Exploring the detailed spatiotemporal characteristics of PM2.5: Generating a full-coverage and hourly PM2.5 dataset in the Sichuan Basin, China

Enhanced PM2.5 estimation across China: An AOD-independent two-stage approach incorporating improved spatiotemporal heterogeneity representations

In China, population growth and aging have partially negated the public health benefits of air pollution control measures, underscoring the ongoing need for precise PM2.5 monitoring and mapping. Despite its prevalence, the satellite-derived Aerosol Optical Depth (AOD) method for estimating PM2.5 concentrations often encounters significant spatial data gaps. Additionally, current research still needs better representation of PM2.5 spatiotemporal heterogeneity. Addressing these challenges, we developed a two-stage model employing the Extreme Gradient Boosting (XGBoost) algorithm. By incorporating improved spatiotemporal factors, we achieved high-precision and full-coverage daily 1-km PM2.5 mappings across China for the year 2020 without utilizing AOD products. Specifically, Model 1 develops improved temporal encodings and a terrain classification factor (DC), while Model 2 constructs an enhanced spatial autocorrelation term (Ps) by integrating observed and estimated values. Notably, Model 2 excelled in 10-fold sample-based cross-validation, achieving a coefficient of determination of 0.948, a mean absolute error of 3.792 μg/m³, a root mean square error of 7.144 μg/m³, and a mean relative error of 14.171%. Feature importance and Shapley Additive exPlanations (SHAP) analyses determined the relative importance of predictors in model training and outcome prediction, while correlation analysis identified strong links between improved temporal encodings, PM2.5 concentrations, and significant meteorological factors. Two-way Partial Dependence Plots (PDPs) further explored the interactions among these factors and their impact on PM2.5 levels. Compared to traditional methods, improved temporal encodings align more closely with seasonal variations and synergize more effectively with meteorological factors. Besides, the structured nature of DC aids in model training, while the improved Ps more effectively captures PM2.5's spatial autocorrelation, outperforming traditional Ps. Overall, this study effectively represents spatiotemporal information, thereby boosting model accuracy and enabling seamless large-scale PM2.5 estimations. It provides deep insights into variables and models, providing significant implications for future air pollution research.

Assessing the short-term effects of PM2.5 and O3 on cardiovascular mortality using high-resolution exposure: a time-stratified case cross-over study in Southwestern China

Air pollution is a major risk factor of cardiovascular disease (CVD). To date, limited studies have estimated the effects of ambient air pollution on CVD mortality using high-resolution exposure assessment, which might fail to capture the spatial variation in exposure and introduce bias in results. Besides, the three-year action plan (TYAP, 2018-2020) was released; thus, the constitution and health effect of air pollutants may have changed. In this study, we estimated the short-term effect exposed to particulate matters with parameter less than 2.5 µm (PM2.5) and ozone (O3) with 0.05° × 0.05° resolution on CVD mortality and measured the influence of TYAP in the associations. We used random forest models with spatial weight matrices to attain high-resolution pollutant concentrations and conditional Poisson regression to assess the relationship between air pollution and cardiovascular mortality. With an increase of 10 µg/m3 in PM2.5 and O3 during 2018-2021 in the Sichuan Basin (SCB), CVD mortality increased 1.0134 (95% CI 1.0102, 1.0166) and 1.0083 (95% CI 1.0060, 1.0107), respectively, using high-resolution air pollutant concentration, comparing to 1.0070 (95% CI 1.0052, 1.0087) and 1.0057 (95% CI 1.0037, 1.0078) using data from air quality monitoring stations (AQMs). After TYAP, the relative risk (RR) due to PM2.5 rose up to 1.0149 (95% CI 1.0054, 1.0243), and the RR due to O3 rose up to 1.0089 (95% CI 1.0030, 1.0148) in Sichuan Province. We found significantly positive association of cardiovascular mortality and air pollution in Sichuan Province. And using high-resolution exposure would be more accurate to estimate the effect of air pollution on CVD. After TYAP, the cardiovascular mortality risk estimation due to PM2.5 decreased in elderly in SCB, and the risk due to O3 increased in Sichuan Province.