Estimating changes in air pollutant levels due to COVID-19 lockdown measures based on a business-as-usual prediction scenario using data mining models: A case-study for urban traffic sites in Spain

Abstract

In response to the COVID-19 pandemic, governments declared severe restrictions throughout 2020, presenting an unprecedented scenario of reduced anthropogenic emissions of air pollutants derived mainly from traffic sources. To analyze the effect of these restrictions derived from COVID-19 pandemic on air quality levels, relative changes in NO, NO 2 , O 3 , PM10 and PM2.5 concentrations were calculated at urban traffic sites in the most populated Spanish cities over different periods with distinct restrictions in 2020. In addition to the changes calculated with respect to the observed air pollutant levels of previous years (2013–2019), relative changes were also calculated using predicted pollutant levels for the different periods over 2020 on a business-as-usual scenario using MLR models with meteorological and seasonal predictors. MLR models were selected among different data mining techniques (MLR RF, KNN), based on their higher performance and accuracy obtained from a leave-one-year-out cross-validation scheme using 2013–2019 data. A q-q mapping post-correction was also applied in all cases in order to improve the reliability of the predictions to reproduce the observed distributions and extreme events. This approach allows us to estimate the relative changes in the studied air pollutants only due to COVID-19 restrictions. The results obtained from this approach show a decreasing pattern for NO x , with the largest reduction in the lockdown period above −50%, whereas the increase observed for O 3 contrasts with the NO x patterns with a maximum increase of 23.9%. The slight reduction in PM10 (−4.1%) and PM2.5 levels (−2.3%) during lockdown indicates a lower relationship with traffic sources. The developed methodology represents a simple but robust framework for exploratory analysis and intervention detection in air quality studies.

Combined effect of changes in NO2, O3, PM2.5, SO2 and CO concentrations on small airway dysfunction

“…The residential address data were annually updated on a 1 km grid for PM 2.5 and a 9 km grid for NO 2 , O 3 , SO 2 and CO. More detailed information on measuring each air pollutant can be obtained through the ‘Guidelines for Using Air Pollution Databases’ section through the following link (URL: https://knhanes.kdca.go.kr/knhanes/sub09/sub09_03.do). Finally, we computed β ‐coefficients from the linear mixed model to estimate the annual changes in air pollutant concentrations across all addresses for each subject over the five‐year period, based on previous studies 21–23 …”

“…Finally, we computed β-coefficients from the linear mixed model to estimate the annual changes in air pollutant concentrations across all addresses for each subject over the five-year period, based on previous studies. [21][22][23]…”

The positive impact of the Omicron pandemic lockdown on air quality and human health in cities around Shanghai

“…This method did not consider the influence of climate factors and social factors (e.g., weekends) on pollutant concentrations, which will bring some deviations to the research results. Some studies predicted pollutant concentrations in the business as usual (BAU) scenario using the multiple linear regression (MLR) and random forest (RF) and compared the predicted results with the observed concentrations during COVID-19 lockdown (Cao et al, 2022 ; González-Pardo et al, 2022 ). However, the predicted results are not very accurate, which may result in inaccurate conclusions.…”

How does COVID-19 lockdown affect air quality: Evidence from Lanzhou, a large city in Northwest China

“…It has not only sickened and killed large populations and posed a serious global public health threat ( Johns Hopkins University, 2022 ), but also had several negative impacts on the socioeconomic system, including psychological pessimism and anxiety ( Traunmüller et al, 2020 ), economic growth slowdown and stagnation ( World Bank, 2022 ; Zhang et al, 2022 ), livelihood level decline and vulnerability increase ( Campbell et al, 2021 ), and even food consumption shrinkag ( Laborde et al, 2021 ). To prevent the indiscriminate spread of this epidemic, many countries (such as China, Italy, France, Spain, and India) have adopted a series of management and control measures to limit human activities, social gatherings, and cross-regional mobility ( González-Pardo et al, 2022 ; Beria and Lunkar, 2021 ; Huang et al, 2020 ; Schlosser et al, 2020 ), including restrictions on road and air traffic, closure of public places, and production shutdown, collectively described as the “lockdown”.…”