The Power of Machine Learning Methods and PSO in Air Quality Prediction

Monitoring and forecasting air quality is essential for public health and environmental management. It details the air's cleanliness, pollution levels, and any related health risks that the general public may find concerning. This research investigates how effective machine learning techniques and particle swarm optimization are in predicting air quality. An array of machine learning algorithms, including XGBoost, support vector regression, linear regression, and random forest, was selected to ensure effective modeling outcomes. The models were trained on an open access dataset and performed performance evaluation. The answers from an on-site gas multisensor device in an Italian city were included in the dataset. The findings from the dataset were shown to accurately model and predict environmental factors affecting air quality (e.g., air temperature, humidity, indium oxide, tin oxide, NOx, NO2, etc.) using real-world air quality data. The experiments were repeated by optimizing the relevant machine learning methods with PSO. PSO is a metaheuristic optimization method widely used in feature selection and feature extraction processes. The metrics MAE, MSE, RMSE, and R2, commonly used to evaluate regression algorithms, were utilized to assess the models' performances. Particle swarm optimization-based support vector regression performed best, with MAE, MSE, RMSE, and R2 values of 0.071, 0.015, 0.122, and 0.999, respectively. In addition, Shapley additive explanations (SHAP) analysis was performed to show which feature of the PSO-based SVR model was practical and to what extent. The results show that the proposed model successfully predicts air quality.