tetano
Editor, Senior Moderator
Appl Energy
. 2020 Dec 1;279:115835.
doi: 10.1016/j.apenergy.2020.115835. Epub 2020 Sep 12.
The relationship between air pollution and COVID-19-related deaths: An application to three French cities
Cosimo Magazzino[SUP] 1 [/SUP], Marco Mele[SUP] 2 [/SUP], Nicolas Schneider[SUP] 3 [/SUP]
Affiliations
Abstract
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[SUB]2.5[/SUB] and PM[SUB]10[/SUB] 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[SUB]2.5[/SUB] and PM[SUB]10[/SUB] connected to COVID-19: 17.4 ?g/m[SUP]3[/SUP] (PM[SUB]2.5[/SUB]) and 29.6 ?g/m[SUP]3[/SUP] (PM[SUB]10[/SUB]) for Paris; 15.6 ?g/m[SUP]3[/SUP] (PM[SUB]2.5[/SUB]) and 20.6 ?g/m[SUP]3[/SUP] (PM[SUB]10[/SUB]) for Lyon; 14.3 ?g/m[SUP]3[/SUP] (PM[SUB]2.5[/SUB]) and 22.04 ?g/m[SUP]3[/SUP] (PM[SUB]10[/SUB]) 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.
Keywords: ANNs, Artificial Neural Networks; Air pollution; Artificial neural networks; CH4, Methane; CMAQ, Community Multiscale Air Quality; CO, Carbon Monoxide; COVID-19; COVID-19, Coronavirus Disease 19; D2C, Causal Direction from Dependency; GAM, Generalized Additive Model; GHG, Greenhouse Gas; ML, Machine Learning; Machine learning; NO2, Nitrogen Dioxide; NOx, Nitrogen Oxides; O3, Ozone; PM10, Particulate Matter with an aerodynamic diameter < 10.0 ?m; PM2.5, Particulate Matter with an aerodynamic diameter < 2.5 ?m; Particulate matter; SO2, Sulfur Dioxide; SO3, Sulphur Trioxide; SOx, Sulphur Oxides; VOC, Volatile Organic Compounds.
. 2020 Dec 1;279:115835.
doi: 10.1016/j.apenergy.2020.115835. Epub 2020 Sep 12.
The relationship between air pollution and COVID-19-related deaths: An application to three French cities
Cosimo Magazzino[SUP] 1 [/SUP], Marco Mele[SUP] 2 [/SUP], Nicolas Schneider[SUP] 3 [/SUP]
Affiliations
- PMID: 32952266
- PMCID: PMC7486865
- DOI: 10.1016/j.apenergy.2020.115835
Abstract
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[SUB]2.5[/SUB] and PM[SUB]10[/SUB] 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[SUB]2.5[/SUB] and PM[SUB]10[/SUB] connected to COVID-19: 17.4 ?g/m[SUP]3[/SUP] (PM[SUB]2.5[/SUB]) and 29.6 ?g/m[SUP]3[/SUP] (PM[SUB]10[/SUB]) for Paris; 15.6 ?g/m[SUP]3[/SUP] (PM[SUB]2.5[/SUB]) and 20.6 ?g/m[SUP]3[/SUP] (PM[SUB]10[/SUB]) for Lyon; 14.3 ?g/m[SUP]3[/SUP] (PM[SUB]2.5[/SUB]) and 22.04 ?g/m[SUP]3[/SUP] (PM[SUB]10[/SUB]) 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.
Keywords: ANNs, Artificial Neural Networks; Air pollution; Artificial neural networks; CH4, Methane; CMAQ, Community Multiscale Air Quality; CO, Carbon Monoxide; COVID-19; COVID-19, Coronavirus Disease 19; D2C, Causal Direction from Dependency; GAM, Generalized Additive Model; GHG, Greenhouse Gas; ML, Machine Learning; Machine learning; NO2, Nitrogen Dioxide; NOx, Nitrogen Oxides; O3, Ozone; PM10, Particulate Matter with an aerodynamic diameter < 10.0 ?m; PM2.5, Particulate Matter with an aerodynamic diameter < 2.5 ?m; Particulate matter; SO2, Sulfur Dioxide; SO3, Sulphur Trioxide; SOx, Sulphur Oxides; VOC, Volatile Organic Compounds.