He Mike Z, Yitshak-Sade Maayan, Just Allan C, Gutiérrez-Avila Iván, Dorman Michael, de Hoogh Kees, Mijling Bas, Wright Robert O, Kloog Itai
Department of Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, New York, New York.
Department of Geography and Environmental Development, Ben-Gurion University of the Negev, Beer Sheva, Israel.
Atmos Pollut Res. 2023 Jun;14(6). doi: 10.1016/j.apr.2023.101763. Epub 2023 Apr 17.
In recent years, there has been growing interest in developing air pollution prediction models to reduce exposure measurement error in epidemiologic studies. However, efforts for localized, fine-scale prediction models have been predominantly focused in the United States and Europe. Furthermore, the availability of new satellite instruments such as the TROPOsopheric Monitoring Instrument (TROPOMI) provides novel opportunities for modeling efforts. We estimated daily ground-level nitrogen dioxide (NO) concentrations in the Mexico City Metropolitan Area at 1-km grids from 2005 to 2019 using a four-stage approach. In stage 1 (imputation stage), we imputed missing satellite NO column measurements from the Ozone Monitoring Instrument (OMI) and TROPOMI using the random forest (RF) approach. In stage 2 (calibration stage), we calibrated the association of column NO to ground-level NO using ground monitors and meteorological features using RF and extreme gradient boosting (XGBoost) models. In stage 3 (prediction stage), we predicted the stage 2 model over each 1-km grid in our study area, then ensembled the results using a generalized additive model (GAM). In stage 4 (residual stage), we used XGBoost to model the local component at the 200-m scale. The cross-validated R of the RF and XGBoost models in stage 2 were 0.75 and 0.86 respectively, and 0.87 for the ensembled GAM. Cross-validated rootmean-squared error (RMSE) of the GAM was 3.95 μg/m. Using novel approaches and newly available remote sensing data, our multi-stage model presented high cross-validated fits and reconstructs fine-scale NO estimates for further epidemiologic studies in Mexico City.
近年来，人们对开发空气污染预测模型以减少流行病学研究中的暴露测量误差的兴趣与日俱增。然而，针对本地化、精细尺度预测模型的努力主要集中在美国和欧洲。此外，诸如对流层监测仪器（TROPOMI）等新型卫星仪器的出现为建模工作提供了新的机遇。我们采用四阶段方法估算了2005年至2019年墨西哥城大都市区1公里网格的每日地面二氧化氮（NO）浓度。在第一阶段（插补阶段），我们使用随机森林（RF）方法插补来自臭氧监测仪器（OMI）和TROPOMI的缺失卫星NO柱测量值。在第二阶段（校准阶段），我们使用地面监测器和气象特征，通过RF和极端梯度提升（XGBoost）模型校准柱NO与地面NO之间的关联。在第三阶段（预测阶段），我们对研究区域内的每个1公里网格预测第二阶段模型，然后使用广义相加模型（GAM）汇总结果。在第四阶段（残差阶段），我们使用XGBoost对200米尺度的局部分量进行建模。第二阶段RF和XGBoost模型的交叉验证R分别为0.75和0.86，汇总GAM的交叉验证R为0.87。GAM的交叉验证均方根误差（RMSE）为3.95μg/m³。通过新颖的方法和新获得的遥感数据，我们的多阶段模型呈现出较高的交叉验证拟合度，并重建了精细尺度的NO估计值，以供墨西哥城进一步的流行病学研究使用。
