2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 18 , Issue 2 , PP: 142-156, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Rusul Al-bayati 1 * , Ülkü Alver Şahin 2 , Hüseyin Toros 3
Doi: https://doi.org/10.54216/JISIoT.180211
Air pollution, especially atmospheric particulate matter with aerodynamic diameters smaller than 10 micrometers (PM10), is one of the constant and serious environmental challenges in urban areas. Its consequences range from negative human health effects to broader ecological disruptions. With the increasing necessity of accurate and trustworthy forecasting devices in the sphere of air quality assessment, we propose a new hybrid-modeling platform that merges the sequential pattern recognition ability of Long Short Term Memory (LSTM) neural networks with fuzzy logic reasoning. The two approaches implemented in this model complement each other: while approaches taking into account the time dependence of the behavior of air pollutants address the complex temporal dynamics present in the problem, methods based on uncertainty propagate inherent uncertainties in the meteorological and environmental data. The model was trained using a well-structured, multi-variable dataset of hourly air quality and meteorological observations for five years (2019–2023) measured in Istanbul and further tested of January 2024 data. The hybrid approach outperformed all tested environments in prediction output, reaching an accuracy of 98% at the Aksaray traffic station, whereas standalone LSTM (97%) and fuzzy logic (94%) models performed lower. Importantly, it identified minute periodicity and pollution peaks with high fidelity and demonstrated robustness across diverse settings such as traffic-dense, industrial, rural and urban zones. These results place the hybrid LSTM–Fuzzy Logic model as a trusted and robust forecasting tool for predicting PM10 concentrations, providing valuable assistance to environmental policy-makers, urban planners, and public health authorities in efforts to reduce air pollution and protect the health of the population.
Air pollution , Long Short-term Memory (LSTM) , Fuzzy Logic , Hybrid mode , Machine learning , Environmental modeling
[1] O. W. Alqaysi and D. Z. Şeker, "PM10 air pollutant prediction using deep learning LSTM model: A case study of Istanbul, Türkiye," Intercontinental Geoinformation Days, vol. 7, pp. 254-257, 2023.
[2] I. Konovalov, M. Beekmann, F. Meleux, A. Dutot, and G. Foret, "Combining deterministic and statistical approaches for PM10 forecasting in Europe," Atmospheric Environment, vol. 43, no. 40, pp. 6425-6434, 2009.
[3] J.-M. Poggi and B. Portier, "PM10 forecasting using clusterwise regression," Atmospheric Environment, vol. 45, no. 38, pp. 7005-7014, 2011.
[4] İ. Aksangür, B. Eren, and C. Erden, "Evaluation of data preprocessing and feature selection process for prediction of hourly PM10 concentration using long short-term memory models," Environmental Pollution, vol. 311, p. 119973, 2022.
[5] Y. Alyousifi, M. Othman, A. Husin, and U. Rathnayake, "A new hybrid fuzzy time series model with an application to predict PM10 concentration," Ecotoxicology and Environmental Safety, vol. 227, p. 112875, 2021.
[6] H. O. Cekim, "Forecasting PM10 concentrations using time series models: A case of the most polluted cities in Turkey," Environmental Science and Pollution Research, vol. 27, no. 20, pp. 25612-25624, 2020.
[7] S. Ç. Bilgin, H. Toros, and T. T. Bilgin, "Evaluation of different imputation methods for handling missing air pollution data in Bursa, Turkey," International Journal of New Horizons in the Sciences, pp. 62-66, 2023.
[8] L. Mampitiya, N. Rathnayake, Y. Hoshino, and U. Rathnayake, "Performance of machine learning models to forecast PM10 levels," MethodsX, vol. 12, p. 102557, 2024.
[9] T. Xayasouk, H. Lee, and G. Lee, "Air pollution prediction using long short-term memory (LSTM) and deep autoencoder (DAE) models," Sustainability, vol. 12, no. 6, p. 2570, 2020.
[10] H. S. Kim et al., "Development of a daily PM10 and PM2.5 prediction system using a deep long short-term memory neural network model," Atmospheric Chemistry and Physics, vol. 19, no. 20, pp. 12935-12951, 2019.
[11] C. Miller, S. O’Neill, M. Rorig, and E. Alvarado, "Air-quality challenges of prescribed fire in the complex terrain and wildland urban interface surrounding Bend, Oregon," Atmosphere, vol. 10, no. 9, p. 515, 2019.
[12] P. Du, J. Wang, Y. Hao, T. Niu, and W. Yang, "A novel hybrid model based on multi-objective Harris hawks optimization algorithm for daily PM2.5 and PM10 forecasting," Applied Soft Computing, vol. 96, p. 106620, 2020.
[13] N. M. Ariff, M. A. A. Bakar, and H. Y. Lim, "Prediction of PM10 concentration in Malaysia using k-means clustering and LSTM hybrid model," Atmosphere, vol. 14, no. 5, p. 853, 2023.
[14] S. G. Bozkurt, L. Kuşak, and Ü. Akkemik, "Investigation of land cover (LC)/land use (LU) change affecting forest and seminatural ecosystems in Istanbul (Turkey) metropolitan area between 1990 and 2018," Environmental Monitoring and Assessment, vol. 195, no. 1, p. 196, 2023.
[15] M. Yılmaz, Y. Kara, H. Toros, and S. İncecik, "Analysis of the summer thermal comfort indices in İstanbul," International Journal of Biometeorology, vol. 68, no. 7, pp. 1327-1342, 2024.
[16] Ü. A. Şahin et al., "Assessment of ambient particulate matter and trace gases in Istanbul: Insights from long-term and multi-monitoring stations," Atmospheric Pollution Research, vol. 15, no. 5, p. 102089, 2024.
[17] S. Gündoğdu and T. Elbir, "Elevating hourly PM2.5 forecasting in Istanbul, Türkiye: Leveraging ERA5 reanalysis and genetic algorithms in a comparative machine learning model analysis," Chemosphere, vol. 364, p. 143096, 2024.
[18] S. M. Al-Selwi et al., "RNN-LSTM: From applications to modeling techniques and beyond—Systematic review," Journal of King Saud University-Computer and Information Sciences, p. 102068, 2024.
[19] Y.-H. Tsai, W.-C. Hung, S. Schulter, K. Sohn, M.-H. Yang, and M. Chandraker, "Learning to adapt structured output space for semantic segmentation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7472-7481.
[20] L. A. Zadeh, "Fuzzy logic," in Granular, Fuzzy, and Soft Computing: Springer, 2023, pp. 19-49.
[21] A. Tomasiello, Geometry of String Theory Compactifications. Cambridge University Press, 2022.
[22] J. Jezewski et al., "Is abdominal fetal electrocardiography an alternative to Doppler ultrasound for FHR variability evaluation?" Frontiers in Physiology, vol. 8, p. 305, 2017.
[23] A. K. Sharma, D. P. Yadav, H. Garg, M. Kumar, and B. Sharma, "Bone cancer detection using feature extraction based machine learning model," Comput. Math. Methods Med., vol. 2021, 2021, doi: 10.1155/2021/7433186.
[24] T. Damodaran et al., "Biological management of banana Fusarium wilt caused by Fusarium oxysporum f. sp. cubense tropical race 4 using antagonistic fungal isolate CSR-T-3 (Trichoderma reesei)," Frontiers in Microbiology, vol. 11, p. 595845, 2020.
[25] Ü. A. Şahin et al., "Temporal variations of atmospheric black carbon and its relation to other pollutants and meteorological factors at an urban traffic site in Istanbul," Atmospheric Pollution Research, vol. 11, no. 7, pp. 1051-1062, 2020.
[26] W. M. Septiawan and S. N. Endah, "Suitable recurrent neural network for air quality prediction with backpropagation through time," in 2018 2nd International Conference on Informatics and Computational Sciences (ICICoS), 2018: IEEE, pp. 1-6.
[27] R. Navares and J. L. Aznarte, "Predicting air quality with deep learning LSTM: Towards comprehensive models," Ecological Informatics, vol. 55, p. 101019, 2020.
[28] L. Fu et al., "Clinical characteristics of coronavirus disease 2019 (COVID-19) in China: a systematic review and meta-analysis," Journal of Infection, vol. 80, no. 6, pp. 656-665, 2020.
[29] O. Orang, P. C. de Lima e Silva, and F. G. Guimarães, "Time series forecasting using fuzzy cognitive maps: a survey," Artificial Intelligence Review, vol. 56, no. 8, pp. 7733-7794, 2023.
[30] W. Wang, J. Shao, and H. Jumahong, "Fuzzy inference-based LSTM for long-term time series prediction," Scientific Reports, vol. 13, no. 1, p. 20359, 2023.
