Assessing the Lockdown Effects on Air Quality during COVID-19 Era

TL;DR

This study analyzes how COVID-19 lockdown measures affected air quality in four European cities by examining satellite data and employing machine learning to predict pollutant levels, revealing moderate correlations and predictive models.

Contribution

It introduces a combined satellite data and machine learning approach to assess and predict short-term air quality changes due to lockdown measures.

Findings

Lockdown measures showed weak to moderate correlation with pollutant levels.

Machine learning models can predict pollutant concentrations two days ahead.

Satellite data effectively captures short-term air quality variations.

Abstract

In this work we investigate the short-term variations in air quality emissions, attributed to the prevention measures, applied in different cities, to mitigate the COVID-19 spread. In particular, we emphasize on the concentration effects regarding specific pollutant gases, such as carbon monoxide (CO), ozone (O3), nitrogen dioxide (NO2) and sulphur dioxide (SO2). The assessment of the impact of lockdown on air quality focused on four European Cities (Athens, Gladsaxe, Lodz and Rome). Available data on pollutant factors were obtained using global satellite observations. The level of the employed prevention measures is employed using the Oxford COVID-19 Government Response Tracker. The second part of the analysis employed a variety of machine learning tools, utilized for estimating the concentration of each pollutant, two days ahead. The results showed that a weak to moderate correlation exists between the corresponding measures and the pollutant factors and that it is possible to create models which can predict the behaviour of the pollutant gases under daily human activities.