Knowledge-Guided Temporal Representation Learning for Air Pollution Forecasting (A Case Study of Nasiriyah City)
DOI:
https://doi.org/10.31185/wjcms.531Keywords:
Air Pollution Prediction, Deep Learning, Knowledge-Guided Learning, Temporal Representation Learning, Dual-Space Optimization, Time-Series Forecasting.Abstract
Air pollution prediction is a key research problem due to its direct impact on public health and the urban environment. Moreover, because air pollutants are dynamic and nonlinear, this poses a complex challenge for time-series modeling. However, while there has been significant development in the use of deep learning–based models for air quality prediction, the vast majority of existing methods are primarily data-driven, concentrating solely on reducing prediction errors in the observed value space while neglecting the modeling quality and stability of the learned temporal representations. In this work, we introduce the Knowledge-Guided Temporal Representation Learning (KG-TRL) framework for improving prediction performance. The proposed methods derive from dual-space optimization extended with temporal structure, enhancing prediction accuracy and enabling the mechanism to organize the underlying temporal representations in a dedicated space to maintain the consistency and stability of the extracted temporal components. Experimental on-air pollution data from Nasiriyah, Iraq. The results further validate that the proposed technique exhibits stable learning and significantly better predictions.
Downloads
References
[1] Y. Xue, L. Wang, Y. Zhang, Y. Zhao, and Y. Liu, "Air pollution: A culprit of lung cancer," Journal of hazardous materials, vol. 434, p. 128937, 2022.
[2] T.-C. Bui, V.-D. Le, and S.-K. Cha, "A deep learning approach for forecasting air pollution in South Korea using LSTM," arXiv preprint arXiv:1804.07891, 2018.
[3] T. Huo et al., "Air pollutant prediction by spatial-temporal information reconstruction and fusion," Results in Engineering, p. 107393, 2025.
[4] C. Chen, B. Zhao, and C. J. Weschler, "Assessing the influence of indoor exposure to “outdoor ozone” on the relationship between ozone and short-term mortality in US communities," Environmental health perspectives, vol. 120, no. 2, p. 235, 2011.
[5] L. Kwok, Y. Lam, and C.-Y. Tam, "Developing a statistical based approach for predicting local air quality in complex terrain area," Atmospheric Pollution Research, vol. 8, no. 1, pp. 114–126, 2017.
[6] J. Murillo-Escobar, J. Sepulveda-Suescun, M. Correa, and D. Orrego-Metaute, "Forecasting concentrations of air pollutants using support vector regression improved with particle swarm optimization: Case study in Aburrá Valley, Colombia," Urban climate, vol. 29, p. 100473, 2019.
[7] F. Alzu’bi, A. Al-Rawabdeh, and A. Almagbile, "Predicting air quality using random forest: A case study in Amman-Zarqa," The Egyptian Journal of Remote Sensing and Space Sciences, vol. 27, no. 3, pp. 604–613, 2024.
[8] Q. Guo et al., "Air pollution forecasting using artificial and wavelet neural networks with meteorological conditions," Aerosol and Air Quality Research, vol. 20, no. 6, pp. 1429–1439, 2020.
[9] B. Zhang et al., "Deep learning for air pollutant concentration prediction: A review," Atmospheric Environment, vol. 290, p. 119347, 2022.
[10] Y.-C. Liang, Y. Maimury, A. H.-L. Chen, and J. R. C. Juarez, "Machine learning-based prediction of air quality," applied sciences, vol. 10, no. 24, p. 9151, 2020.
[11] H. Sun et al., "Development of an LSTM broadcasting deep-learning framework for regional air pollution forecast improvement," Geoscientific Model Development, vol. 15, no. 22, pp. 8439–8452, 2022.
[12] W. Li, Y. Zhang, and Y. Liu, "Multivariate air quality forecasting with residual nested LSTM neural network based on DSWT," Sustainability, vol. 17, no. 5, p. 2244, 2025.
[13] S. Baniasadi, R. Salehi, S. Soltani, D. Martín, P. Pourmand, and E. Ghafourian, "Optimizing long short-term memory network for air pollution prediction using a novel binary chimp optimization algorithm," Electronics, vol. 12, no. 18, p. 3985, 2023.
[14] B. Zhang, G. Zou, D. Qin, Y. Lu, Y. Jin, and H. Wang, "A novel Encoder-Decoder model based on read-first LSTM for air pollutant prediction," Science of The Total Environment, vol. 765, p. 144507, 2021.
[15] S. Zhang and M. Yu, "Enhanced urban PM2. 5 prediction: Applying quadtree division and time-series transformer with WRF-chem," Atmospheric Environment, vol. 337, p. 120758, 2024.
[16] W. Li and X. Jiang, "Prediction of air pollutant concentrations based on TCN-BiLSTM-DMAttention with STL decomposition," Scientific Reports, vol. 13, no. 1, p. 4665, 2023.
[17] S. Hwang, J. Park, Y.-T. Chu, and J. Choi, "A GNN-based interpolation method for enhancing air pollution prediction based on Internet of Things (IoT) data," Atmospheric Environment, p. 121835, 2026.
[18] 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.
[19] H. Shi, S. Du, Y. Yang, J. Zhang, T. Li, and Y. Zheng, "A Knowledge-Guided Pre-Training Temporal Data Analysis Foundation Model for Urban Computing," IEEE Transactions on Knowledge and Data Engineering, 2025.
[20] A. K. Ali, P. Adibi, and M.-S. Ehsani, "Depth Map Reconstruction and Enhancement With Local and Patch Manifold Regularized Deep Depth Priors," IEEE Access, vol. 9, pp. 136111–136125, 2021.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Abbas Ali, Mansoor Ahmed Khuhro, Hadi Tabealhojeh
This work is licensed under a Creative Commons Attribution 4.0 International License.
