A Hyperparameter-Optimized LSTM Machine Learning Method for Predicting Air Quality
DOI:
https://doi.org/10.63503/acset.119Keywords:
Air Quality Index (AQI), Machine Learning, LSTM, Ensemble Learning, XGBoost, Random Forest, Air Pollution Forecasting, Environmental MonitoringAbstract
Urban air pollution is a significant environmental concern that affects both the ecosystem and human health. In this paper, the authors propose a machine learning model for predicting the Air Quality Index (AQI). Various machine learning techniques are employed, including Linear Regression, Decision Tree, K-Nearest Neighbours (KNN), Random Forest, Gradient Boosting, XGBoost, and sequence modelling using Long Short-Term Memory (LSTM) networks for AQI prediction. The performance of these models is evaluated using key performance indicators such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R² score). The experimental results reveal that the XGBoost model outperforms the other models, while hyperparameter tuning further improves the effectiveness of both the Decision Tree and KNN models. The proposed system demonstrates high predictive performance with MAE: 14.637, RMSE: 30.698, MAPE: 9.355%, and R² Score: 0.948. In addition, a web interface for real-time AQI monitoring has been developed, making the proposed system useful for public awareness and environmental management.
References
[1] Dawar et al. (2025) explored the use of utilizing machine learning to forecast the Air Quality Index in Dehradun, a city in the Himalayas, as detailed in their study published in Natural Hazards.
[2] Alrashidi H., Sibai F. N., Abonamah A., Alrashidi M., and Alsaber A. examined PM2.5 levels and predicted the Air Quality Index through machine learning based on data from air quality monitoring stations in Kuwait, as published in Sustainability in 2025.
[3] Gokulan Ravindiran, Gasim Hayder, Karthick Kanagarathinam, Avinash Alagumalai, and Christian Sonne conducted a predictive study on forecasting air quality in Visakhapatnam through machine learning models, India, published in Chemosphere, Volume 338, 2023, Article 139518 (ISSN 0045-6535).
[4] Singh et al. (2022) investigated air quality forecasting using machine learning techniques in their publication in the SSRN Electronic Journal.
[5] Liang Y.-C., Maimury Y., Chen A. H.-L., and Juarez J. R. C. published a 2020 study in Applied Sciences on utilizing machine learning to predict air quality.
[6] C. Li, Y. Li, and Y. Bao presented their work titled "Research on Air Quality Prediction Based on Machine Learning" at the 2021 2nd International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) held in Shenyang, China.
[7] B. D. Parameshachari, G. M. Siddesh, V. Sridhar, M. Latha, K. N. A. Sattar, and G. Manjula presented their work titled "Prediction and Analysis of Air Quality Index using Machine Learning Algorithms" at the 2022 International Conference on Data Science and Intelligent Systems (ICDSIS) held in Hassan, India.
[8] M. S. Ram, C. Reshmasri, S. Shahila, and J. V. P. Saketh presented their work titled "Air Quality Prediction using Machine Learning Algorithm" at the 2023 International Conference on Smart Computing and Data Science (ICSCDS) held in Erode, India.
[9] Bhathal, B. S., and Gupta, G. (2024) presented a study on air quality prediction utilizing a hybrid machine learning model from Punjab, featured in the Journal of Electrical Systems, Volume 17, Issue 1.
[10] Gupta et al. (2023) conducted a comparative analysis of machine learning techniques for predicting the Air Quality Index, published in the Journal of Environmental and Public Health.
[11] Pant, A., Sharma, S., and Pant, K. (2023) evaluated different machine learning algorithms to forecast the Air Quality Index (AQI) in the Journal of Reliability and Statistical Studies, Volume 16, Issue 2, pp. 229–242.
[12] Yang, W., Guo, J., and other authors (2024) presented a comparative study on machine learning methods for predicting air quality in Xi'an, China, featured in the proceedings of the Artificial Intelligence and Pattern Recognition Conference, pp. 1170–1176.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2026 Adroid Conference Series: Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
