What question did this study set out to answer?

The study aims to improve air quality predictions using machine learning algorithms and explainable AI techniques.

Air Quality Prediction Using Machine Learning and Statistical Analysis: An Explainable AI Perspective

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial applies machine learning to air quality index prediction, indicating improved accuracy and insights.

The study aims to improve air quality predictions using machine learning algorithms and explainable AI techniques.
Utilized five machine learning algorithms: SVM, KNN, GNB, RF, and XGBoost to classify AQI levels.
Employed 10-fold cross-validation to validate model robustness and applied T-test for feature significance analysis.
Used Explainable AI methods (LIME and SHAP) to interpret model decisions and identify critical air pollutants.
RF achieved 99% accuracy, precision, recall, and F1-score, with low inference time (42 s).
PM2.5, PM10, NO2, and NOx were identified as key features influencing AQI predictions through XAI.
Paired t-test confirmed the statistical significance of RF's superior performance over other models.

Prity et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark