dispersion
  9. Models: a Novel Methodology for Air Pollution
  10. Models”, Int. J. Environment and Pollution,
  11. Cilt 20, No.1-6, 136-146, 2003.
  12. Wahab-Abdul, S.A. ve Al-Alawi, S.M.,
  13. “Assessment and Prediction of Trophospheric
  14. Ozone Concentration Levels Using Artificial
  15. Neural Networks”, Environmental Modeling &
  16. Software, Cilt 17, pp 219-228, 2002.
  17. Gardner, M.W., Dorling S.R., “Statistical Surface
  18. Ozone Models; an Improved Methodology to
  19. account for Nonlinear Behavior” Atmospheric
  20. Environment, Cilt 34, 21-34, 2000.
  21. Spellman G., “An Application of Artificial
  22. Neural Networks to the Prediction of Surface
  23. ozone Concentrations in the United Kingdom”,
  24. Applied Geography, Cilt 19, 123-136, 1999.
  25. Comrie A. C., “Comparing Neural Networks and
  26. Regression Model for Ozone Forecasting”,
  27. Journal of Air and Waste Manegement
  28. Association Cilt 47, 653-663, 1997.
  29. Jorquera H., Ricardo P.,Cipriano A., Espejo A.,
  30. Letelier M.V., and Acuna G., “Forecasting Ozone Daily Maximum Levels At Santiago, Chile”,
  31. Atmospheric Environment, Cilt. 32, 1267-1271,
  32. Elkamel A., Wahab-Abdul S.A., Bouhamra W.,
  33. Alper E., “Measurement and Prediction of Ozone
  34. Levels Around a Heavly Industrialized Area; A
  35. Neural Network Approach”, Advanced in
  36. Environmental Reserch, Cilt 5,.47-59, 2001.
  37. Ruiz –Suarez J.C., Mayora-Ibarra O.A., Torres-
  38. Jimenes J. ve Ruiz –Suarez L.G., “Short Term
  39. Ozone Forecasting by Artificial Neural
  40. Networks”, Advances in Engineering Software,
  41. Cilt 23, 143-149, 1995.
  42. Chua L.O., Yang L.,. “Cellular Neural Networks”
  43. Application, IEEE Transactions on Circuits
  44. and Systems Cilt 35 (10), 1273-1290, 1988.
  45. Şahin U., Uçan O.N., Tolluoğlu O., ve Bayat C.,
  46. “İstanbul’un Hava Kirliliğinin Hücresel Yapay
  47. Sinir Ağ ile Modellenmesi”, TAINN’04 Turkish
  48. Symposium on Artificial Intelligence and
  49. Neural Networks.,2004 Izmir, Turkey
  50. Albora, A.M., Ucan, O.N., Ozmen, A.,ve Ozkan,
  51. T. “Separation of Bouguer Anomaly Map Using
  52. Cellular Neural Network”, Journal of Applied
  53. Geophysics Cilt 46, 129-142, 2001.
  54. Cimagalli, V. “Cellular Neural Networks A
  55. Review”, Proceedings of Sixth Italian
  56. Workshop on Parallel Architectures and
  57. Neural Networks, Vietri Sul Mare, May 12-14,, Italy
  58. Özcan H.K, Şahin Ü, Bayat C., Uçan O.N
  59. “İstanbul Şehir Atmosferindeki Troposferik Ozon
  60. (O3) Kirliliğinin Yapay Zeka İle Modellenmesi”,
  61. HİTEK’05 Havacılıkta İleri Teknolojiler
  62. Sempozyumu, Hava Harb Okulu, İstanbul, 2005.