Being 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 PM_2.5 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 PM_2.5 and PM₁₀ connected to COVID-19: 17.4 µg/m³ (PM_2.5) and 29.6 µg/m³ (PM₁₀) for Paris; 15.6 µg/m³ (PM_2.5) and 20.6 µg/m³ (PM₁₀) for Lyon; 14.3 µg/m³ (PM_2.5) and 22.04 µg/m³ (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.

法国交通部门严重依赖石油产品（主要是汽油和柴油），是颗粒物（PM）的主要排放者，其临界水平会对城市居民的健康造成有害影响。我们选择了法国三个主要城市（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。通过人工神经网络 (ANN) 实验，我们确定了与 COVID-19 相关死亡相关的 PM _2.5和 PM ₁₀浓度。我们的重点是颗粒物 (PM) 对流行病传播的潜在影响。基本假设是，预先确定的颗粒浓度可以促进 COVID-19 并使呼吸系统更容易受到这种感染。实证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 PM _2.5和 PM ₁₀的新阈值水平：17.4 µg/m ³ (PM _2.5 ) 和 29.6 µg/m ³ (PM ₁₀ )巴黎;里昂为 15.6 µg/m ³ (PM _2.5 ) 和 20.6 µg/m ³ (PM ₁₀ )；马赛为 14.3 µg/m ³ (PM _2.5 ) 和 22.04 µg/m ³ (PM ₁₀ )。有趣的是，人工神经网络确定的所有阈值都高于欧洲议会施加的限制。最后，应用依赖关系因果方向（D2C）算法来检查我们研究结果的一致性。