Search

This study aims to analyze the correlation between environmental factors and confirmed cases of COVID-19 pandemic in Victoria, Mexico. The analysis is performed at the micro-level, filtering only confirmed cases of COVID-19 that are located near air quality monitoring stations, within an approximate coverage of 2.5 km, in order to identify a possible specific association between PM 2.5 , PM 10 , carbon monoxide (CO), relative humidity, temperature, absolute humidity, and total confirmed cases of COVID-19. The results evidenced that the cases of COVID-19 were very strongly associated with CO concentration. Our results also suggested that particulate matter pollution (PM 2.5 and PM 10 ) exposure have a significant correlation for confirmed cases of COVID-19. Furthermore, we studied the changes in air quality during the COVID-19 outbreak by comparing the average concentration of the four weeks before lockdown (February 16 to March 14, 2020) and the following twelve weeks during the partial lockdown (March 15 to June 06, 2020), revealing a very significant decrease of pollutants., (Copyright © 2020 Elsevier Inc. All rights reserved.)

Air pollution is an issue of great concern globally due to the risks to the health of humanity, animals, and ecosystems. On the one hand, air quality monitoring systems allow for determining the concentration level of air pollutants and health risks through an air quality index (AQI). On the other hand, accurate future predictions of air pollutant concentration levels can provide valuable information for data-driven decision-making to reduce health risks from short- and long-term exposure when indicators exceed permissible limits. In this paper, five deep learning architectures are evaluated to predict the concentration of particulate matter pollutants (in their fractions PM2.5 and PM10) and carbon monoxide (CO) in consecutive hours. The proposed prediction models are based on recurrent neural networks (RNNs), long short-term memory (LSTM), vanilla LSTM, Stacked LSTM, Bi-LSTM, and encoder–decoder LSTM networks. Moreover, a methodology is presented to guide the construction of the prediction model, encompassing raw data processing, model design and optimization, and neural network training, testing, and evaluation. The results underscore the precision and reliability of the Stacked LSTM model in predicting the hourly concentration level for PM2.5, with an RMSE of 3.4538 μg/m3. Similarly, the encoder–decoder LSTM model accurately predicts the concentration level for PM10 and CO, with an RMSE of 3.2606 μg/m3 and 2.1510 ppm, respectively. These evaluations, with their minimal differences in error metrics and coefficient of determination, validate the effectiveness and superiority of the deep learning models over other reference models, instilling confidence in their potential. [ABSTRACT FROM AUTHOR]

The lockdown measures implemented due to the SARS-CoV-2 pandemic to reduce the epidemic curve, in most cases, have had a positive impact on air quality indices. Our study describes the changes in the concentration levels of PM 2.5 and PM 10 during the lockdown and post-lockdown in Victoria, Mexico, considering the following periods: before the lockdown (BL) from 16 February to 14 March, during the lockdown (DL) from 15 March to 2 May, and in the partial lockdown (PL) from 3 May to 6 June. When comparing the DL period of 2019 and 2020, we document a reduction in the average concentration of PM 2.5 and PM 10 of −55.56% and −55.17%, respectively. Moreover, we note a decrease of −53.57% for PM 2.5 and −51.61% for PM 10 in the PL period. When contrasting the average concentration between the DL periods of 2020 and 2021, an increase of 91.67% for PM 2.5 and 100.00% for PM 10 was identified. Furthermore, in the PL periods of 2020 and 2021, an increase of 38.46% and 31.33% was observed for PM 2.5 and PM 10 , respectively. On the other hand, when comparing the concentrations of PM 2.5 in the three periods of 2020, we found a decrease between BL and DL of −50.00%, between BL and PL a decrease of −45.83%, and an increase of 8.33% between DL and PL. In the case of PM 10 , a decrease of −48.00% between BL and DL, −40.00% between BL and PL, and an increase of 15.38% between the DL and PL periods were observed. In addition, we performed a non-parametric statistical analysis, where a significant statistical difference was found between the DL-2020 and DL-2019 pairs ( x 2 = 1.204) and between the DL-2021 and DL-2019 pairs ( x 2 = 0.372), with a p < 0.000 for PM 2.5 , and the contrast between pairs of PM 10 (DL) showed a significant difference between all pairs with p < 0.01 . [ABSTRACT FROM AUTHOR]