Assessing the COVID‐19 Impact on Air Quality: A Machine Learning Approach

Abstract

The worldwide research initiatives on Corona Virus disease 2019 lockdown effect on air quality agree on pollution reduction, but the most reliable method to pollution reduction quantification is still in debate. In this paper, machine learning models based on a Gradient Boosting Machine algorithm are built to assess the outbreak impact on air quality in Quito, Ecuador. First, the precision of the prediction was evaluated by cross‐validation on the four years prelockdown, showing a high accuracy to estimate the real pollution levels. Then, the changes in pollution are quantified. During the full lockdown, air pollution decreased by −53 ± 2%, −45 ± 11%, −30 ± 13%, and −15 ± 9% for NO2, SO2, CO, and PM2.5, respectively. The traffic‐busy districts were the most impacted areas of the city. After the transition to the partial relaxation, the concentrations have nearly returned to the levels as before the pandemic. The quantification of pollution drop is supported by an assessment of the prediction confidence.

Gradient Boosting Machine to Assess the Public Protest Impact on Urban Air Quality

“…For this latter pollutant, the observational inter-period analysis tends to overperform the GBM (except the northern suburban S2-Cotocollao site), even if the difference is minuscule. This result is consistent with previous studies showing a lower performance of the models to predict SO 2 than other pollutants [25,33,44]. It suggests that the ML model should integrate additional features to improve the prediction of this particular contaminant [45].…”

“…These statistics confirm the importance of the suspension of human activities, especially the circulation of motorized traffic. This has been previously proven globally during the COVID-19 pandemic [25,[40][41][42][43]. While the primary pollutants show a significant reduction due to the reduction in anthropogenic activities during the national strike, O 3 shows only a slight reduction (−6.82 ± 15.11%) in its concentrations.…”

“…This apparent contradiction can be explained by the fact that the protest occurred in quite a short period of time, for which the environmental condition (e.g., seasonal variation) did not change significantly. It suggests that a simple averaging approach can provide a fair estimate of pollution change on a few weeks of unchanged meteorology, but might have more complications to account for an event that lasts over several months, such as the COVID-19 lockdown [25].…”

“…As the straightforward observational data analysis of the inter-period comparison may be skewed by variation of meteorological conditions, it is important to estimate the pollution changes using a business-as-usual scenario modeled using the ML technique [25]. Figure 3 shows observed and modeled trace gas concentrations during the study period, including three 12-day periods of pre-strike (20 September 2019-1 October 2019), during the strike (2 October 2019-13 October 2019) and post-strike (14 October 2019-25 October 2019) averaged over the whole city of Quito (black lines).…”

“…In the case of traffic-borne primary pollutants, however, macroscopic observations before and after events that cause a change in traffic, are useful as differences are directly related to the physical source of pollution. In the case of statistics-based models (e.g., machine learning algorithms), meteorology variables can be included in order to avoid biases and to increase confidence when calculating business-as-usual (BAU) conditions, as previously done in COVID-19 impact studies [23][24][25].…”