Evaluation and Prediction of Air Quality in Kayseri Organized Industrial Zone By Using ANNs

Öz

Industrial activities cause air pollution such as motor vehicle traffic, construction activities, energy production, as well as waste management. Air pollution has diverse adverse effects on human health and environmental health. Therefore, the environmental monitoring of air quality is very important for public health and environmental health protection. Such monitoring is assisted easily by artificial intelligence (AI). AI technologies such as artificial neural networks (ANNs) have started to receive wider attention in recent times for monitoring and modeling air pollution. Because these technologies facilitate easier and more accurate data processing and analysis which, therefore, aids in the estimation of air pollution levels. In this research, data relating to PM2.5, PM10, and SO2 levels collected from January 1, 2020 to November 1, 2024 at the air quality monitoring station in Kayseri Organized Industrial Zone are analyzed. The study is conducted in two stage. The first part deals with factors affecting the observations in this long period. The second part involves using a multilayer perceptron (MLP) artificial neural network model to predict the PM2.5, PM10, and SO2 levels. The data covering the period from January 1, 2020 to January 1, 2024 were applied to train the artificial intelligence model for modeling purposes, while those from January 1, 2024 to November 1, 2024 were employed for the validation of the model. In this step, ANNs can identify and exclude missing or unusual measurements. It was determined that the MLP model can be used for air pollution modelling. In addition, the consistency of the model was discussed and climatic data can be included to improve it.

Anahtar Kelimeler

• Air Quality
• ANNs
• PM2.5
• PM10
• SO2.

Kaynakça

1. [1] Madronich, S., Shao, M., Wilson, S.R., Solomon, K.R., Longstreth, J. D. and Tang, X.Y. 2015. Changes in air quality and tropospheric composition due to depletion of stratospheric ozone and interactions with changing climate: Implications for human and environmental health. Photochemical & Photobiological Sciences, 14: 149-169.
2. [2] WHO. (2006). Air quality guidelines: Global update 2005. World Health Organization.
3. [3] Nakhjiri, A. and Kakroodi, A.A. 2024. Air pollution in industrial clusters: A comprehensive analysis and prediction using multi-source data. Ecological Informatics Volume, 80, https://doi.org/10.1016/j.ecoinf.2024.102504
4. [4] Orellano, P., Reynoso, J., Quaranta, N. 2021. Short-term exposure to sulphur dioxide (SO2) and all-cause and respiratory mortality: A systematic review and meta-analysis. Environment International, 150, https://doi.org/10.1016/j.envint.2021.106434 [5] Rothschild, R.E. 2018. Poisonous skies. Acid rain and the globalization of pollution. Chicago: University of Chicago Press. ISBN 9780226634852.
5. [6] Chen, J., Sun, L., Jia, H., Li, C., Ai, X. and Zang, S. 2022. Effects of seasonal variation on spatial and temporal distributions of ozone in Northeast China. International Journal of Environmental Research and Public Health, 19 (23), p. 15862, https://doi.org/10.3390/ijerph192315862
6. [7] Filonchyk, M. 2022. Characteristics of the severe march 2021 Gobi Desert dust storm and its impact on air pollution in China. Chemosphere, 287, 132219, https://doi.org/10.1016/j.chemosphere.2021.132219
7. [8] Elminir, K.H. and Galil, A.H. 2006. Estimation of air pollutant concentration from meteorological parameters using artificial neural network. Journal of Electrical Engineering, 57 (2), 105–110.
8. [9] Benjamin, L.N., Sharma, S., Pendharker, U. and Shrivastava, J.K. 2014. Air quality prediction using artificial neural network. International Journal of Chemical Studies, 2 (4), 7–9.

9. [10] Golizadeh, H. and Darand, M. 2009. Forecasting of air pollution using artificial neural networks: The case study Tehran city. Journal of Applied Sciences, 9, 3882–3887.
10. [11] Mahmoudzadeh, S., Othma, Z., Yazdani, M.A. and Bakar, A.A. 2012. Carbon monoxide prediction using artificial neural network and imperialist competitive algorithm. Journal of Basic & Applied Sciences, 7 (4), 735–744.
11. [12] Ayturan, Y.A., Öztürk, A. and Ayturan, Z.C. 2017. Modelling of PM10 pollution in Karatay district of Konya with artificial neural networks. Journal of International Environmental Application and Science, 12 (3), 256-263.
12. [13] Gökçek, B., Şaşa, N., Dokuz, Y. and Bozdağ, A. 2022. PM10 parametresinin makine öğrenmesi algoritmalari ile mekânsal analizi, Kayseri ili örneği. Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 24, 70, 65 – 80.
13. [14] Yadav, V., Yadav, A.K., Singh, V. and Singh, T. Artificial neural network an innovative approach in air pollutant prediction for environmental applications: A review. Results in Engineering, 22, 102305, https://doi.org/10.1016/j.rineng.2024.102305
14. [15] Cabaneros, S.M., Calautit, J.K. and Hughes, B.R. 2019. A review of artificial neural network models for ambient air pollution prediction. Environmental Modelling & Software, 119, 285-304.
15. [16] Antanasijević, D.Z., Pocajt, V.V., Povrenović, D.S., Ristić, M.D., Perić-Grujić, A.A. 2013. PM10 emission forecasting using artificial neural networks and genetic algorithm input variable optimization. Science of The Total Environment, 443, 511-519.
16. [17] Maleki, H., Sorooshian, A., Goudarzi, G., Baboli, Z., Birgani, Y.T. and Rahmat, M. 2019. Air pollution prediction by using an artificial neural network model. Clean Technologies and Environmental Policy, 21, 1341–1352.
17. [18] Agarwal,S., Sharma, S., Suresh R., Rahman, H., Vranckx, S., Maiheu, B., Blyth, L., Janssen, S., Gargava, P., Shukla, V.K. and Batra, S. 2020. Air quality forecasting using artificial neural networks with real time dynamic error correction in highly polluted regions, Science of The Total Environment, Volume 735, 2020, 139454, ISSN 0048-9697, https://doi.org/10.1016/j.scitotenv.2020.139454.
18. [19] Jiang, D., Zhang, Y., Hu, X., Zeng, Y., Tan, J. and Shao, D. 2004. Progress in developing an ANN model for air pollution index forecast. Atmospheric Environment, 38, 40, 7055-7064.
19. [20] Jairi, I., Ben-Othman, S., Canivet, L. And Zgaya-Biau, H. 2024. Enhancing air pollution prediction: A neural transfer learning approach across different air pollutants. Environmental Technology & Innovation, 36, 102158. https://doi.org/10.1016/j.eti.2024.103793
20. [21] Air Quality (1.11.2024). National air quality monitoring network. https://sim.csb.gov.tr/Services/AirQuality [22] Biancofiore, F., Busilacchio, M., Verdecchia, M., Tomassetti, B., Aruffo, E., Bianco, S., Di Tommaso, S., Colangeli, C., Rosatelli, G. and Di Carlo, P. Recursive neural network model for analysis and forecast of PM10 and PM2.5. Atmospheric Pollution Research, 8, 4, 652-659.
21. [23] Agirre-Basurko, E., Ibarra-Berastegi, G., Madariaga, I. 2006. Regression and multilayer perceptron-based models to forecast hourly O3 and NO2 levels in the Bilbao area. Environmental Modelling & Software, 21, 4, 430-446.
22. [24] Chen, H., Oliver, B.G., Pant, A., Olivera, A., Poronnik, P., Pollock, C.A. and Saad, A. 2022. Effects of air pollution on human health – Mechanistic evidence suggested by in vitro and in vivo modelling. Environmental Research, 212, C, 113378, https://doi.org/10.1016/j.envres.2022.113378.
23. [25] Saygın, M., Gonca, T., Öztürk, Ö., Has, M., Çalışkan, S., Has, Z.G. and Akkaya, A. 2017. To Investigate the Effects of Air Pollution (PM10 and SO2) on the Respiratory Diseases Asthma and Chronic Obstructive Pulmonary Disease. Turkish Thoracic Journal, 33-39.