Exploring air pollution characteristics from spatio-temporal perspective: A case study of the top 10 urban agglomerations in China

Revealing the impacts of the built environment factors on pedestrian-weighted air pollutant concentration using automated and interpretable machine learning

Urban air pollution poses significant health risks, especially to pedestrians due to their proximity to pollutants and lack of physical protection. Understanding the influence of built environment factors is essential to mitigate this pollution and safeguard pedestrian health. However, most existing literature focus primarily on pollutant sources and dispersion dynamics, paying less attention to the factors that affect the extent of pedestrian exposure to pollutants. Additionally, while machine learning has gained traction in urban studies, challenges remain in model optimization and interpretability, leading to limited transparency and reduced clarity in environment strategy development. To address these gaps, this study proposes a methodological framework to measure pedestrian-weighted air pollutant concentrations (PWAPC) and analyze the complex effects of the built environment. The objectives include (1) integrating air pollution and pedestrian volume data to quantify PWAPC levels, and (2) employing automated machine learning (AutoML) and interpretable machine learning (IML) to model PWAPC and evaluate key built environment impacts. A case study on PM2.5 concentrations in Central London demonstrates the efficiency of AutoML in algorithm selection and hyperparameter optimization. Using IML, critical factors such as points of interest (POIs), traffic infrastructure, diversion ratios, betweenness centrality, street canyon effects, and urban greenness are identified. The analysis also reveals non-linear relationships between these factors and PWAPC. This study provides actionable insights for urban planning and environmental management.

Novel method for predicting concentrations of incineration flue gas based on waste composition and machine learning

The complex composition of solid waste leads to the variability of flue gas emissions during its incineration, which poses a challenge to the stable operation of incineration and pollution control systems. To address this problem, the study explored a new method to predict the concentrations of flue gas pollutants during incineration based on the composition of mixed solid waste using machine learning. Through comprehensive model interpretation and analysis, the important influence of waste composition characteristics on the generation of flue gas pollutants during incineration was deeply explored. The study found that rubber and plastic components significantly promoted the conversion of C to CO during waste incineration; N content and C/N ratio had a significant effect on the generation of NOX; S content and C/S ratio affected the generation of SO2; Cl content and C/Cl ratio had a significant effect on the generation of HCl, especially with PVC components. The extreme gradient boosting tree (XGBOOST) model optimized by feature engineering showed more excellent R2-validation (0.98, 0.94, 1.00, 0.98, 1.00, 0.98) for predicting CO2, CO, N2O, NO, SO2, and HCl concentration, than K-nearest neighbor (KNN), random forest (RF), and light gradient boosting machine (LGBM). This study provides a new prediction and optimization method for waste incineration plants, which can guide the regulation of feedstock and incineration parameters, thus improving operating efficiency and pollution control. It is of great significance to promote sustainable waste management and environmental protection.

Spatiotemporal characteristics analysis of multi-factorial air pollution in the Jing-Jin-Ji region based on improved sequential ICI method and novel grey spatiotemporal incidence models

Air pollution shares the attributes of multi-factorial influence and spatiotemporal complexity, leading to air pollution control assistance models easily falling into a state of failure. To address this issue, we design a framework containing improved data fusion method, novel grey incidence models and air pollution spatiotemporal analysis to analyze the complex characteristics of air pollution under the fusion of multiple factors. Firstly, we improve the existing data fusion method for multi-factor fusion. Subsequently, we construct two grey spatiotemporal incidence models to examine the spatiotemporal characteristics of multi-factorial air pollution in network relationships and changing trends. Furthermore, we propose two new properties that can manifest the performance of grey incidence analysis, and we provide detailed proof of the properties of the new models. Finally, in the Jing-Jin-Ji region, the novel models are used to study the network relationships and trend changes of air pollution. The findings are as follows: (1) Two highly polluted belts in the region require attention. (2) Although the air pollution network under multi-factorial fusion obeys the first law of geography, the network density and node density exhibit significant variations. (3) From 2013 to 2021, all pollutants except O3 show improvement. (4) Recommendations for responses are presented based on the above-mentioned results. (5) The parameter analyses, model comparisons, Monte Carlo experiments and model feature summaries illustrate that the proposed models are practical, interpretable and considerably outperform various prevailing competitors with remarkable universality.

Governance effects of pollution reduction and carbon mitigation of carbon emission trading policy in China

China's carbon emission trading policy plays a crucial role in achieving both its "3060" dual carbon objectives and the United Nations Sustainable Development Goal 13 (SDG 13) on climate action. The policy's effectiveness in reducing pollution and mitigating carbon emissions holds significant importance. This paper investigated whether China's carbon emission trading policy affects pollution reduction (PM2.5 and SO2) and carbon mitigation (CO2) in pilot regions, using panel data from 30 provinces and municipalities in China from 2005 to 2019 and employing a multi-period difference-in-differences (DID) model. Furthermore, it analyzed the heterogeneity of carbon market mechanisms and regional variations. Finally, it examined the governance pathways for pollution reduction and carbon mitigation from a holistic perspective. The results indicate that: (1) China's carbon emission trading policy has reduced CO2 emissions by 18% and SO2 emissions by 36% in pilot areas, with an immediate impact on the "carbon mitigation" effect, while the "pollution reduction" effect exhibits a time lag. (2) Higher carbon trading prices lead to stronger "carbon mitigation" effect, and larger carbon market scales are associated with greater "pollution reduction" effects on PM2.5. Governance effects on pollution reduction and carbon mitigation vary among pilot regions: Carbon markets of Beijing, Chongqing, Shanghai, and Tianjin show significant governance effects in both "pollution reduction" and "carbon mitigation", whereas Guangdong's carbon market exhibits only a "pollution reduction" effect, and Hubei's carbon market demonstrates only a "carbon mitigation" effect. (3) Currently, China's carbon emission trading policy achieves pollution reduction and carbon mitigation through "process management" and "end-of-pipe treatment". This study could provide empirical insights and policy implications for pollution reduction and carbon mitigation, as well as for the development of China's carbon emission trading market.

The Association Between Urbanization and Electrocardiogram Abnormalities in China: a Nationwide Longitudinal Study

The health effects of urbanization are controversial. The association between urbanization and reversible subclinical risks of cardiovascular diseases (e.g., electrocardiogram (ECG) abnormalities) has rarely been studied. This study aimed to assess the association between urbanization and ECG abnormalities in China based on the China National Stroke Screening Survey (CNSSS). We used changes in the satellite-measured impervious surfaces rate and nighttime light data to assess the level of urbanization. Every interquartile increment in the impervious surfaces rate or nighttime light was related to a decreased risk of ECG abnormalities, with odds ratios of 0.894 (95% CI, 0.869-0.920) or 0.809 (95% CI, 0.772-0.847), respectively. And we observed a U-shaped nonlinear exposure-response relationship curve between the impervious surfaces rate and ECG abnormalities. In conclusion, the current average level of urbanization among the studied Chinese adults remains a beneficial factor for reducing cardiovascular risks.