Bagging-MLP yöntemiyle troposferik ozon konsantrasyonunun tahmini

Abstract

İnsan faaliyetleri atmosfer kirliliği ile bağlantılıdır ve ekonomik gelişmelerden etkilenir. Yer seviyesindeki ozon birçok ülke için önemli ve zararlı bir kirletici haline gelmiş olup halk sağlığını olumsuz etkiler. Yerinde yapılan ölçümlerin sınırlı sayıda olmasından dolayı, ozon konsantrasyonlarını doğru bir şekilde tahmin etmek için alternatif yöntemlere ihtiyaç vardır. Bu çalışmada, Avrupa'da on ülkede 2008-2018 yıllarını kapsayan CO2, N2O, CO, NOx, SOx ve O3 yıllık ortalama konsantrasyonlarını içeren bir veritabanı oluşturuldu. Bu değişkenleri kullanarak O3 konsantrasyonunu tahmin etmek için on farklı yapay zeka regresyon yöntemi geliştirildi. Geliştirilen yapay zeka modellerinin tahmin performansı, determinasyon katsayısı, ortalama mutlak hata, kök ortalama karesel hata ve göreceli mutlak hata ölçütleri kullanılarak karşılaştırıldı. Deneysel sonuçlar, Bagging-MLP yönteminin diğer modellere göre ozon konsantrasyonu tahmininde daha iyi bir performansa sahip olduğunu, R2 değeri 0.9994, ortalama mutlak hata 24.67, kök ortalama karesel hata 33.85 ve göreceli mutlak hata ise %2.9 olarak ortaya koydu. Bu çalışma, yapay zeka yöntemlerinden olan Bagging-MLP yöntemi kullanılarak O3 konsantrasyonunun gerçek değere oldukça yakın bir şekilde tahmin edilebileceğini göstermektedir.

Keywords

• Yapay zeka
• torbalama yöntemi
• çok katmanlı algılayıcı
• kentsel çevre
• ozon

Prediction of tropospheric ozone concentration with Bagging-MLP method

Abstract

Human activities are linked to atmospheric pollution and are affected by economic development. Ground-level ozone has become an important and harmful pollutant for many countries, adversely affecting public health. As there is a limited number of on-site measurements, alternative methods are required to accurately estimate ozone concentrations. In this study, a database containing annual average concentrations of CO2, N2O, CO, NOx, SOx, and O3, covering the years 2008-2018 for ten countries in Europe, was created. Ten different artificial intelligence regression methods were developed to predict the O3 concentration using these variables. The predictive performance of the developed artificial intelligence models was compared using the coefficient of determination, mean absolute error, root mean square error, and relative absolute error criteria. Experimental results show that the Bagging-MLP method has a better prediction performance than other models in ozone concentration estimation, with an R2 value of 0.9994, mean absolute error of 24.67, root mean square error of 33.85, and relative absolute error of 2.9%. This study shows that the O3 concentration can be estimated very close to the actual value by using the Bagging-MLP method, one of the artificial intelligence methods.

Keywords

• Artificial intelligence; bagging; multilayer perceptron; urban environment; ozone

References

1. [1] M. O. Andreae and P. J. Crutzen, "Atmospheric aerosols: Biogeochemical sources and role in atmospheric chemistry," Science, vol. 276, no. 5315, pp. 1052-1058, 1997.
2. [2] H. K. Ozcan, E. Bilgili, U. Sahin, O. N. Ucan, and C. Bayat, "Modeling of trophospheric ozone concentrations using genetically trained multi-level cellular neural networks," Advances in Atmospheric Sciences, vol. 24, no. 5, pp. 907-914, 2007. doi:10.1007/s00376-007-0907-y
3. [3] O. P. Tripathi et al., "An assessment of the surface ozone trend in Ireland relevant to air pollution and environmental protection," Atmospheric Pollution Research, vol. 3, no. 3, pp. 341-351, 2012. doi:10.5094/APR.2012.038
4. [4] Z. Feng, E. Hu, X. Wang, L. Jiang, and X. Liu, "Ground-level O3 pollution and its impacts on food crops in China: a review," Environmental Pollution, vol. 199, pp. 42-48, 2015. doi:10.1016/j.envpol.2015.01.016
5. [5] R. Tang, X. Huang, D. Zhou, H. Wang, J. Xu, and A. Ding, "Global air quality change during the COVID-19 pandemic: Regionally different ozone pollution responses COVID-19: 疫情期间全球空气质量变化: 臭氧响应的区域间差异," Atmospheric and Oceanic Science Letters, vol. 14, no. 4, p. 100015, 2021. doi:10.1016/j.aosl.2020.100015
6. [6] Y. Ma, B. Ma, H. Jiao, Y. Zhang, J. Xin, and Z. Yu, "An analysis of the effects of weather and air pollution on tropospheric ozone using a generalized additive model in Western China: Lanzhou, Gansu," Atmospheric Environment, vol. 224, p. 117342, 2020. doi:10.1016/j.atmosenv.2020.117342
7. [7] X. Ren, Z. Mi, and P. G. Georgopoulos, "Comparison of Machine Learning and Land Use Regression for fine scale spatiotemporal estimation of ambient air pollution: Modeling ozone concentrations across the contiguous United States," Environment International, vol. 142, p. 105827, 2020. doi:10.1016/j.envint.2020.105827
8. [8] X. Yang et al., "Summertime ozone pollution in Sichuan Basin, China: Meteorological conditions, sources and process analysis," Atmospheric Environment, vol. 226, p. 117392, 2020. doi:10.1016/j.atmosenv.2020.117392

9. [9] A. Yerramilli et al., "Simulation of surface ozone pollution in the Central Gulf Coast region during summer synoptic condition using WRF/Chem air quality model," Atmospheric Pollution Research, vol. 3, no. 1, pp. 55-71, 2012. doi:10.5094/APR.2012.005
10. [10] T. Zhang et al., "Modeling the joint impacts of ozone and aerosols on crop yields in China: An air pollution policy scenario analysis," Atmospheric Environment, vol. 247, p. 118216, 2021. doi:10.1016/j.atmosenv.2021.118216
11. [11] M. Zunckel et al., "Modelled surface ozone over southern Africa during the cross border air pollution impact assessment project," Environmental Modelling & Software, vol. 21, no. 7, pp. 911-924, 2006. doi:10.1016/j.envsoft.2005.04.004
12. [12] Y. Fu and A. Tai, "Impact of climate and land cover changes on tropospheric ozone air quality and public health in East Asia between 1980 and 2010," Atmospheric Chemistry and Physics, vol. 15, no. 17, pp. 10093-10106, 2015. doi:10.5194/acp-15-10093-2015
13. [13] R. Liu, Z. Ma, Y. Liu, Y. Shao, W. Zhao, and J. Bi, "Spatiotemporal distributions of surface ozone levels in China from 2005 to 2017: A machine learning approach," Environment international, vol. 142, p. 105823, 2020. doi:10.1016/j.envint.2020.105823
14. [14] S. Amini and S. Mohaghegh, "Application of machine learning and artificial intelligence in proxy modeling for fluid flow in porous media," Fluids, vol. 4, no. 3, p. 126, 2019. doi:10.1016/j.envint.2020.105823
15. [15] M. Meroni, F. Waldner, L. Seguini, H. Kerdiles, and F. Rembold, "Yield forecasting with machine learning and small data: what gains for grains?," Agricultural and Forest Meteorology, vol. 308, 2021. doi:10.1016/j.agrformet.2021.108555
16. [16] B. Dietrich, J. Walther, M. Weigold, and E. Abele, "Machine learning based very short term load forecasting of machine tools," Applied Energy, vol. 276, p. 115440, 2020. doi:10.1016/j.apenergy.2020.115440
17. [17] M. Cheng, F. Fang, T. Kinouchi, I. Navon, and C. Pain, "Long lead-time daily and monthly streamflow forecasting using machine learning methods," Journal of Hydrology, vol. 590, p. 125376, 2020. doi:10.1016/j.jhydrol.2020.125376
18. [18] V. Chandran et al., "Wind power forecasting based on time series model using deep machine learning algorithms," Materials Today: Proceedings, vol. 47, 2021. doi:10.1016/j.matpr.2021.03.728
19. [19] S. George and A. Dixit, "A machine learning approach for prioritizing groundwater testing for per-and polyfluoroalkyl substances (PFAS)," Journal of Environmental Management, vol. 295, p. 113359, 2021. doi:10.1016/j.jenvman.2021.113359
20. [20] L. Nevasalmi, "Forecasting multinomial stock returns using machine learning methods," The Journal of Finance and Data Science, vol. 6, pp. 86-106, 2020. doi:10.1016/j.jfds.2020.09.001
21. [21] P. Cihan, "Forecasting fully vaccinated people against COVID-19 and examining future vaccination rate for herd immunity in the US, Asia, Europe, Africa, South America, and the World," Applied Soft Computing, vol. 111, p. 107708, 2021. doi:10.1016/j.asoc.2021.107708
22. [22] P. Cihan, "Fuzzy rule-based system for predicting daily case in covid-19 outbreak," in 2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), 2020: IEEE, pp. 1-4. doi:10.1109/ISMSIT50672.2020.9254714
23. [23] P. Cihan, H. Ozel, and H. K. Ozcan, "Modeling of atmospheric particulate matters via artificial intelligence methods," Environmental Monitoring and Assessment, vol. 193, pp. 1-15, 2021. doi:10.1007/s10661-021-09091-1
24. [24] P. Cihan, O. Kalıpsız, and E. Gökçe, "Hayvan Hastalığı Teşhisinde Normalizasyon Tekniklerinin Yapay Sinir Ağı ve Özellik Seçim Performansına Etkisi," Electronic Turkish Studies, vol. 12, no. 11, 2017. doi:10.7827/TurkishStudies.11902
25. [25] P. Cihan and Z. B. Ozger, "A new heuristic approach for treating missing value: ABCIMP," Elektronika ir Elektrotechnika, vol. 25, no. 6, pp. 48-54, 2019. doi:10.5755/j01.eie.25.6.24826
26. [26] P. Cihan and Z. B. Ozger, "A new approach for determining SARS-CoV-2 epitopes using machine learning-based in silico methods," Computational Biology and Chemistry, vol. 98, p. 107688, 2022. doi:10.1016/j.compbiolchem.2022.107688
27. [27] P. Cihan, E. Gokce, and O. Kalipsiz, "A review of machine learning applications in veterinary field," Kafkas Universitesi Veteriner Fakultesi Dergisi, vol. 23, no. 4, 2017. doi:10.9775/kvfd.2016.17281
28. [28] P. Cihan, "The machine learning approach for predicting the number of intensive care, intubated patients and death: The COVID-19 pandemic in Turkey," Sigma Journal of Engineering and Natural Sciences, vol. 40, no. 1, pp. 85-94, 2022. doi:10.14744/sigma.2022.00007
29. [29] T. F. Cova and A. A. Pais, "Deep learning for deep chemistry: optimizing the prediction of chemical patterns," Frontiers in chemistry, vol. 7, p. 809, 2019. doi:10.3389/fchem.2019.00809
30. [30] M. Ani, G. Oluyemi, A. Petrovski, and S. Rezaei-Gomari, "Reservoir uncertainty analysis: The trends from probability to algorithms and machine learning," in SPE Intelligent Energy International Conference and Exhibition, 2016: OnePetro. doi:10.2118/181049-MS
31. [31] P. Cıhan and H. Coşkun, "Performance comparison of machine learning models for diabetes prediction," in 2021 29th Signal Processing and Communications Applications Conference (SIU), 2021: IEEE, pp. 1-4. doi:10.1109/SIU53274.2021.9477824
32. [32] P. Cihan, O. Kalipsiz, and E. Gökçe, "Yenidoğan kuzularda bilgisayar destekli tanı," Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, vol. 26, no. 2, pp. 385-391, 2020. doi:10.5505/pajes.2019.51447
33. [33] Z. B. Ozger and P. Cihan, "A novel ensemble fuzzy classification model in SARS-CoV-2 B-cell epitope identification for development of protein-based vaccine," Applied soft computing, vol. 116, p. 108280, 2022. doi:10.1016/j.asoc.2021.108280
34. [34] P. Cihan, "Impact of the COVID-19 lockdowns on electricity and natural gas consumption in the different industrial zones and forecasting consumption amounts: Turkey case study," International Journal of Electrical Power & Energy Systems, vol. 134, p. 107369, 2022. doi:10.1016/j.ijepes.2021.107369
35. [35] E. E. Ozbas, D. Aksu, A. Ongen, M. A. Aydin, and H. K. Ozcan, "Hydrogen production via biomass gasification, and modeling by supervised machine learning algorithms," International Journal of Hydrogen Energy, vol. 44, no. 32, pp. 17260-17268, 2019. doi:10.1016/j.ijhydene.2019.02.108
36. [36] E. K. Juarez and M. R. Petersen, "A comparison of machine learning methods to forecast tropospheric ozone levels in Delhi," Atmosphere, vol. 13, no. 1, p. 46, 2021. doi:10.3390/atmos13010046
37. [37] E. Jumin et al., "Machine learning versus linear regression modelling approach for accurate ozone concentrations prediction," Engineering Applications of Computational Fluid Mechanics, vol. 14, no. 1, pp. 713-725, 2020. doi:10.1080/19942060.2020.1758792
38. [38] Q. Pan, F. Harrou, and Y. Sun, "A comparison of machine learning methods for ozone pollution prediction," Journal of Big Data, vol. 10, no. 1, p. 63, 2023. doi:10.1186/s40537-023-00748-x
39. [39] W. Wang, X. Liu, J. Bi, and Y. Liu, "A machine learning model to estimate ground-level ozone concentrations in California using TROPOMI data and high-resolution meteorology," Environment International, vol. 158, p. 106917, 2022. doi:10.1016/j.envint.2021.106917
40. [40] A. Yafouz et al., "Comprehensive comparison of various machine learning algorithms for short-term ozone concentration prediction," Alexandria Engineering Journal, vol. 61, no. 6, pp. 4607-4622, 2022. doi:10.1016/j.aej.2021.10.021
41. [41] M. Aljanabi, M. Shkoukani, and M. Hijjawi, "Ground-level ozone prediction using machine learning techniques: A case study in Amman, Jordan," International Journal of Automation and Computing, vol. 17, pp. 667-677, 2020. doi:10.1007/s11633-020-1233-4
42. [42] D. T. Bui, Q. P. Nguyen, N.-D. Hoang, and H. Klempe, "A novel fuzzy K-nearest neighbor inference model with differential evolution for spatial prediction of rainfall-induced shallow landslides in a tropical hilly area using GIS," Landslides, vol. 14, no. 1, pp. 1-17, 2017. doi:10.1007/s10346-016-0708-4
43. [43] M. O. Elish, "A comparative study of fault density prediction in aspect-oriented systems using MLP, RBF, KNN, RT, DENFIS and SVR models," Artificial Intelligence Review, vol. 42, no. 4, pp. 695-703, 2014. doi:10.1007/s10462-012-9348-9
44. [44] P. Kumar, M. Folk, M. Markus, and J. C. Alameda, Hydroinformatics: data integrative approaches in computation, analysis, and modeling. CRC Press, 2005.
45. [45] J. Han and M. Kamber, "Data mining concepts and techniques, Morgan Kaufmann Publishers," San Francisco, CA, pp. 335-391, 2001.
46. [46] L. Breima, "Random Forests. Machine Learning," 2010.
47. [47] L. Breiman, "Bagging predictors," Machine learning, vol. 24, no. 2, pp. 123-140, 1996.
48. [48] J. D’Haen, D. Van den Poel, and D. Thorleuchter, "Predicting customer profitability during acquisition: Finding the optimal combination of data source and data mining technique," Expert systems with applications, vol. 40, no. 6, pp. 2007-2012, 2013.
49. [49] J. C. W. W. W. Carole and N. Beale, Global climate change linkages: acid rain, air quality, and stratospheric ozone. Springer Science & Business Media, 1989.
50. [50] S. Gao et al., "Simulation of surface ozone over Hebei province, China using Kolmogorov-Zurbenko and artificial neural network (KZ-ANN) combined model," Atmospheric Environment, vol. 261, p. 118599, 2021. doi:10.1016/j.atmosenv.2021.118599
51. [51] B. Jia, R. Dong, and J. Du, "Ozone concentrations prediction in Lanzhou, China, using chaotic artificial neural network," Chemometrics and Intelligent Laboratory Systems, vol. 204, p. 104098, 2020. doi:10.1016/j.chemolab.2020.104098