Dynamic model to predict the association between air quality, COVID-19 cases, and level of lockdown

Abstract

Studies have reported significant reductions in air pollutant levels due to the COVID-19 outbreak worldwide due to global lockdowns. Nevertheless, all of the reports are limited compared to data from the same period over the past few years, providing mainly an overview of past events, with no future predictions. Lockdown level can be directly related to the number of new COVID-19 cases, air pollution, and economic restriction. As lockdown status varies considerably across the globe, there is a window for mega-cities to determine the optimum lockdown flexibility. To that end, firstly, we employed four different Artificial Neural Networks (ANN) to examine the compatibility to the original levels of CO, O 3 , NO 2 , NO, PM 2.5 , and PM 10 , for São Paulo City, the current Pandemic epicenter in South America. After checking compatibility, we simulated four hypothetical scenarios: 10%, 30%, 70%, and 90% lockdown to predict air pollution levels. To our knowledge, ANN have not been applied to air pollution prediction by lockdown level. Using a limited database, the Multilayer Perceptron neural network has proven to be robust (with Mean Absolute Percentage Error ∼ 30%), with acceptable predictive power to estimate air pollution changes. We illustrate that air pollutant levels can effectively be controlled and predicted when flexible lockdown measures are implemented. The models will be a useful tool for governments to manage the delicate balance among lockdown, number of COVID-19 cases, and air pollution.

The Effect of Lockdown Period during the COVID-19 Pandemic on Air Quality in Sydney Region, Australia

“…Table 1 summarizes the methods, analysis, and data used in this study and in some of other studies from the literature to determine the effect of COVID-19 lockdown on air quality in various parts of the world. Other methods to predict the effect of different lockdown scenarios on air quality have also been used, such as the data-driven artificial neuron network (ANN) used recently by [ 34 ], as applied to the lockdown in Brazil, South America. However, this ANN method is not considered in this study.…”

Machine Learning on the COVID-19 Pandemic, Human Mobility and Air Quality: A Review

“…A 20.4% to 55.5% reduction in NO 2 during full and partial lockdown scenario, respectively, compared to the pre-COVID situation, was also reported in Dhaka, Bangladesh [102]. Thus, it is evidenced that the concentration of NO x has reduced significantly in urban areas due to city-wide and countrywide lockdown measures and closure of transportation and workplaces [103].…”

“…[113] 100 European cities Estimating changes in NOx due to COVID-19 lockdown. [91], [93], [97], [98], [100]- [103], [107], [109], [111], [112] PM 2.5 , PM 10 [91], [93], [93], [96], [96], [97], [99], [102], [103], [107], [109], [111], [112] SO 2 [101], [102], [102], [109], [111] O 3 [91], [93], [97], [98], [101]- [103], [112] Total Oxidant [97] 10 . It is also evident that there is a negative correlation between lockdown levels and air pollutants (i.e., a higher level of lockdown measures reduces the amount of PM in the air to a greater extent).…”

Effects of COVID-19 on the environment: An overview on air, water, wastewater, and solid waste

“…The results obtained from different air pollution monitoring station have been reported for many countries worldwide, which all shows the significant improvement in air quality, as will be discussed in this section. In addition, extensive modeling and simulation efforts have been paid to describe the improvement in air quality in response to the quarantine and lockdown measures associated with the COVID-19 at different restriction levels ( Meng et al, 2020 ; Tadano et al, 2021 ). Meanwhile, a reverse effect of the air quality on the evaluation of the number of COVID-19 cases was observed as well.…”