Comparison of machine learning methods for predicting ground-level ozone pollution in Beijing

High ground - level ozone (O 3 ) concentrations severely undermine urban air quality and threaten human health, creating an urgent need for precise and effective ozone - level predictions to aid environmental monitoring and policy - making.This study incorporated the historical concentrations of ozone and nitrogen dioxide (NO 2 ) from the past 3 hours as lagged features into a Lagged Feature Prediction Model (LFPM), evaluated using nine machine - learning algorithms (including XGBoost). Initially, XGBoost combined with SHAP identified 11 key features, boosting computational efficiency by 30% without sacrificing prediction accuracy. Then, ozone concentrations were predicted using six meteorological variables.Results showed that LSTM - based methods, especially ED - LSTM, performed best among meteorological - only models (R 2 = 0.479). Yet, predictions based solely on meteorological variables had limited accuracy. Adding five pollutant variables markedly improved the predictive performance across all machine - learning methods. XGBoost achieved the highest accuracy (R 2 = 0.767, RMSE = 11.35 μg/m 3 ), a 125% relative improvement in R 2 compared to meteorological - variable - only predictions. Further application of the LFPM model enhanced prediction accuracy for all nine machine - learning methods, with XGBoost still leading (R 2 = 0.873, RMSE = 8.17 μg/m 3 ).These findings conclusively demonstrate that integrating lagged feature variables significantly enhances ozone prediction accuracy, offering stronger support for environmental monitoring and policy - formulation.