Paper Contents
Abstract
The timely and accurately forecasting of air quality is one of the major determinants of urban sustainability. In this study, the PM2.5 concentration in Delhi is predicted using machine learning techniques from environmental and pollutants data. The models evaluated in this study were Random Forest and XGBoost, both capable of modelling complex and nonlinear phenomena. Data were collected from open repositories, pre-processed through imputation and normalization, and the appropriate features such as NO, NO2, CO, SO2, O3, PM10, NH3 were selected and used for training the models. The results indicate that XGBoost is slightly better than Random Forest regarding predictive capability. This would find utility in issuing public health-related advisories and urban planning.Keywords: Air Quality, PM2.5, Random Forest, XGBoost, Prediction, Machine Learning
Copyright
Copyright © 2025 Shubham Suresh Khairnar. This is an open access article distributed under the Creative Commons Attribution License.
