Abstract
BACKGROUND AND AIM: China faces serious air pollution problems, especially for traffic-related pollutants such as nitrogen dioxide (NO₂). Epidemiological studies in China were much less focused on NO₂ exposure and consequent health effects as compared to fine particles exposure at national scale, mainly due to lack of high-quality exposure model for accurate NO₂ predictions over a long period. We aim to develop a national model in estimating long-term NO₂ exposure in China with high spatiotemporal resolution. METHODS: We proposed an advanced modeling framework that incorporated multisource, high-quality predictors data (e.g., satellite observations [OMI NO₂, TROPOMI NO₂, and MAIAC AOD], chemical transport model simulations, high-resolution geographical variables) and three independent machine learning algorithms into an ensemble model. The model included three-stages: (1) filling missing satellite data; (2) building an ensemble model and predicting daily NO₂ levels from 2005 to 2019 across China at 1-km resolution; (3) downscaling the predictions to 100-meter resolution at city scale. RESULTS:Our model achieved a high performance with an overall cross-validated (CV) R² of 0.72 and a spatial R² of 0.85. The model has the potential to be extrapolated to previous years (2005-2012) or regions without monitoring data, with moderately good performance (CV R² 0.68). We identified a clear decreasing trend of NO₂ exposure from 2005 to 2019 across the country with the largest reduction in suburban and rural areas. Our downscaled model further improved the prediction ability by 4% in some megacities and captured substantial NO₂ variations within 1-km grids in urban areas especially near major roads. CONCLUSIONS:We developed a NO₂ national model with very high spatiotemporal resolution (daily, 1-km grid). Our model provided flexibility at both temporal and spatial scales that can be useful for exposure assessment and epidemiological studies with various study domains (e.g. national or citywide) and settings (e.g. long-term and short-term). KEYWORDS: air pollution, oxides of nitrogen, exposure assessment, long-term exposure, modeling
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.