Authors:
Hlaing Htake Khaung Tin, Jaime Alfonso Flores Navas, Mika Sillanpää, Fatima Hamouche, Pareena Khadka, Samundra Pandit

Addresses:
Faculty of Information Science, University of Information Technology, Yangon, Yangon Region, Myanmar. Faculty of Sciences, National Autonomous University of Mexico, Coyoacán, Mexico City, Mexico. Department of Chemical Engineering Technology, University of Johannesburg, Johannesburg, Gauteng, South Africa. Department of Chemistry, Ibn Tofail University, Kenitra, Rabat-Salé-Kénitra, Morocco. Department of Applied Science, Lincoln University, Lincoln, Canterbury, New Zealand.

Abstract:

As the degree of urbanisation and industrial activities has been growing continuously over time, air quality has become a crucial environmental and health issue. Properly classifying air quality levels supports environmental monitoring and informs pollution-management decisions. This research paper compares machine learning approaches for air quality classification using open environmental datasets. Specifically, relevant air pollution parameters and meteorological variables serve as input features, and air quality levels are classified into predefined classes. For this purpose, the researchers selected several supervised machine learning approaches: Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and K-Nearest Neighbours. They evaluated those using common metrics such as accuracy, precision, recall, F1-score, and confusion matrix analysis. Researchers preprocessed the data, including handling missing values, feature transformation, and normalization where applicable, before training the models. Based on the experimental results, researchers identified the best-performing model for effectively distinguishing air quality levels.

Keywords: Air Quality Classification; Machine Learning (ML); Environmental Data; Random Forest; Air Pollution; Environmental Monitoring; Support Vector Machine (SVM).

Received on: 02/06/2025, Revised on: 07/08/2025, Accepted on: 12/10/2025, Published on: 07/09/2026

DOI: 10.69888/FTSESS.2026.000785

FMDB Transactions on Sustainable Environmental Sciences, 2026 Vol. 3 No. 3, Pages: 133-142

• Views : 15
• Downloads : 6

Download PDF