Department of Science and Technology, Ministry of Natural Resources and Environment, 10 Ton That Thuyet Street, My Dinh 2 Ward, Nam Tu Liem District, Hanoi City, Vietnam.
Water Resources Institute, 8 Phao Dai Lang Street, Lang Thuong Ward, Dong Da District, Hanoi City, Vietnam.
Sci Rep. 2020 Nov 6;10(1):19268. doi: 10.1038/s41598-020-75547-y.
The degradation of air quality is the most concerned issue of our society due to its harmful impacts on human health, especially in cities with rapid urbanization and population growth like Hanoi, the capital of Vietnam. This study aims at developing a new approach that combines data-driven models and interpolation technique to develop the PM concentration maps from meteorological factors for the central area of Hanoi. Data-driven models that relate the PM concentration with the meteorological factors at the air quality monitoring stations in the study area were developed using the Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) algorithms. Models' performance comparison showed that ANN models yielded better goodness-of-fit indices than MLR models at all stations in the study area with average coefficient of correlation (r) and Nash-Sutcliffe Efficiency Index (NSE) of 0.51 and 0.34 for the former, and 0.7 and 0.49 for the latter. These indices indicates that the ANN-based data-driven models outperformed the MLR-based models. Thus, the ANN-based models and the Inverse Distance Weighting (IDW) interpolation technique were then combined for mapping the monthly PM concentration with a spatial resolution of 1 km from global meteorological data. With this combination, the PM concentration maps account for both local PM concentration and impacts of spatio-temporal variations of meteorological factors on the PM concentration. This study provides a promising method to predict the PM concentration with a high spatio-temporal resolution from meteorological data.
由于空气质量下降对人类健康造成的有害影响，空气质量下降是我们社会最关注的问题，尤其是在城市化和人口增长迅速的城市，如越南首都河内。本研究旨在开发一种新方法，该方法结合了数据驱动模型和插值技术，从气象因素为河内中心区域开发 PM 浓度图。使用多元线性回归 (MLR) 和人工神经网络 (ANN) 算法，针对研究区域内空气质量监测站的 PM 浓度与气象因素之间的关系，开发了数据驱动模型。模型性能比较表明，在研究区域内的所有站点，ANN 模型的拟合优度指数 (r) 和纳什-苏特克里夫效率指数 (NSE) 均优于 MLR 模型，前者的平均值分别为 0.51 和 0.34，后者的平均值分别为 0.7 和 0.49。这些指数表明，基于 ANN 的数据驱动模型优于基于 MLR 的模型。因此，随后将基于 ANN 的模型和反距离权重 (IDW) 插值技术结合起来，从全球气象数据中以 1 公里的空间分辨率绘制每月 PM 浓度图。通过这种组合，PM 浓度图既考虑了当地 PM 浓度，又考虑了气象因素时空变化对 PM 浓度的影响。本研究提供了一种很有前途的方法，可根据气象数据以高时空分辨率预测 PM 浓度。
