Zuidema Christopher, Bi Jianzhao, Burnham Dustin, Carmona Nancy, Gassett Amanda J, Slager David L, Schumacher Cooper, Austin Elena, Seto Edmund, Szpiro Adam A, Sheppard Lianne
Department of Occupational and Environmental Health Sciences, University of Washington, Seattle, WA, USA.
Department of Biostatistics, University of Washington, Seattle, WA, USA.
J Expo Sci Environ Epidemiol. 2025 Apr;35(2):169-179. doi: 10.1038/s41370-024-00667-w. Epub 2024 Apr 9.
Statistical models of air pollution enable intra-urban characterization of pollutant concentrations, benefiting exposure assessment for environmental epidemiology. The new generation of low-cost sensors facilitate the deployment of dense monitoring networks and can potentially be used to improve intra-urban models of air pollution.
Develop and evaluate a spatiotemporal model for nitrogen dioxide (NO) in the Puget Sound region of WA, USA for the Adult Changes in Thought Air Pollution (ACT-AP) study and assess the contribution of low-cost sensor data to the model's performance through cross-validation.
We developed a spatiotemporal NO model for the study region incorporating data from 11 agency locations, 364 supplementary monitoring locations, and 117 low-cost sensor (LCS) locations for the 1996-2020 time period. Model features included long-term time trends and dimension-reduced land use regression. We evaluated the contribution of LCS network data by comparing models fit with and without sensor data using cross-validated (CV) summary performance statistics.
The best performing model had one time trend and geographic covariates summarized into three partial least squares components. The model, fit with LCS data, performed as well as other recent studies (agency cross-validation: CV- root mean square error (RMSE) = 2.5 ppb NO; CV- coefficient of determination ( ) = 0.85). Predictions of NO concentrations developed with LCS were higher at residential locations compared to a model without LCS, especially in recent years. While LCS did not provide a strong performance gain at agency sites (CV-RMSE = 2.8 ppb NO; CV- = 0.82 without LCS), at residential locations, the improvement was substantial, with RMSE = 3.8 ppb NO and = 0.08 (without LCS), compared to CV-RMSE = 2.8 ppb NO and CV- = 0.51 (with LCS).
We developed a spatiotemporal model for nitrogen dioxide (NO) pollution in Washington's Puget Sound region for epidemiologic exposure assessment for the Adult Changes in Thought Air Pollution study. We examined the impact of including low-cost sensor data in the NO model and found the additional spatial information the sensors provided predicted NO concentrations that were higher than without low-cost sensors, particularly in recent years. We did not observe a clear, substantial improvement in cross-validation performance over a similar model fit without low-cost sensor data; however, the prediction improvement with low-cost sensors at residential locations was substantial. The performance gains from low-cost sensors may have been attenuated due to spatial information provided by other supplementary monitoring data.
空气污染统计模型能够对城市内污染物浓度进行特征描述，有助于环境流行病学的暴露评估。新一代低成本传感器便于密集监测网络的部署，并有可能用于改进城市内空气污染模型。
为美国华盛顿州普吉特海湾地区的成人思维变化空气污染（ACT-AP）研究开发并评估二氧化氮（NO）的时空模型，并通过交叉验证评估低成本传感器数据对模型性能的贡献。
我们为研究区域开发了一个时空NO模型，纳入了1996 - 2020年期间来自11个机构监测点、364个补充监测点和117个低成本传感器（LCS）监测点的数据。模型特征包括长期时间趋势和降维土地利用回归。我们通过使用交叉验证（CV）汇总性能统计数据比较有和没有传感器数据的拟合模型，评估LCS网络数据的贡献。
性能最佳的模型有一个时间趋势和地理协变量，汇总为三个偏最小二乘分量。该模型结合LCS数据，表现与其他近期研究相当（机构交叉验证：CV - 均方根误差（RMSE）= 2.5 ppb NO；CV - 决定系数（ ）= 0.85）。与没有LCS的模型相比，使用LCS得出的NO浓度预测在居民区更高，尤其是近年来。虽然LCS在机构监测点未带来显著性能提升（CV - RMSE = 2.8 ppb NO；没有LCS时CV - = 0.82），但在居民区，改进显著，RMSE = 3.8 ppb NO且 = 0.08（没有LCS），而使用LCS时CV - RMSE = 2.8 ppb NO且CV - = 0.51。
我们为华盛顿州普吉特海湾地区的二氧化氮（NO）污染开发了一个时空模型，用于成人思维变化空气污染研究的流行病学暴露评估。我们研究了在NO模型中纳入低成本传感器数据的影响，发现传感器提供的额外空间信息预测的NO浓度高于没有低成本传感器时的情况，尤其是近年来。我们没有观察到与没有低成本传感器数据的类似拟合模型相比，交叉验证性能有明显的实质性改进；然而，低成本传感器在居民区的预测改进是显著的。由于其他补充监测数据提供的空间信息，低成本传感器的性能提升可能有所减弱。
