| Issue |
EPJ Web Conf.
Volume 379, 2026
2nd International Conference on Sustainable Materials, Methodologies, Technologies & Applications in Engineering (ICS2MT-2026)
|
|
|---|---|---|
| Article Number | 05004 | |
| Number of page(s) | 8 | |
| Section | Energy, Environment, Artificial Intelligence and Sustainable Development | |
| DOI | https://doi.org/10.1051/epjconf/202637905004 | |
| Published online | 03 August 2026 | |
https://doi.org/10.1051/epjconf/202637905004
Comparative Analysis of Machine Learning Models for Air Quality Index Prediction in Hyderabad and Delhi Cities
1 Department of ECE, CVR College of Engineering, Hyderabad, Telangana, India
2,3,4 Department of CSE, CVR College of Engineering, Hyderabad, Telangana, India
* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.
Published online: 3 August 2026
Abstract
According to the WHO, air pollution contributes to around 7 million premature deaths each year. This study aims to analyze the prediction of air quality using machine learning techniques. It utilizes data collected from India’s Hyderabad and Delhi. The classification and prediction accuracy of various key pollutants, such as Particular Matrix (PM10), Nitrogen Dioxide (NO2,) and Sulfur Dioxide (SO2,) are evaluated. The XGBoost model performed well in Delhi, with a Coefficient of Determination (R²) of 0.9998 and a 99.5% accuracy rate. In Hyderabad on the other hand the model found to be very satisfactory with R² of 0.786 and accuracy of 86%. The findings from the study suggest that the XGBoost model is able to predict the air quality in an urban area accurately. It has the potential to help improve the management of health risks and reduce pollution levels.
© The Authors, published by EDP Sciences, 2026
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.