A hybrid approach to predict daily NO2 concentrations at city block scale.
A hybrid approach to predict daily NO2 concentrations at city block scale.
复制标题
DOI：
10.1016/j.scitotenv.2020.143279
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Xueying Zhang;A. Just;H. Hsu;I. Kloog;M. Woody;Zhongyuan Mi;Johnathan Rush;P. Georgopoulos;R. Wright;A. Stroustrup
中科院分区：
文献类型：
--
作者：
Xueying Zhang;A. Just;H. Hsu;I. Kloog;M. Woody;Zhongyuan Mi;Johnathan Rush;P. Georgopoulos;R. Wright;A. Stroustrup
估计周围环境中二氧化氮(NO2)的浓度是具有挑战性的，因为当地化石燃料燃烧产生的NO2在空间和时间上的浓度差异很大。这项研究展示了一种结合弥散模拟和土地利用回归(LUR)的综合混合方法，以高空间分辨率(例如，50米)预测纽约三州地区的日NO2浓度。使用研究线源(R-LINE)模型，利用公路性能和管理系统提供的交通数据输入和NOAA地面综合数据库提供的气象数据，估计了2015-2017年间环境保护局在研究区的NO2监测点与交通相关的NO2日浓度。我们使用R线预测的NO2日浓度来建立混合影响回归模型，包括代表土地利用特征、地理特征、天气和其他预测因素的额外变量。采用弹性网法对混合模型进行选择。用样本外决定系数(R2)和十次交叉验证(CV)的均方误差均方根(RMSE)来评价每个模型的性能。混合模型具有较好的预测效果(CV R2：0.75~0.79，RMSE：3.9~4.0 ppb)。R线输出使整体、空间和时间变异R2分别提高了10.0%、18.9%和7.7%。考虑到R线的输出是基于点的，并且具有灵活的空间分辨率，这种混合方法允许以极高的空间分辨率预测日NO2，例如城市街区。
Estimating the ambient concentration of nitrogen dioxide (NO2) is challenging because NO2generated by local fossil fuel combustion varies greatly in concentration across space and time. This study demonstrates an integrated hybrid approach combining dispersion modeling and land use regression (LUR) to predict daily NO2concentrations at a high spatial resolution (e.g., 50 m) in the New York tri-state area. The daily concentration of traffic-related NO2was estimated at the Environmental Protection Agency's NO2monitoring sites in the study area for the years 2015–2017, using the Research LINE source (R-LINE) model with inputs of traffic data provided by the Highway Performance and Management System and meteorological data provided by the NOAA Integrated Surface Database. We used the R-LINE-predicted daily concentrations of NO2to build mixed-effects regression models, including additional variables representing land use features, geographic characteristics, weather, and other predictors. The mixed model was selected by the Elastic Net method. Each model's performance was evaluated using the out-of-sample coefficient of determination (R2) and the square root of mean squared error (RMSE) from ten-fold cross-validation (CV). The mixed model showed a good prediction performance (CV R2: 0.75–0.79, RMSE: 3.9–4.0 ppb). R-LINE outputs improved the overall, spatial, and temporal CV R2by 10.0%, 18.9% and 7.7% respectively. Given the output of R-LINE is point-based and has a flexible spatial resolution, this hybrid approach allows prediction of daily NO2at an extremely high spatial resolution such as city blocks.