Kentsel Bölgelerde Hava Kalitesinin Öngörüsü: Derin Öğrenme Yaklaşımı

Year 2025, Volume: 13 Issue: 4, 1445 - 1454, 30.10.2025

Yasin Kırelli

https://doi.org/10.29130/dubited.1591784

Abstract

Hava kirliliği çevresel ve insan sağlığı üzerindeki etkileri nedeniyle önemli bir araştırma konusu haline gelmiştir. Günümüzde hızlı sanayileşme ve kentleşme nedeniyle hava kalitesi kötüleşmekte olup zararlı gazların emisyonunda önemli faktörlerden biridir. Bu çalışmada hava kalitesi sorunları ele alınmış ve kükürt dioksit (SO2), azot dioksit (NO2), karbon monoksit (CO) ve partikül madde (PM2.5 ve PM10) gibi kirleticilerin insan sağlığı üzerindeki olumsuz etkileri ve sonuçları değerlendirilmiştir. Bu çalışmada İstanbul Beşiktaş'taki hava kalitesi verileri hava kirletici seviyelerini ve değerlerini tahmin etmek için Evrişimsel Sinir Ağları (CNN), Uzun Kısa Süreli Bellek (LSTM) ve Geçitli Yinelemeli Birim (GRU) tabanlı derin öğrenme modelleri kullanılarak analiz edilmiştir. Bu modellerin performansı, Ortalama Karesel Hata (MSE), Ortalama Mutlak Hata (MAE), Kök Ortalama Karesel Hata (RMSE) ve Ortalama Mutlak Yüzdelik Hata (MAPE) gibi metrikler kullanılarak değerlendirilmiştir. Çalışmanın bulguları sunulan GRU modelinin CO ve NO2 gibi kirleticiler için üstün tahmin doğruluğu sağladığını, CNN modelinin ise SO2 ve O3 tahminleri için daha iyi performans gösterdiğini ortaya koymaktadır. Bu çalışma hava kirliliği yönetimi için gelişmiş derin öğrenme tekniklerinin kullanılmasının önemini vurgulamaktadır. Sürdürülebilir kalkınma için politika yapma sürecine katkıda bulunmak üzere öngörücü modellerin potansiyelini sunmaktadır.

Keywords

Hava kalitesi tahmini , Derin öğrenme modelleri , Kirlilik öngörüsü

Air Quality Forecasting in Urban Environments: A Deep Learning Approach

Abstract

Air pollution has become an important research topic due to its environmental and human health effects. Today, rapid industrialization and urbanization is one of the major factors in the emission of harmful gases, leading to deteriorating air quality. In this study, air quality problems are discussed, and the adverse effects and consequences of pollutants including sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), and particulate matter (PM2.5 and PM10) on human health are assessed. In this study, air quality data from Beşiktaş, Istanbul, has been analyzed by using deep learning models based on Convolutional Neural Networks (CNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) to predict air pollutant levels and values. The performance of these models is evaluated using metrics such as Mean Square Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The study's findings reveal that the presented GRU model provides superior forecast accuracy for pollutants like CO and NO2, while the CNN model performs better for SO2 and O3 forecasts. This study highlights the importance of using advanced deep-learning techniques for air pollution management. It shows the potential of predictive models to contribute to the policy-making process for sustainable development.

Keywords

Air Quality Forecasting , Deep Learning Models , Urban Environments , Pollution Forecasting

Ethical Statement

This study does not involve human or animal participants. All procedures followed scientific and ethical principles, and all referenced studies are appropriately cited.

Thanks

The author would like to express their sincere thanks to the editor and the anonymous reviewers for their helpful comments and suggestions.

References

• Bouvrie, J. (2006). Notes on convolutional neural networks. Massachusetts Institute of Technology.
• Cabaneros, S. M., Calautit, J. K., & Hughes, B. R. (2019). A review of artificial neural network models for ambient air pollution prediction. Environmental Modelling & Software, 119, 285-304. https://doi.org/10.1016/j.envsoft.2019.06.014
• Ding, Z., Chen, H., Zhou, L., & Wang, Z. (2022). A forecasting system for deterministic and uncertain prediction of air pollution data. Expert Systems with Applications, 208, Article 118123. https://doi.org/10.1016/j.eswa.2022.118123
• Drewil, G. I., & Al-Bahadili, R. J. (2022). Air pollution prediction using LSTM deep learning and metaheuristics algorithms. Measurement: Sensors, 24, Article 100546. https://doi.org/10.1016/j.measen.2022.100546
• Graves, A. (2012). Supervised sequence labelling. In J. Kacprzyk (Ed.), Studies in computational intelligence (Vol. 370, pp. 5–13). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-24797-2_2
• Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., & Chen, T. (2018). Recent advances in convolutional neural networks. Pattern Recognition, 77, 354-377. https://doi.org/10.1016/j.patcog.2017.10.013
• Hochreiter, S. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
• Jia, T., Cheng, G., Chen, Z., Yang, J., & Li, Y. (2024). Forecasting urban air pollution using multi-site spatiotemporal data fusion method (Geo-BiLSTMA). Atmospheric Pollution Research, 15(6), Article 102107. https://doi.org/10.1016/j.apr.2024.102107
• Lahmiri, S. (2016). A variational mode decompoisition approach for analysis and forecasting of economic and financial time series. Expert Systems with Applications, 55, 268-273. https://doi.org/10.1016/j.eswa.2016.02.025
• Liu, X., Zhang, H., Pan, W., Xue, Q., Fu, J., Liu, G., Zheng, M., & Zhang, A. (2019). A novel computational solution to the health risk assessment of air pollution via joint toxicity prediction: A case study on selected PAH binary mixtures in particulate matters. Ecotoxicology and Environmental Safety, 170, 427-435. https://doi.org/10.1016/j.ecoenv.2018.12.010
• Morley, D. W., & Gulliver, J. (2018). A land use regression variable generation, modelling and prediction tool for air pollution exposure assessment. Environmental Modelling & Software, 105, 17-23. https://doi.org/10.1016/j.envsoft.2018.03.030
• Nakhjiri, A., & Kakroodi, A. A. (2024). Air pollution in industrial clusters: A comprehensive analysis and prediction using multi-source data. Ecological Informatics, 80, Article 102504. https://doi.org/10.1016/j.ecoinf.2024.102504
• Noor, N. M., Al Bakri Abdullah, M. M., Yahaya, A. S., & Ramli, N. A. (2015, January). Comparison of linear interpolation method and mean method to replace the missing values in environmental data set. In Materials Science Forum (Vol. 803, pp. 278-281). Trans Tech Publications Ltd. https://doi.org/10.4028/www.scientific.net/MSF.803.278
• Patro, S. G. K., & Sahu, K. K. (2015). Normalization: A preprocessing stage. https://doi.org/10.48550/arXiv.1503.06462
• Samad, A., Garuda, S., Vogt, U., & Yang, B. (2023). Air pollution prediction using machine learning techniques–an approach to replace existing monitoring stations with virtual monitoring stations. Atmospheric Environment, 310, Article 119987. https://doi.org/10.1016/j.atmosenv.2023.119987
• Shakya, D., Deshpande, V., Goyal, M. K., & Agarwal, M. (2023). PM2.5 air pollution prediction through deep learning using meteorological, vehicular, and emission data: A case study of New Delhi, India. Journal of Cleaner Production, 427, Article 139278. https://doi.org/10.1016/j.jclepro.2023.139278
• Sharma, N., Jain, V., & Mishra, A. (2018). An analysis of convolutional neural networks for image classification. Procedia Computer Science, 132, 377-384. https://doi.org/10.1016/j.procs.2018.05.198
• Shen, G., Tan, Q., Zhang, H., Zeng, P., & Xu, J. (2018). Deep learning with gated recurrent unit networks for financial sequence predictions. Procedia Computer Science, 131, 895-903. https://doi.org/10.1016/j.procs.2018.04.298
• Singh, D., & Singh, B. (2020). Investigating the impact of data normalization on classification performance. Applied Soft Computing, 97, Article 105524. https://doi.org/10.1016/j.asoc.2019.105524
• Van Houdt, G., Mosquera, C., & Nápoles, G. (2020). A review on the long short-term memory model. Artificial Intelligence Review, 53(8), 5929-5955. https://doi.org/10.1007/s10462-020-09838-1
• Wang, A., Xu, J., Tu, R., Saleh, M., & Hatzopoulou, M. (2020). Potential of machine learning for prediction of traffic related air pollution. Transportation Research Part D: Transport and Environment, 88, Article 102599. https://doi.org/10.1016/j.trd.2020.102599
• Wang, X., Xu, J., Shi, W., & Liu, J. (2019, October). OGRU: An optimized gated recurrent unit neural network. In Journal of Physics: Conference Series (Vol. 1325, No. 1, p. 012089). IOP Publishing. https://doi.org/10.1088/1742-6596/1325/1/012089
• Wen, C., Liu, S., Yao, X., Peng, L., Li, X., Hu, Y., & Chi, T. (2019). A novel spatiotemporal convolutional long short-term neural network for air pollution prediction. Science of the Total Environment, 654, 1091-1099. https://doi.org/10.1016/j.scitotenv.2018.11.086
• Wu, F., Min, P., Jin, Y., Zhang, K., Liu, H., Zhao, J., & Li, D. (2023). A novel hybrid model for hourly PM2.5 prediction considering air pollution factors, meteorological parameters and GNSS-ZTD. Environmental Modelling & Software. https://doi.org/10.1016/j.envsoft.2023.105780
• Yang, C. H., Chen, P. H., Wu, C. H., Yang, C. S., & Chuang, L. Y. (2024). Deep learning-based air pollution analysis on carbon monoxide in Taiwan. Ecological Informatics. https://doi.org/10.1016/j.ecoinf.2024.102477
• Yang, W., Wang, J., Zhang, K., & Hao, Y. (2023). A novel air pollution forecasting, health effects, and economic cost assessment system for environmental management: From a new perspective of the district-level. Journal of Cleaner Production, 417, Article 138027. https://doi.org/10.1016/j.jclepro.2023.138027
• Zeinalnezhad, M., Chofreh, A. G., Goni, F. A., & Klemeš, J. J. (2020). Air pollution prediction using semi-experimental regression model and Adaptive Neuro-Fuzzy Inference System. Journal of Cleaner Production, 261, Article 121218. https://doi.org/10.1016/j.jclepro.2020.121218
• Zhang, Z., Zhang, S., Chen, C., & Yuan, J. (2024). A systematic survey of air quality prediction based on deep learning. Alexandria Engineering Journal, 93, 128-141. https://doi.org/10.1016/j.aej.2024.03.031
• Zhao, R., Wang, D., Yan, R., Mao, K., Shen, F., & Wang, J. (2017). Machine health monitoring using local feature-based gated recurrent unit networks. IEEE Transactions on Industrial Electronics, 65(2), 1539-1548. https://doi.org/10.1109/TIE.2017.2733438