Year: 2023
Type: article
Abstract: Air pollution poses significant health risks and necessitates the need for accurate air quality monitoring systems. This research paper focuses on predicting the Air Quality Index (AQI) using both regression and classification models. Various machine learning algorithms such as Linear Regression, Decision Tree Regressor, Random Forest Regressor, Logistic Regression, Decision Tree Classifier, Random Forest Classifier, and K-Nearest Neighbors Classifier were employed to estimate AQI based on pollutant concentrations of SO₂, NO₂, RSPM, and SPM. The performance of these models was evaluated using metrics like RMSE, R² score, accuracy, and Cohen's Kappa score. The results demonstrate the efficacy of the models in predicting AQI, with Random Forest models exhibiting superior performance in both regression and classification tasks. This study underscores the potential of machine learning techniques in enhancing the accuracy and reliability of air quality predictions, thereby contributing to better environmental management and public health policies.
Language: English
Subfield: Environmental Engineering
Field: Environmental Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4401515232