Article Sidebar

Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

Air pollution has become a critical issue in environmentally challenged regions due to rapid urbanization, especially in countries where forecasting tools remain underdeveloped. Despite the success of deep learning approaches in predicting air quality, there has been little research on multivariate forecasting of particulate matter in Iraqi cities using publicly accessible environmental information. This study proposes a CNN-LSTM architecture to predict the concentrations of PM₂.₅ and PM₁₀ the following day in Baghdad and Basra. Environmental data related to air quality, along with temperature, relative humidity, wind speed, and seasonal cyclical features, were used to generate multivariate time series with a 14-day lookback window. The proposed model was compared with an LSTM model and a conventional autoregressive integrated moving average model using 1,249 daily data samples collected from August 2022 to December 2025. The results reveal that the deep learning models outperformed the statistical baseline, and the LSTM approach exhibited the best generalization performance. A threshold-based pollution alert module was also implemented to demonstrate how continuous concentration forecasts can support operational air quality warning systems. The findings demonstrate the applicability of multivariate deep learning for short-term urban air pollution forecasting in data-constrained environments and provide a baseline framework for future environmental monitoring systems in Iraq.

Keywords

Air pollution forecasting PM2.5 PM10 CNN-LSTM Early warning system

Article Details

How to Cite
Nadheer, I. . ., & Aal-nouman, M. I. (2026). Hybrid CNN-LSTM model for urban air pollution forecasting: towards early warning systems for public health: a case study of Baghdad and Basra . Future Technology, 5(4), 63–73. Retrieved from https://fupubco.com/futech/article/view/1094
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. P. Jayaraman, G. N. Manikandan, and P. Partheeban, “Analysis of neural networks for air quality forecasting in populated areas,” Environmental Engineering Research, vol. 31, no. 4, p. 250400, 2026. Doi:10.4491/eer.2025.400
  2. Y. He, Y. Jiang, Q. Cao, W. Li, and Z. Chen, “A study on the prediction and driving mechanisms of typical air pollutant concentrations in the Yunnan Plateau region using machine learning,” Atmospheric Environment, vol. 372, p. 121880, 2026. Doi: 10.1016/j.atmosenv.2026.121880
  3. C. Erden, “Adaptive learning rate optimization in deep recurrent architectures for precision PM2.5 forecasting under climate variability,” Chemosphere, vol. 397, p. 144875, 2026. Doi: 10.1016/j.chemosphere.2026.144875
  4. J. Bhatta, S. R. Acharya, and K. M. Yang, “Machine learning-enhanced air quality forecasting and trend analysis: A five-year comprehensive assessment of PM2.5 concentrations in Bangkok, Thailand,” Environmental Challenges, vol. 22, p. 101442, 2026. Doi: 10.1016/j.envc.2026.101442
  5. L. Zeng, R. Dong, M. Yuan, L. Jing, and S. Jiao, “Evaluating deep learning time series models for PM2.5 forecasting across diverse horizons,” iScience, vol. 29, no. 2, p. 114770, 2026. DOI: 10.1016/j.isci.2026.114770
  6. P. Karaiskos, Y. Munian, A. Martinez-Molina, and M. Alamaniotis, “Indoor air quality prediction modeling for a naturally ventilated fitness building using RNN-LSTM artificial neural networks,” Smart and Sustainable Built Environment, vol. 15, no. 1, pp. 384–406, 2026. Doi: 10.1007/s11869-026-01901-0
  7. Q. Li, M. Li, C. Zhao, and X. Jiang, “Day ahead PM concentration forecast in Fenwei plain of China,” Air Quality, Atmosphere and Health, vol. 19, no. 2, p. 37, 2026. Doi: 10.1108/SASBE-10-2023-0308
  8. S. A. Shahriar, Y. Choi, R. Islam, S. R. Shams, and A. K. Salman, “Forecasting PM2.5 and assessing health impacts in Texas using advanced deep learning models,” Earth Systems and Environment, vol. 10, no. 1, pp. 819–840, 2026. Doi: 10.1007/s41748-025-00634-x.
  9. Y. Yin, W. Bao, H. Lu, Z. Huang, and X. Lin, “Mechanistic impacts of extra-long tunnel construction on eco-environmentally vulnerable zones: Coupled system dynamics and LSTM-Transformer modelling,” Tunnelling and Underground Space Technology, vol. 167, p. 107084, 2026. DOI: 10.1016/j.tust.2025.107084.
  10. Y. Domalatov, K. Chezhimbayeva, B. Issakov, M. Sakitzhanov, and D. Tokseit, “Air pollution forecasting in Almaty based on meteorological data using machine learning for sustainable environmental management,” International Journal of Sustainable Development and Planning, vol. 20, no. 12, pp. 5227–5246, 2025. DOI: 10.18280/ijsdp.201217.
  11. A. Adnane, A. Ajdour, and R. Leghrib, “Improving the forecasting of air pollutant gases applying hybrid machine learning methods: Application to extremes,” Modeling Earth Systems and Environment, vol. 11, no. 6, p. 436, 2025. Doi: 10.1007/s40808-025-02597-4.
  12. T. Dangare, N. R. Matandirotya, G. Handizvihwe, E. Matandirotya, and E. Mashonjowa, “Leveraging low-cost sensors and machine learning for air quality insights in an urban location of Zimbabwe: A case study,” Scientific African, vol. 30, p. e02992, 2025. Doi: 10.1016/j.sciaf.2025.e02992
  13. M. Rajesh, R. G. Babu, U. Moorthy, and S. V. Easwaramoorthy, “Machine learning-driven framework for real-time air quality assessment and predictive environmental health risk mapping,” Scientific Reports, vol. 15, no. 1, p. 28801, 2025. Doi: 10.1038/s41598-025-14214-6.
  14. A. Iqbal and N. Mukherjee, “A systematic review and comparative study of machine learning techniques for air quality prediction,” Water, Air, and Soil Pollution, vol. 236, no. 12, p. 789, 2025. Doi: 10.1007/s11270-025-08410-3.
  15. X. Gao, X. Wang, F. Li, A. Zhang, and L. Jiao, “PM2.5 concentration 7-day prediction in the Beijing–Tianjin–Hebei region using a novel stacking framework,” Scientific Reports, vol. 15, no. 1, p. 20731, 2025. Doi: 10.1038/s41598-025-07719-7.
  16. W. Abuouelezz, N. Ali, Z. Aung, S. B. Shah, and D. Gliddon, “Exploring PM2.5 and PM10 ML forecasting models: A comparative study in the UAE,” Scientific Reports, vol. 15, no. 1, p. 9797, 2025. Doi: 10.1038/s41598-025-94013-1.
  17. L. Sharma, H. Singh, and M. P. Choudhary, “Application of deep learning techniques for analysis and prediction of particulate matter at Kota city, India,” EQA, vol. 66, pp. 107–115, 2025. Doi: 10.6092/issn.2281-4485/20687.
  18. M. Kaya and İ. Ö. Bucak, “Time series analysis and prediction of PM2.5 pollution concentration in Igdir province with deep learning models,” Atmospheric Environment, vol. 361, p. 121491, 2025. Doi: 10.1016/j.atmosenv.2025.121491
  19. S. A. Asklany, D. Mohammed, I. K. Youssef, M. Nawaz, and W. A. Malwi, “Forecasting urban air quality in Paris using ensemble machine learning: A scalable framework for environmental management,” PLOS ONE, vol. 20, no. 11, p. e0336897, 2025. Doi: 10.1371/journal.pone.0336897
  20. S. Raja, A. Damodaran, and G. Manohar, “Enhanced forecasting of air quality index through an integrated deep learning framework,” Environmental Science and Pollution Research, vol. 32, no. 55, pp. 30503–30516, 2025. Doi: 10.1007/s11356-025-37269-4
  21. H. Bouzghiba, A. Ajdour, N. Omar, A. Mendyl, and G. Géczi, “A novel application of Choquet integral for multi-model fusion in urban PM10 forecasting,” Atmosphere, vol. 16, no. 11, p. 1274, 2025. Doi: 10.3390/atmos16111274.
  22. M. E. Akiner, “A comprehensive modeling framework for air quality prediction in Istanbul and CatBoost-SHAP based explainability,” Pure and Applied Geophysics, vol. 182, no. 11, pp. 4771–4803, 2025. Doi: 10.1007/s00024-025-03840-w
  23. N. A. K. and A. Mathew, “Insights into airborne particulate matter: Artificial intelligence-driven PM2.5 modelling in Hyderabad district, India,” Stochastic Environmental Research and Risk Assessment, vol. 39, no. 10, pp. 4575–4598, 2025. Doi: 10.1007/s00477-024-02728-w.
  24. C. Mountzouris, G. Protopsaltis, and J. Gialelis, “Short-term forecast of indoor CO2 using attention-based LSTM: A use case of a hospital in Greece,” Sensors, vol. 25, no. 17, p. 5382, 2025. Doi: 10.3390/s25175382
  25. M. Su, J. Li, and W. Kim, “Port ship congestion and port-oriented cities air pollution: The role of machine learning models in transportation environmental governance,” Transport Policy, vol. 171, pp. 896–915, 2025. Doi: 10.1016/j.tranpol.2025.07.023.
  26. N. Ahmad and V. Kumar, “Effective air pollution prediction using WaveNet deep learning with XGBoost (1DCNN-BiLSTM-XgRC) for urban US embassies,” Theoretical and Applied Climatology, vol. 156, no. 9, p. 464, 2025. Doi: 10.1007/s00704-025-05715-5.
  27. Y. Liu and Y. Du, “A deep learning-random forest hybrid model for predicting historical temperature variations driven by air pollution: Methodological insights from Wuhan,” Atmosphere, vol. 16, no. 9, p. 1056, 2025. Doi: 10.3390/atmos16091056
  28. R. S. Pathak, V. Pathak, and A. Rai, “A novel attention-based deep learning model for accurate PM2.5 concentration prediction and health impact assessment,” Journal of Atmospheric and Solar-Terrestrial Physics, vol. 274, p. 106583, 2025. Doi: 10.1016/j.jastp.2025.106583
  29. A. Issakhov, N. Rysmambetov, and A. Abylkassymova, “Predicting particulate matter (PM2.5) air pollution levels in Almaty city using machine learning techniques,” Modeling Earth Systems and Environment, vol. 11, no. 4, p. 236, 2025. Doi: 10.1007/s40808-025-02397-w
  30. S. Helyar and A. Alnaggar, “Air quality monitoring and mitigation through time series forecasting and stochastic optimization,” Journal of Environmental Management, vol. 389, p. 125540, 2025. Doi: 10.1016/j.jenvman.2025.125540
  31. F. Zhang, J. Hu, and M. Zeng, “A spatiotemporal multimodal framework for air pollution prediction based on Bayesian optimization—Evidence from Sichuan, China,” Atmosphere, vol. 16, no. 8, p. 958, 2025. Doi: 10.3390/atmos16080958
  32. A. Hasnain, A. Sohail, U. A. Bhatti, M. Asif, and M. A. Zia, “Prediction of particulate matter pollution using a long short-term memory model in Zhejiang Province, China,” Environmental Earth Sciences, vol. 84, no. 16, p. 478, 2025. Doi: 10.1007/s12665-025-12463-2
  33. F. Illescas-Martinez, L. Garcia, A. J. Garcia-Sanchez, R. Asorey-Cacheda, and J. Garcia-Haro, “Air quality forecasting in non-monitored urban areas through machine and deep-learning model,” Expert Systems with Applications, vol. 284, p. 127749, 2025. Doi: 10.1016/j.eswa.2025.127749
  34. S. R. Shams, Y. Choi, D. Singh, S. Kayastha, and J. Park, “Deep learning-based forecasting of daily maximum ozone levels and assessment of socioeconomic and health impacts in South Korea,” Science of the Total Environment, vol. 983, p. 179684, 2025. Doi: 10.1016/j.scitotenv.2025.179684
  35. M. Komarudin, S. R. Sulistiyanti, S. Suharso, and A. Sophian, “Advancing precision in air quality forecasting through machine learning integration,” International Journal of Artificial Intelligence, vol. 14, no. 3, pp. 2113–2122, 2025. Doi: 10.11591/ijai.v14.i3.pp2113-2122
  36. R. R. He, Y. Q. Chen, L. Tian, L. Shan, and X. S. Sang, “Constructing and evaluating predictors for data-driven PM2.5 forecasting models,” International Journal of Environmental Research, vol. 19, no. 3, p. 99, 2025. Doi: 10.1007/s41742-025-00767-x
  37. I. Stergiou, N. Traka, D. Melas, E. Tagaris, and R. E. P. Sotiropoulou, “A deep learning method for improving community multiscale air quality forecast: Bias correction, event detection, and temporal pattern alignment,” Atmosphere, vol. 16, no. 6, p. 739, 2025. Doi: 10.3390/atmos16060739
  38. P. Viswanathan and N. Subbu, “Revolutionizing air quality forecasts with optimal nonlinear regression self-organizing mapping recurrent network,” Modeling Earth Systems and Environment, vol. 11, no. 3, p. 199, 2025. Doi: 10.1007/s40808-025-02381-4
  39. F. Hu, P. Xie, J. Xu, Y. Li, and W. Q. Liu, “Mapping regional meteorological processes to ozone variability in the North China Plain and the Yangtze River Delta, China,” Environmental Science & Technology, vol. 59, no. 19, pp. 9632–9643, 2025. Doi: 10.1021/acs.est.4c11988
  40. S. Raj, J. Smith, and E. Hayes, “Hybrid graph convolutional LSTM model for spatio-temporal air quality transfer learning,” Air Quality, Atmosphere and Health, vol. 18, no. 5, pp. 1425–1445, 2025. Doi: 10.1007/s11869-025-01713-8
  41. Open-Meteo, “Open-Meteo Air Quality API: Global Air Quality Data including PM2.5 and PM10,” Open-Meteo Environmental Data Services, 2024. Available: https://open-meteo.com/en/docs/air-quality-api
  42. Open-Meteo, “Open-Meteo Historical Weather API: Global Weather Data including Temperature, Humidity, and Wind Speed,” Open-Meteo Environmental Data Services, 2024. Available: https://open-meteo.com/en/docs/historical-weather-api
  43. European Centre for Medium-Range Weather Forecasts (ECMWF), “Copernicus Atmosphere Monitoring Service (CAMS): Global Atmospheric Composition Data for Air Quality Monitoring,” Copernicus Programme, 2024. Available: https://atmosphere.copernicus.eu