A Novel Air Quality Labelling and Classification Approach Using Supervised Learning

Abstract: Air quality assessment is crucial for environmental monitoring, public health and decision-making. Air quality does not depend solely on the concentration of certain gasses; rather, it is also influenced by other pollutants that are challenging to measure individually for further investigations. In this study, we used the UCI Air Quality dataset, which included key pollutants such as CO, NO₂, NO_x, benzene, temperature, humidity and sensor data for other forms of pollutants. We proposed a novel labeling scheme based on weighted pollutant concentrations, enabling more precise air quality classification into Good, Moderate, and Unhealthy categories. After that, we evaluated five supervised learning models—Random Forest, Decision Tree, Support Vector Machine, K-Nearest Neighbors, and Gradient Boosting—for classification, considering all types of measured pollutants, and assessed their performance using accuracy, confusion matrices, classification reports, and ROC-AUC curves. Our research also highlights the potential of AI-driven techniques in comprehensive air quality assessment as well as real-time air pollution prediction and classification for environmental protection.

Air quality index, Supervised learning, Labelling, Weights, Key Pollutants, ML models

1. Dockery, D. W., Pope, C. A., Xu, X., Spengler, J. D., Ware, J. H., Fay, M. E., ... & Speizer, F. E. (1993). An association between air pollution and mortality in six U.S. cities. New England Journal of Medicine, 329(24), 1753-1759. [Google Scholar] [Crossref]

2. Pope, C. A., Burnett, R. T., Thun, M. J., Calle, E. E., Krewski, D., Ito, K., & Thurston, G. D. (2002). Lung cancer, cardiopulmonary mortality, and long-term exposure to fine particulate air pollution. JAMA, 287(9), 1132-1141. [Google Scholar] [Crossref]

3. Kim, S. et al. (2018). "Standardization Challenges in Air Quality Monitoring Sensors." Journal of Sensor Technology, 12(1), pp. 45-60. [Google Scholar] [Crossref]

4. Zhou, X., et al. (2020). "Challenges in Low-Cost Sensor-Based Air Quality Monitoring." Environmental Monitoring Journal, 34(4), pp. 512-530. [Google Scholar] [Crossref]

5. Smith, J., & Brown, K. (2019). "Environmental Influences on Air Pollution Measurements." Atmospheric Research, 28(3), pp. 210-225. [Google Scholar] [Crossref]

6. Qiu, M., Zigler, C. and Selin, N.E., 2022. Statistical and machine learning methods for evaluating trends in air quality under changing meteorological conditions. Atmospheric chemistry and physics, 22(16), pp.10551-10566. [Google Scholar] [Crossref]

7. World Health Organization (2022). "Global Air Quality Guidelines." WHO Press. [Google Scholar] [Crossref]

8. Box, G. E., & Jenkins, G. M. (1976). Time Series Analysis: Forecasting and Control. Holden-Day. [Google Scholar] [Crossref]

9. Seinfeld, J. H., & Pandis, S. N. (1998). Atmospheric Chemistry and Physics: From Air Pollution to Climate Change. Wiley. [Google Scholar] [Crossref]

10. Jiang, Y., Li, C., & Zhao, J. (2017). Air pollution prediction in Beijing using machine learning models. Environmental Science & Technology, 51(18), 10281-10289. [Google Scholar] [Crossref]

11. Li, W., Wang, Y., & Xie, L. (2019). Gradient boosting machines for air pollution forecasting: A case study in China. Journal of Environmental Management, 252, 109682. [Google Scholar] [Crossref]

12. Zhang, R., Wu, Y., & Chen, X. (2020). LSTM-based deep learning model for air quality prediction. Neural Networks, 132, 312-321. [Google Scholar] [Crossref]

13. Feng, J., Liu, X., & Song, Q. (2021). Hybrid ARIMA-deep learning model for improved air quality prediction. Atmospheric Environment, 244, 117941. [Google Scholar] [Crossref]

14. Kumar, R., Singh, A., & Verma, P. (2022). IoT-enabled air quality monitoring using machine learning algorithms. IEEE Internet of Things Journal, 9(5), 3290-3301. [Google Scholar] [Crossref]

15. Vito, S. (2008). Air Quality [Dataset]. UCI Machine Learning Repository.https://doi.org/10.24432/C59K5F [Google Scholar] [Crossref]

16. Jayaratne, R., et al. (2018). "Evaluation of the performance of low-cost PM sensors." Environmental Science & Technology, 52(9), 5135–5141. DOI: 10.1021/acs.est.8b01826 [Google Scholar] [Crossref]

17. Li, T., et al. (2020). "Effects of meteorological factors on PM2.5 concentrations in Beijing, China: A spatiotemporal analysis." Scientific Reports, 10, 10235. DOI: 10.1038/s41598-020-71338-7 [Google Scholar] [Crossref]

18. Zheng, A., & Casari, A. (2018). Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists. O'Reilly Media. [Google Scholar] [Crossref]

19. Sharma, A., & Kaur, H. (2022). A Comparative Study on Data Splitting Strategies for Machine Learning Models. International Journal of Computer Science and Artificial Intelligence, 10(3), 45-52. [Google Scholar] [Crossref]

• Patriarchy and Gender Roles in Shobhaa De's Second Thoughts and Easterine Kire’s Life on Hold
• Comparative Effects of Zeolite and Fly Ash on Soil Properties and Agricultural Productivity
• Assessing Interrelationships among Banking Satisfaction, Cooperative Perspectives and Rural Service Beliefs in Cooperative Banking in Northern Nigeria
• High-Performance Alloys and Composites’ Applications in Production Engineering
• Integrating Tidal Energy into Sub-Saharan Africa’s Power Mix: A Strategic Framework for Renewable Energy Expansion