Department of Epidemiology, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100037, China; Department of Environmental Health, Rollins School of Public Health, Emory University, Atlanta, GA 30322, USA.
Department of Environmental Health, Rollins School of Public Health, Emory University, Atlanta, GA 30322, USA.
Sci Total Environ. 2019 Dec 20;697:134094. doi: 10.1016/j.scitotenv.2019.134094. Epub 2019 Aug 27.
Previous PM related epidemiological studies mainly relied on data from sparse regulatory monitors to assess exposure. The introduction of non-regulatory PM monitors presents both opportunities and challenges to researchers and air quality managers. In this study, we evaluated the advantages and limitations of integrating non-regulatory PM measurements into a satellite-based daily PM model at 100 m resolution in New York City in 2015. Two separate machine learning models were developed, one using only PM data from the US Environmental Protection Agency (EPA), and the other with measurements from both EPA and the New York City Community Air Survey (NYCCAS). The EPA-only model obtained a cross-validation (CV) R of 0.85 while the EPA + NYCCAS model obtained a CV R of 0.73. With the help of the NYCCAS measurements, the EPA + NYCCAS model predicted distinctly different PM spatial patterns and more pollution hotspots compared with the EPA model, and its predictions were >15% higher than the EPA model along major roads and in densely populated areas. Our results indicated that satellite AOD and non-regulatory PM measurements can be fused together to capture neighborhood-scale PM levels and previous studies may have underestimated the disease burden due to PM in densely populated areas.
先前的 PM 相关流行病学研究主要依赖于来自稀疏监管监测器的数据来评估暴露情况。非监管性 PM 监测器的引入为研究人员和空气质量管理者带来了机遇和挑战。在这项研究中，我们评估了在 2015 年将非监管性 PM 测量值整合到基于卫星的每日 PM 模型（分辨率为 100m）中的优势和局限性，在纽约市。开发了两个独立的机器学习模型，一个仅使用美国环境保护署 (EPA) 的 PM 数据，另一个则使用 EPA 和纽约市社区空气调查 (NYCCAS) 的测量值。EPA 模型的交叉验证 (CV) R 为 0.85，而 EPA+NYCCAS 模型的 CV R 为 0.73。在 NYCCAS 测量值的帮助下，EPA+NYCCAS 模型预测了与 EPA 模型明显不同的 PM 空间模式和更多的污染热点，并且其预测值在主要道路和人口密集地区比 EPA 模型高>15%。我们的结果表明，卫星 AOD 和非监管性 PM 测量值可以融合在一起，以捕捉邻里尺度的 PM 水平，先前的研究可能低估了人口密集地区 PM 造成的疾病负担。
