The relationship between air pollution and COVID-19-related deaths: An application to three French cities
The relationship between air pollution and COVID-19-related deaths: An application to three French cities
复制标题
DOI：
10.1016/j.apenergy.2020.115835
复制
发表时间：
2020-12-01
期刊：
影响因子：
11.2
通讯作者：
Schneider, Nicolas
中科院分区：
文献类型：
--
作者：
Magazzino, Cosimo;Mele, Marco;Schneider, Nicolas
由于严重依赖石油产品（主要是汽油和柴油），法国交通部门是颗粒物的主要排放者，其临界水平对城市居民的健康造成有害影响。我们选择了法国的三个主要城市（巴黎、里昂和马赛）来调查冠状病毒病19（COVID-19）爆发与空气污染之间的关系。利用人工神经网络（ANN）实验，我们确定了与COVID-19相关死亡相关的PM2. 5和PM10浓度。我们的重点是颗粒物（PM）在传播流行病方面的潜在影响。其基本假设是，预先确定的颗粒物浓度可能会助长COVID-19，并使呼吸系统更容易受到这种感染。经验策略使用了创新的机器学习（ML）方法。特别是，通过人工神经网络中所谓的切割技术，我们发现了与COVID-19相关的PM2.5和PM10的新阈值水平：17.4 μ g/m（3）巴黎的PM2.5和PM10分别为29.6微克/立方米（3）和15.6微克/立方米（3）里昂的PM2.5和PM10分别为20.6 μ g/m3和14.3 μ g/m3;马赛的PM2.5和PM10分别为22.04 μ g/m3和22.04 μ g/m3。有趣的是，人工神经网络确定的所有阈值都高于欧洲议会规定的限制。最后，因果方向依赖（D2C）算法被应用于检查我们的研究结果的一致性。
YBeing heavily dependent to oil products (mainly gasoline and diesel), the French transport sector is the main emitter of Particulate Matter (PMs) whose critical levels induce harmful health effects for urban inhabitants. We selected three major French cities (Paris, Lyon, and Marseille) to investigate the relationship between the Coronavirus Disease 19 (COVID-19) outbreak and air pollution. Using Artificial Neural Networks (ANNs) experiments, we have determined the concentration of PM2.5 and PM10 linked to COVID-19-related deaths. Our focus is on the potential effects of Particulate Matter (PM) in spreading the epidemic. The underlying hypothesis is that a pre-determined particulate concentration can foster COVID-19 and make the respiratory system more susceptible to this infection. The empirical strategy used an innovative Machine Learning (ML) methodology. In particular, through the so-called cutting technique in ANNs, we found new threshold levels of PM2.5 and PM10 connected to COVID-19: 17.4 mu g/m(3) (PM2.5) and 29.6 mu g/m(3) (PM10) for Paris; 15.6 mu g/m(3) (PM2.5) and 20.6 mu g/m(3) (PM10) for Lyon; 14.3 mu g/m(3) (PM2.5) and 22.04 mu g/m(3) (PM10) for Marseille. Interestingly, all the threshold values identified by the ANNs are higher than the limits imposed by the European Parliament. Finally, a Causal Direction from Dependency (D2C) algorithm is applied to check the consistency of our findings.