Graduate School of Engineering, Osaka University, Yamadaoka 2-1, Suita, Osaka, 565-0871, Japan.
Department of Public Health, Hyogo College of Medicine, Mukogawa-cho 1-1, Nishinomiya, Hyogo, 663-8501, Japan.
Environ Pollut. 2020 Aug;263(Pt A):114476. doi: 10.1016/j.envpol.2020.114476. Epub 2020 Apr 5.
Accurate estimation of historical PM exposures for epidemiological studies is challenging when extensive monitoring data are limited in duration. Here, we develop a national-scale PM exposure model for Japan using measurements recorded between 2014 and 2016 to estimate monthly means for 1987 through 2016. Our objective is to obtain accurate PM estimates for years prior to implementation of extensive PM monitoring, using observations from a limited period. We utilize a neural network to convey the non-linear relationship between the target pollutant and predictors, while incorporating the associated air pollutants. We obtain high R values of 0.76 and 0.73 through spatial and temporal cross validation, respectively. We evaluate estimation accuracy using an independent data set and achieve an R of 0.75. Moreover, monthly variations for 2000-2013 are well reproduced with correlation coefficients of greater than 0.78, obtained through a comparison with observations. We estimate monthly means at 1 × 1 km resolution from 1987 through 2016. The estimates show decreases in the area and population weighted means beginning in the 1990s. We successfully estimate monthly mean PM concentrations over three decades with outstanding predictive accuracy. Our findings illustrate that the presented approach achieves accurate long-term historical estimations using observations limited in duration.
当监测数据的时间范围有限时，准确估计流行病学研究中的历史 PM 暴露量是具有挑战性的。在这里，我们使用 2014 年至 2016 年记录的测量数据，为日本开发了一个全国范围的 PM 暴露模型，以估计 1987 年至 2016 年的每月平均值。我们的目标是利用有限时间段的观测值，为广泛 PM 监测实施之前的年份获得准确的 PM 估计值。我们利用神经网络来传达目标污染物与预测因子之间的非线性关系，同时纳入相关的空气污染物。我们通过空间和时间交叉验证分别获得了 0.76 和 0.73 的高 R 值。我们使用独立数据集评估估计精度，得到了 0.75 的 R 值。此外，通过与观测值的比较，我们获得了大于 0.78 的相关系数，很好地再现了 2000-2013 年的每月变化。我们从 1987 年至 2016 年以 1×1 公里的分辨率估计每月平均值。这些估计表明，从 20 世纪 90 年代开始，面积加权平均值和人口加权平均值都有所下降。我们成功地使用时间有限的观测值估计了过去三十年的每月平均 PM 浓度，具有出色的预测精度。我们的研究结果表明，该方法通过使用有限的观测值，实现了准确的长期历史估计。
