Urbanisation, industrial growth, and rising traffic emissions have made air quality a critical public health and environmental concern. Accurate Air Quality Index (AQI) forecasting is essential for enabling timely warnings and informed decision-making by authorities and the public. This study develops an AQI forecasting model using the Temporal Fusion Transformer (TFT), a deep learning architecture well-suited for multivariate time-series prediction. Since real-world air quality data is often unavailable or incomplete, synthetic datasets were generated to preserve the statistical characteristics and temporal trends representative of environmental air quality databases. The proposed approach captures both short-term fluctuations and long-term

This study presented a comprehensive approach to forecasting Air Quality Index using the Temporal Fusion Transformer model on multivariate hourly pollution data across multiple cities and monitoring stations. The research demonstrated that attention-based deep learning architectures are capable of effectively capturing complex temporal dependencies in air quality data. Although data limitations and computational constraints posed challenges, the proposed methodology could actually realize forecasting performances that were stable and reliable such was confirmed by RMSE and MAE evaluation metrics. The results show the potential of more specialized deep learning models in environmental monitoring and decision support science. This research contributes to a reproducible, scalable framework for intelligent AQI forecasting that can be extended to additional cities, longer time horizons, and richer feature sets in future work

[1] H. Liu et al., “Air quality index and air pollutant concentration prediction based on machine learning algorithms,” Applied Sciences, vol. 9, p. 4069, 2019. [2] B. Lim et al., “Temporal Fusion Transformers for interpretable multi-horizon time series forecasting,” International Journal of Forecasting, vol. 37, no. 4, pp. 1748–1764, 2021. [3] R. Janarthanan et al., “A deep learning approach for prediction of air quality index in a metropolitan city,” Sustainable Cities and Society, vol. 67, p. 102720, 2021. [4] A. Mishra and Y. Gupta, “Comparative analysis of air quality index prediction using deep learning algorithms,” Spatial Information Research, vol. 32, no. 1, pp. 63–72, 2024. [5] R. Zhang et al., “Deep learning for air pollutant concentration prediction: A review,” Atmospheric Environment, vol. 290, p. 119347, 2022. [6] R. Navares and J. L. Aznarte, “Predicting air quality with deep learning LSTM: Towards comprehensive models,” Ecological Informatics, vol. 55, p. 101019, 2020. [7] G. I. Drewil and R. J. Al-Bahadili, “Air pollution prediction using LSTM deep learning and metaheuristics algorithms,” Results in Engineering, vol. 16, p. 100546, 2022. [8] L. Zhang et al., “Air quality predictions with a semi-supervised bidirectional LSTM neural network,” Atmospheric Pollution Research, vol. 12, no. 1, pp. 328–339, 2021. [9] N. Maltare and S. Vahora, “Air quality index prediction using machine learning for Ahmedabad city,” Cleaner Engineering and Technology, vol. 12, p. 100093, 2023. [10] D. Iskandaryan, F. Ramos, and S. Trilles, “Air quality prediction in smart cities using machine learning technologies based on sensor data: A review,” Applied Sciences, vol. 10, no. 7, p. 2401, 2020. [11] I. Ganguli et al., “Comprehensive analysis of air quality trends in India using machine learning and deep learning models,” in Proc. 26th Int. Conf. Distributed Computing and Networking, 2025. [12] M. Kaur et al., “Computational deep air quality prediction techniques: A systematic review,” Artificial Intelligence Review, vol. 56, pp. S2053–S2098, 2023. [13] L. Xu et al., “Modeling tabular data using Conditional GAN,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 32, 2019. [14] A. Figueira and B. Vaz, “Survey on synthetic data generation, evaluation methods and GANs,” Mathematics, vol. 10, no. 15, p. 2733, 2022. [15] Y. Sun and J. Liu, “AQI prediction based on CEEMDAN-ARMA-LSTM,” Sustainability, vol. 14, no. 19, p. 12182, 2022. [16] Q. Tao et al., “Air pollution forecasting using a deep learning model based on 1D ConvNets and bidirectional GRU,” IEEE Access, vol. 7, pp. 76690–76698, 2019. [17] Y. Huang et al., “Air quality prediction using improved PSO-BP neural network,” IEEE Access, vol. 8, pp. 99346–99353, 2020. [18] H. Chen, M. Guan, and H. Li, “Air quality prediction based on integrated dual LSTM model,” IEEE Access, vol. 9, pp. 93285–93297, 2021. [19] S. Du et al., “Deep air quality forecasting using hybrid deep learning framework,” IEEE Transactions on Knowledge and Data Engineering, vol. 33, no. 6, pp. 2412–2424, 2021. [20] Y. Zhou et al., “Data-driven air quality characterization for urban environments: A case study,” IEEE Access, vol. 6, pp. 77996–78006, 2018. [21] P.-W. Soh, J.-W. Chang, and J.-W. Huang, “Adaptive deep learning-based air quality prediction model using the most relevant spatial-temporal relations,” IEEE Access, vol. 6, pp. 38186–38199, 2018. [22] G. Zhao et al., “Regional spatiotemporal collaborative prediction model for air quality,” IEEE Access, vol. 7, pp. 134903–134919, 2019. [23] Y. Hashmy et al., “Modular air quality calibration and forecasting method for low-cost sensor nodes,” IEEE Sensors Journal, vol. 23, no. 4, pp. 4193–4203, 2023. [24] Q. Shao, J. Chen, and T. Jiang, “A novel coupled optimization prediction model for air quality,” IEEE Access, vol. 11, pp. 69667–69685, 2023. [25] F. Naz et al., “Comparative analysis of deep learning and statistical models for air pollutants prediction in urban areas,” IEEE Access, vol. 11, pp. 64016–64025, 2023.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close