Data-Driven Analysis and Predictive Modeling of Urban Air Quality for Environmental Management

Muhammad Raqib Hayat Raqib; Abu Bakar Abu Bakar; Muhammad Bilal; , Muhammad Ramzan Shahid Khan Ramzan Shahid Khan

Authors

Raqib Department of Computer Science, Namal University Mianwali
Abu Bakar Department of Computer Science, Namal University Mianwali
Muhammad Bilal Namal University Mianwali
Ramzan Shahid Khan Department of Computer Science, Namal University Mianwali

Keywords:

Air Quality, Data Analysis, Machine Learning, Environmental Monitoring, Time Series, Predictive Modeling

Abstract

This research study presents a detailed analysis of air quality data collected from an Italian city for one year. The study aimed to analyze air pollution trends, explore the relationships among various pollutants and environmental variables, and build predictive models for classifying air quality levels. The dataset contained measurements of various pollutants (CO, NO_x, NO₂ and C₆H₆), sensor readings, and environmental factors (temperature, humidity). Key findings include strong correlations between certain pollutants, clear seasonal and weekly patterns in pollution levels, and the successful development of classification models to predict high pollution events with up to 99.46% accuracy. The Support Vector Machine (SVM) model outperformed all others. Feature importance analysis consistently identified the CO sensor reading as the most significant predictor, along with seasonal factors. The study presents detailed visualizations that contribute to a better understanding to a better understanding of urban air pollution dynamics and provides a foundation for developing effective air quality management strategies and early warning systems.

References

W. H. O. R. O. for Europe, “Air quality guidelines: global update 2005: particulate matter, ozone, nitrogen dioxide and sulfur dioxide,” Dec. 2006, Accessed: Mar. 23, 2026. [Online]. Available: https://iris.who.int/handle/10665/107823

“A Comparative Analysis of Monitored Ambient Hazardous Air Pollutant Levels with Modeled Estimates from the Assessment System for Population Exposure Nationwide | Request PDF.” Accessed: Mar. 23, 2026. [Online]. Available: https://www.researchgate.net/publication/295184698_A_Comparative_Analysis_of_Monitored_Ambient_Hazardous_Air_Pollutant_Levels_with_Modeled_Estimates_from_the_Assessment_System_for_Population_Exposure_Nationwide

Srishti Jain, S. K. Sharma, “Source apportionment of PM10 in Delhi, India using PCA/APCS, UNMIX and PMF,” Particuology, vol. 37, pp. 107–118, 2018, doi: https://doi.org/10.1016/j.partic.2017.05.009.

Yu Zheng, Furui Liu, “U-Air: when urban air quality inference meets big data,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2013, [Online]. Available: https://dl.acm.org/doi/10.1145/2487575.2488188

R. Bhardwaj and D. Pruthi, “Time series and predictability analysis of air pollutants in Delhi,” Proc. 2016 2nd Int. Conf. Next Gener. Comput. Technol. NGCT 2016, pp. 553–560, Mar. 2017, doi: 10.1109/NGCT.2016.7877476.

Meng Du, Yixin Chen, “A Novel Hybrid Method to Predict PM2.5 Concentration Based on the SWT-QPSO-LSTM Hybrid Model,” Comput. Intell. Neurosci., 2022, doi: 10.1155/2022/7207477.

Stuart K. Grange, David C. Carslaw, “Using meteorological normalisation to detect interventions in air quality time series,” Sci. Total Environ., vol. 653, pp. 578–588, 2019, doi: https://doi.org/10.1016/j.scitotenv.2018.10.344.

“UK air quality showed clear improvement from 2015 to 2024 but breaching of targets remains very common - Environmental Science: Atmospheres (RSC Publishing) DOI:10.1039/D5EA00055F.” Accessed: May 10, 2026. [Online]. Available: https://pubs.rsc.org/en/content/articlehtml/2025/ea/d5ea00055f

Dr. Rais Abdul Hamid Khan, Mr. Kshirsagar Sopan Bapu, “A Review : Air Pollution Prediction using Machine Learning Techniques,” Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., vol. 10, no. 3, pp. 644–647, 2024.

Xiang Li, Ling Peng, “Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation,” Environ. Pollut., vol. 231, pp. 997–1004, 2017, doi: https://doi.org/10.1016/j.envpol.2017.08.114.

Héctor Jorquera, Ricardo Pérez, “Forecasting ozone daily maximum levels at Santiago, Chile,” Atmos. Environ., vol. 32, no. 20, pp. 3415–3424, 1998, doi: https://doi.org/10.1016/S1352-2310(98)00035-1.

U. Mahalingam, K. Elangovan, H. Dobhal, C. Valliappa, S. Shrestha, and G. Kedam, “A machine learning model for air quality prediction for smart cities,” 2019 Int. Conf. Wirel. Commun. Signal Process. Networking, WiSPNET 2019, pp. 452–457, Mar. 2019, doi: 10.1109/WISPNET45539.2019.9032734.

Md Masudur Rahman, “Recommendations on the measurement techniques of atmospheric pollutants from in situ and satellite observations: a review,” Arab. J. Geosci., vol. 16, no. 5, p. 326, 2023, [Online]. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC10116117/

Bas Mijling, Qijun Jiang, “Practical field calibration of electrochemical NO2 sensors for urban air quality applications,” Atmos. Meas. Tech. Discuss., 2017, doi: 10.5194/amt-2017-43.