A machine learning approach to address air quality changes during the COVID-19 lockdown in Buenos Aires, Argentina

Diaz Resquin, Melisa; Lichtig, Pablo; Alessandrello, Diego; De Oto, Marcelo; Gómez, Darío; Rössler, Cristina; Castesana, Paula; Dawidowski, Laura

doi:https://doi.org/10.5194/essd-15-189-2023

Articles | Volume 15, issue 1

https://doi.org/10.5194/essd-15-189-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Benchmark datasets and machine learning algorithms for Earth...

https://doi.org/10.5194/essd-15-189-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 15, issue 1

Data description paper

|

10 Jan 2023

Data description paper |

| 10 Jan 2023

A machine learning approach to address air quality changes during the COVID-19 lockdown in Buenos Aires, Argentina

Melisa Diaz Resquin, Pablo Lichtig, Diego Alessandrello, Marcelo De Oto, Darío Gómez, Cristina Rössler, Paula Castesana, and Laura Dawidowski

Supplement

https://doi.org/10.5194/essd-15-189-2023-supplement

Data sets

AQ-CNEA-CAC Air quality dataset (2019-2020): "A machine learning approach to address air quality changes during the COVID-19 lockdown in Buenos Aires, Argentina" Melisa Diaz Resquin, Diego Alessandrello, Marcelo De Oto, Pablo Lichtig, Hector Bajano, Alejandro Ponso, Facundo Bajano, Darío Gomez, and Laura Dawidowski https://doi.org/10.17632/h9y4hb8sf8.1

Model code and software

AQ-CNEA-CAC Air quality dataset (2019-2020): "A machine learning approach to address air quality changes during the COVID-19 lockdown in Buenos Aires, Argentina" Melisa Diaz Resquin, Diego Alessandrello, Marcelo De Oto, Pablo Lichtig, Hector Bajano, Alejandro Ponso, Facundo Bajano, Darío Gomez, and Laura Dawidowski https://doi.org/10.17632/h9y4hb8sf8.1

Download

The requested paper has a corresponding corrigendum published. Please read the corrigendum first before downloading the article.

Article (8407 KB)
Full-text XML

Short summary

We explored the performance of the random forest algorithm to predict CO, NO_x, PM₁₀, SO₂, and O₃ air quality concentrations and comparatively assessed the monitored and modeled concentrations during the COVID-19 lockdown phases. We provide the first long-term O₃ and SO₂ observational dataset for an urban–residential area of Buenos Aires in more than a decade and study the responses of O₃ to the reduction in the emissions of its precursors because of its relevance regarding emission control.