2020 年新冠疫情大流行期间，韩国两个未封锁的特大城市之间的 PM、PM、和 NO 浓度的人工神经网络模型。
Artificial Neural Network Modeling on PM, PM, and NO Concentrations between Two Megacities without a Lockdown in Korea, for the COVID-19 Pandemic Period of 2020.
机构信息
Department of Computer Engineering, Konkuk University, Chungju 27478, Republic of Korea.
Atmospheric and Oceanic Disaster Research Institute, Gangneung 25563, Republic of Korea.
出版信息
Int J Environ Res Public Health. 2022 Dec 6;19(23):16338. doi: 10.3390/ijerph192316338.
The mutual relationship among daily averaged PM, PM, and NO concentrations in two megacities (Seoul and Busan) connected by the busiest highway in Korea was investigated using an artificial neural network model (ANN)-sigmoid function, for a novel coronavirus (COVID-19) pandemic period from 1 January to 31 December 2020. Daily and weekly mean concentrations of NO in 2020 under neither locked down cities, nor limitation of the activities of vehicles and people by the Korean Government have decreased by about 15%, and 12% in Seoul, and Busan cities, than the ones in 2019, respectively. PM (PM) concentration has also decreased by 15% (10%), and 12% (10%) in Seoul, and Busan, with a similar decline of NO, causing an improvement in air quality in each city. Multilayer perception (MLP), which has a back-propagation training algorithm for a feed-forward artificial neural network technique with a sigmoid activation function was adopted to predict daily averaged PM, PM, and NO concentrations in two cities with their interplay. Root mean square error (RMSE) with the coefficient of determination (R) evaluates the performance of the model between the predicted and measured values of daily mean PM, PM, and NO in Seoul were 2.251 with 0.882 (1.909 with 0.896; 1.913 with 0.892), 0.717 with 0.925 (0.955 with 0.930; 0.955 with 0.922), and 3.502 with 0.729 (2.808 with 0.746; 3.481 with 0.734), in 2 (5; 7) nodes in a single hidden layer. Similarly, they in Busan were 2.155 with 0.853 (1.519 with 0.896; 1.649 with 0.869), 0.692 with 0.914 (0.891 with 0.910; 1.211 with 0.883), and 2.747 with 0.667 (2.277 with 0.669; 2.137 with 0.689), respectively. The closeness of the predicted values to the observed ones shows a very high Pearson r correlation coefficient of over 0.932, except for 0.818 of NO in Busan. Modeling performance using IBM SPSS-v27 software on daily averaged PM, PM, and NO concentrations in each city were compared by scatter plots and their daily distributions between predicted and observed values.
利用人工神经网络模型（ANN-sigmoid 函数）研究了韩国最繁忙公路连接的两个特大城市（首尔和釜山）中每日平均 PM、PM 和 NO 浓度之间的相互关系，研究期间为 2020 年 1 月 1 日至 12 月 31 日的新型冠状病毒（COVID-19）大流行时期。2020 年，在韩国政府没有封锁城市，也没有限制车辆和人员活动的情况下，首尔和釜山的每日和每周平均 NO 浓度分别下降了约 15%和 12%，PM（PM）浓度也分别下降了 15%（10%）和 12%（10%），这导致了每个城市的空气质量得到改善。多层感知器（MLP）采用了具有反向传播训练算法的前馈人工神经网络技术和 sigmoid 激活函数，用于预测两个城市的每日平均 PM、PM 和 NO 浓度及其相互作用。首尔的每日平均 PM、PM 和 NO 预测值与实测值之间的均方根误差（RMSE）和决定系数（R）分别为 2.251 和 0.882（1.909 和 0.896；1.913 和 0.892），0.717 和 0.925（0.955 和 0.930；0.955 和 0.922），3.502 和 0.729（2.808 和 0.746；3.481 和 0.734），在单个隐藏层中有 2（5；7）个节点。同样，在釜山，它们分别为 2.155 和 0.853（1.519 和 0.896；1.649 和 0.869），0.692 和 0.914（0.891 和 0.910；1.211 和 0.883），和 2.747 和 0.667（2.277 和 0.669；2.137 和 0.689）。除了釜山的 NO 为 0.818 外，预测值与观测值的接近程度表明 Pearson r 相关系数非常高，超过 0.932。使用 IBM SPSS-v27 软件在每个城市的每日平均 PM、PM 和 NO 浓度上进行建模性能比较，通过散点图和预测值与观测值之间的每日分布进行比较。
Zotero 插件