Surface, Satellite Ozone Changes in Northern South America During Low Anthropogenic Emission Conditions : A Machine Learning Approach
2020 presented the ideal conditions for studying the air quality response to several emission reductions due to the Covid-19 lockdowns. Several studies found that the tropospheric ozone increased its concentrations in many countries even in lockdown conditions, but its reasons are not entirely understood. This research aims to better understand the ozone variations in Northern South America. First, satellite and reanalysis data were used to analyze regional ozone, precursors, and meteorological variations. Then, a local analysis for two of the most polluted Colombian cities was performed by quantifying the percentage changes of the ozone and its precursors and by doing a machine learning ensemble (4-models) decomposition to disentangle the contributions that the precursors and the meteorology made for the O3 formation. The results indicated that regional ozone increased 16% its concentration in most areas, especially where wildfires are present in the region. Meteorology is associated with the favorable conditions to promote wildfires in the North of Colombia and Venezuela. Regarding the local analysis, the ensemble shows that the decreased titration process associated with the NO plummeting owing to mobility reduction could be the main contributor to the O3 increase (50%). It also shows that wildfires are an important source of O3, a feature that the ensemble was able to identify. All these tools lead to concluded that i) the increase in O3 produced by the reduction of the titration process that would be associated with an improvement in mobile sources technology has to be considered in the new air quality policies, ii) a boost in international cooperation is essential to control wildfires since an event that occur in one country can affect others and iii) a machine learning decomposition approach couple with sensitivity experiments can help us explain and understand the physico-chemical mechanism that drive ozone formation
Year of publication: |
[2022]
|
---|---|
Authors: | Casallas, Alejandro ; Castillo-Camacho, Maria Paula ; Sanchez, Edwin Ricardo ; González, Yuri ; Celis, Nathalia ; Mendez-Espinosa, Juan Felipe ; Belalcazar, Luis Carlos ; Ferro, Camilo |
Publisher: |
[S.l.] : SSRN |
Subject: | Künstliche Intelligenz | Artificial intelligence | Südamerika | South America | Ozonbelastung | Ozone pollution | Luftverschmutzung | Air pollution |
Saved in:
Saved in favorites
Similar items by subject
-
Short-term hourly ozone concentration forecasting using functional data approach
Shah, Ismail, (2024)
-
Productivity loss amid invisible pollution
Wang, Chunchao, (2020)
-
Chapter 1. Geophysical and Geochemical Aspects of Environmental Degradation
Bolin, Bert, (2003)
- More ...