Next-Gen Air Quality Index Forecasting with Hybrid Machine Learning Models and Cloud Synergy

Next-Gen Air Quality Index Forecasting with Hybrid Machine Learning Models and Cloud Synergy
  IJETT-book-cover           
  
© 2025 by IJETT Journal
Volume-73 Issue-8
Year of Publication : 2025
Author : Diana George, R. Navya, Vinitha V
DOI : 10.14445/22315381/IJETT-V73I8P111

How to Cite?
Diana George, R. Navya, Vinitha V,"Next-Gen Air Quality Index Forecasting with Hybrid Machine Learning Models and Cloud Synergy", International Journal of Engineering Trends and Technology, vol. 73, no. 8, pp.129-136, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I8P111

Abstract
Globally, nowadays, air pollution remains a major menace in terms of both environmental and public health; as such, accurate monitoring and forecasting the quality of air are essential for mitigating its deleterious impact. The Air Quality Index (AQI) is used to detect the quality of air and its hazardous effects on human health. This paper tries to formulate a forecasting mechanism for AQI by measuring the rate of the major issues causing air pollutants such as PM2.5, PM10, O3, CO, SO2, NO2, Pb(lead), and NH3. Hence, this paper formulates a model that combines both Convolutional Neural Networks (CNNs) along with Transformers and an enhanced Attention Mechanism to improve the prediction accuracy. CNNs are intended for effective feature extraction and capturing spatial patterns in air quality data, while the transformer model captures the sequential dependencies, allowing for accurate predictions over time. This proposed hybrid model addresses the limitations of age-old time-series models like ARIMA and LSTM, which often struggle to analyze the complex spatial-temporal air quality relationship. The proposed model was trained using the same historical air quality data provided by the Government of India (GoI) for training and validation, with real-time deployment with live sensor data. Also, the use of cloud computing ensures efficient handling of live data streams, enabling real-time data processing, prediction, and updates. This allows for quick, scalable and reliable predictions on large, diverse datasets, timely public health alerts, and supports proactive environmental management.

Keywords
Air Quality Forecasting, Attention mechanism, Transformer, CNN, Cloud computing.

References
[1] Xiqian Yuan et al., “Air Quality Secondary Forecast Model based on ARIMA Time Series Model,” 2023 3rd Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS), Shenyang, China, pp. 310-313, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Ziqi Zhou, “Air Quality Prediction Based on Improved LSTM Model,” 2023 4th International Conference on Computer Engineering and Application (ICCEA), Hangzhou, China, pp. 392-395, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] P. Preethi et al., “A Real-time Environmental Air Pollution Predictor Model Using Dense Deep Learning Approach in IoT Infrastructure,” Global NEST Journal, vol. 26, no. 3, pp. 1-16, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Qiwei Guo et al., “Air Quality Time Series Analysis and Prediction Based on SMA-Transformer-QR,” 2025 IEEE International Conference on Electronics, Energy Systems and Power Engineering (EESPE), Shenyang, China, pp. 1572-1576, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Junhao Wu et al., “A Novel Framework for High Resolution Air Quality Index Prediction with Interpretable Artificial Intelligence and Uncertainties Estimation,” Journal of Environmental Management, vol. 357, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yanrong Ma, Jun Ma, and Yifan Wang et al., “Hybrid Prediction Model of Air Pollutant Concentration for PM2.5 and PM10,” Atmosphere, vol. 14, no. 7, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Zefan Dong, and Yonghui Zhou, “A Novel Hybrid Model for Financial Forecasting Based on CEEMDAN-SE and ARIMA-CNN-LSTM,” Mathematics, vol. 12, no. 16, pp. 1-16, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] S. Veera Manikandan et al., “Internet of Things Enabled ML for Air Quality Assessment: Systematic Review,” 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, pp. 1509-1514, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Nitin Nilesh et al., “IoT and ML-based AQI Estimation using Real-time Traffic Data,” 2022 IEEE 8th World Forum on Internet of Things (WF-IoT), Yokohama, Japan, pp. 1-6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] S. Mathupriya et al., “Localized Detection, Control and Combating of Greenhouse Gas Emissions using IoT and Data Science,” 2024 International Conference on Power, Energy, Control and Transmission Systems (ICPECTS), Chennai, India, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Fabian Surya Pramudya, Felix Indra Kurniadi, and Aldilla Noor Rakhiemah, “Breathing in Jakarta: Uncovering the Air Quality Index using Data Visualization,” 2023 7th International Conference on New Media Studies (CONMEDIA), Bali, Indonesia, pp. 162-166, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Snehal Lawande et al., “Comparative Analysis of Machine Learning Models for Prediction of Air Quality Index,” 2024 International Conference on Intelligent Systems and Advanced Applications (ICISAA), Pune, India, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Vanshay Gupta, Samit Kapadia, and Chetashri Bhadane, “Time Series Analysis and Forecasting of Air Quality in India,” 2023 Fifth International Conference on Electrical, Computer and Communication Technologies (ICECCT), Erode, India, pp. 1-5, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Xiaonan Sun, and Yundong Gu, “Evaluation of Ambient Air Quality Grade Based on Cloud Model and Combination Weighting Method,” 2024 7th International Conference on Computer Information Science and Application Technology (CISAT), Hangzhou, China, pp. 1007-1010, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Abhishek Walia et al., “Prediction of Air Quality Index Using Random Forest and Prophet Tool,” 2024 19th Annual System of Systems Engineering Conference (SoSE), Tacoma, WA, USA, pp. 275-280, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Swati Jha et al., “IoT Based Incident Control System using Air Quality Index Monitoring System,” 2022 International Conference on Emerging Trends in Engineering and Medical Sciences (ICETEMS), Nagpur, India, pp. 108-112, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Sandeep Kumar Sunori, Pushpa Bhakuni Negi, and Pradeep Juneja, “Estimation of Air Quality Index using AI and ML Techniques,” 2023 International Conference on Sustainable Communication Networks and Application (ICSCNA), Theni, India, pp. 1078-1082, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Nanda Aulia Sofiah et al., “A Comparative Assessment SARIMA and LSTM Models for the Gurugram Air Quality Index's Knowledge Discovery,” 2024 International Conference on Electrical Engineering and Computer Science (ICECOS), Palembang, Indonesia, pp. 26-31, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Swati Varshney, Jitendra Nath Shrivastava, and Neha Gupta, “Machine Learning Algorithms for Forecasting Air Quality Index: A Predictive Analysis in the Taj Trapezium Zone (TTZ) of Agra,” 2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), Gwalior, India, vol. 3, pp. 1-6, 2025.
[CrossRef] [Google Scholar] [Publisher Link]