Estimating and characterizing spatiotemporal distributions of elemental PM2.5 using an ensemble machine learning approach in Taiwan

Abstract

This paper presents an ensemble machine learning approach that combines Generalized Additive Model (GAM) with eXtreme Gradient Boosting (XGBoost) to estimate and characterize the spatiotemporal distributions of elemental PM_2.5 in Taiwan. Daily field measurements of 12 PM_2.5 elemental components were collected from 28 air quality monitoring stations between June 2021 and May 2022. Time-variant meteorological factors and time-invariant land-use patterns were incorporated as predictors. Results showed that the ensemble model effectively captured spatial variations in elemental PM_2.5 levels, as demonstrated by the identification of numerous time-invariant features using Shapley additive explanations analysis. A comparative analysis was conducted with a model using only XGBoost, which outperformed the ensemble model with higher cross-validated R² and lower prediction errors. While the XGBoost-only model is recommended for exposure prediction, the ensemble model offers superior interpretability for investigating air pollution sources and aids in formulating air quality strategies from a spatial perspective.