SavedAdd your journal

Journals / Mühendislik Bilimleri ve Tasarım Dergisi / 2026 / Cilt: 14 Sayı: 2

LONG-TERM AIR QUALITY (PM2.5) PREDICTION USING DEEP LEARNING-BASED TEMPORAL CONVOLUTIONAL NETWORKS

DERİN ÖĞRENME TABANLI ZAMANSAL EVRİŞİMSEL AĞLAR KULLANARAK UZUN VADELİ HAVA KALİTESİ (PM2.5) TAHMİNİ

Vakkas Doğan(KIRIKKALE UNIVERSITY)0000-0001-5934-4156
Mustafa Yasin Erten(KIRIKKALE UNIVERSITY)0000-0002-5140-1213
Hüseyin Aydilek(KIRIKKALE UNIVERSITY)0000-0003-3051-4259
Pages
416–430
Publication Date
2026-06-30
🏛️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)

The study was based on experiments using the hourly dataset of the air quality station in Beijing Aotizhongxin from 2013 to 2017.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Among various sources of pollution, particulate matter with a diameter of 2.5 micrometers or less (PM2.5) is the chief environmental problem worldwide.
📊
Key Findings & Data:Collectively, the details of this pollutant PM2.5, its sources and effects measured from various studies, the pollution levels in various cities, the methods used to measure and predict the concentration, the effect of climate change and the possible solution, have been discussed in this review.
💡
Conclusion & Impact:The study was based on experiments using the hourly dataset of the air quality station in Beijing Aotizhongxin from 2013 to 2017.
🔬Design:Review & Systematic Survey
📍Scope:2013 Verileri
⚙️Variables:Hava Kalitesi Tahmini · PM2.5 Tahmini · Zamansal Konvolüsyonel Ağlar

Abstract

Among various sources of pollution, particulate matter with a diameter of 2.5 micrometers or less (PM2.5) is the chief environmental problem worldwide. Collectively, the details of this pollutant PM2.5, its sources and effects measured from various studies, the pollution levels in various cities, the methods used to measure and predict the concentration, the effect of climate change and the possible solution, have been discussed in this review. Pollution levels are rising globally at alarming rates with detrimental effects on the environment as well as human health. However, air quality data represents a time series that is inherently challenging to forecast given its nonlinear nature, noisy data, and long-term dependencies in time. In this work, a Temporal Convolutional Network (TCN)-based deep learning model has been proposed for PM2.5 forecasting, and its performance benchmarked against RNN, LSTM, GRU, and Attention mechanism-based Bi-LSTM models. The study was based on experiments using the hourly dataset of the air quality station in Beijing Aotizhongxin from 2013 to 2017.

Özet

Çeşitli kirlilik kaynakları arasında, çapı 2.5 mikrometre veya daha küçük olan partikül maddeler (PM2.5), dünya çapındaki temel çevresel sorundur. Bu incelemede; bu kirleticinin detayları, çeşitli çalışmalardan elde edilen kaynakları ve etkileri, farklı şehirlerdeki kirlilik seviyeleri, konsantrasyonu ölçmek ve tahmin etmek için kullanılan yöntemler, iklim değişikliğinin etkisi ve olası çözümler toplu bir şekilde ele alınmıştır. Kirlilik seviyeleri hem çevre hem de insan sağlığı üzerindeki zararlı etkileriyle birlikte küresel ölçekte endişe verici oranlarda artmaktadır. Bununla birlikte, hava kalitesi verileri; doğrusal olmayan yapısı, gürültülü veri içeriği ve zamana bağlı uzun vadeli bağımlılıkları nedeniyle tahmin edilmesi doğası gereği zor olan bir zaman serisini temsil eder. Bu çalışmada, (PM2.5) tahmini için Zamansal Evrişimsel Ağ tabanlı bir derin öğrenme modeli önerilmiş ve modelin performansı; RNN, LSTM, GRU ve dikkat mekanizması tabanlı Bi-LSTM modelleriyle kıyaslanmıştır. Çalışma, Pekin Aotizhongxin hava kalitesi istasyonunun 2013-2017 yılları arasındaki saatlik veri seti kullanılarak yapılan deneylere dayanmaktadır.

🔖

Cite This Article

Doğan, V., Erten, M. Y., Aydilek, H. (2026). LONG-TERM AIR QUALITY (PM2.5) PREDICTION USING DEEP LEARNING-BASED TEMPORAL CONVOLUTIONAL NETWORKS. Mühendislik Bilimleri ve Tasarım Dergisi, Cilt: 14 Sayı: 2, 416–430. https://doi.org/10.21923/jesd.1902759

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (33)

  1. Agbehadji, I. E., Obagbuwa, I. C., 2024. Spatio-temporal PM2.5 prediction using graph neural networks: A review. Environmental Science and Pollution Research, 31, 1234-1250.
  2. Aggarwal, C. C., 2017. Outlier analysis (2nd ed.). Springer.
  3. Bai, S., Kolter, J. Z., Koltun, V., 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271.
  4. Brook, R. D., Rajagopalan, S., Pope, C. A., Brook, J. R., Bhatnagar, A., Diez-Roux, A. V., Kaufman, J. D., 2010. Particulate matter air pollution and cardiovascular disease: An update to the scientific statement from the American Heart Association. Circulation, 121(21), 2331-2378.
  5. Chai, T., Draxler, R. R., 2014. Root mean square error (RMSE) or mean absolute error (MAE)–Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247-1250.
  6. Chen, H., Guan, Y., Li, H., 2023. Air quality prediction based on Bi-LSTM and multi-head attention mechanism. Applied Intelligence, 53(1), 1234-1245.
  7. Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y., 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078.
  8. Cobourn, W. G., 2010. An enhanced PM2.5 air quality forecast model based on nonlinear regression and back-trajectory concentrations. Atmospheric Environment, 44(25), 3015-3023.
  9. Di, Q., Wang, Y., Zanobetti, A., Wang, Y., Koutrakis, P., Choirat, C., Schwartz, J., 2017. Air pollution and mortality in the Medicare population. New England Journal of Medicine, 376(26), 2513-2522.
  10. Dua, D., Graff, C., 2019. UCI Machine Learning Repository. University of California, Irvine, School of Information and Computer Sciences.
  11. Duan, L., Jiang, Z., Carlson, D., 2023. Augmenting ground-level PM2.5 prediction via Kriging-based pseudo-label generation. NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning.
  12. Eren, E., Yücel, M., Özden, S., 2023. A comparative evaluation of deep learning models for short-term air quality forecasting. Atmospheric Environment, 294, 119520.
  13. Grange, S. K., Carslaw, D. C., Lewis, A. C., Boleti, E., Hueglin, C., 2018. Random forest meteorological normalisation models for Swiss PM10 trend analysis. Atmospheric Chemistry and Physics, 18(9), 6223-6239.
  14. He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778.
  15. Hochreiter, S., Schmidhuber, J., 1997. Long short-term memory. Neural Computation, 9(8), 1735-1780.
  16. Hu, J., Jia, Y., Jia, Z. H., He, C. B., Shi, F., 2024. Prediction of PM2.5 concentration based on deep learning for high-dimensional time series. Applied Sciences, 14(19), 8745.
  17. Kara, A., 2021. A Hybrid Prognostic Approach Based on Deep Learning for the Degradation Prediction of Machinery. Sakarya University Journal of Computer and Information Sciences.
  18. Kingma, D. P., Ba, J., 2015. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  19. Lelieveld, J., Evans, J. S., Fnais, M., Giannadaki, D., Pozzer, A., 2015. The contribution of outdoor air pollution sources to premature mortality on a global scale. Nature, 525(7569), 367-371.
  20. Li, X., Peng, L., Hu, Y., Shao, J., Chi, T., 2016. Deep learning architecture for air quality predictions. Environmental Science and Pollution Research, 23(22), 22408-22417.
  21. Lim, B., Arık, S. Ö., Loeff, N., Pfister, T., 2021. Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4), 1748-1764.
  22. Liu, Y., et al., 2024. Deep learning-based CNN-RNN hybrid model for PM2.5 forecasting. Atmosphere, 15(9), 1003.
  23. Mengüş, D., & Daş, B., 2025. Comparative Analysis of Data Visualization and Deep Learning Models in Air Quality Forecasting. Sakarya University Journal of Computer and Information Sciences, 8(1), 89-111.
  24. Oord, A. v. d., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kavukcuoglu, K., 2016. WaveNet: A generative model for raw audio. arXiv preprint arXiv:1609.03499.
  25. Pope, C. A., Dockery, D. W., 2006. Health effects of fine particulate air pollution: Lines that connect. Journal of the Air & Waste Management Association, 56(6), 709-742.
  26. Schuster, M., Paliwal, K. K., 1997. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673-2681.
  27. Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C., 2015. Efficient object localization using convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 680-688.
  28. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Polosukhin, I., 2017. Attention is all you need. Advances in Neural Information Processing Systems, 30.
  29. Willmott, C. J., Matsuura, K., 2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30(1), 79-82.
  30. World Health Organization, 2021. WHO global air quality guidelines: particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide. World Health Organization.
  31. Yu, F., Koltun, V., 2016. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122.
  32. Zhang, S., Guo, B., Dong, A., He, J., Zipf, A., Dewan, P., 2017. Cautionary tales on air-quality improvement in Beijing. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 473(2205), 20170457.
  33. Zhou, S., Wang, W., Zhu, L., Qiao, Q., Kang, Y., 2024. Deep-learning architecture for PM2.5 concentration prediction: A review. Environmental Science and Ecotechnology, 21, 100400.