Impact of Regional Mobility on Air Quality during COVID-19 Lockdown in Mississippi, USA Using Machine Learning DOI Open Access

Francis Tuluri,

Reddy Remata,

Wilbur L. Walters

et al.

International Journal of Environmental Research and Public Health, Journal Year: 2023, Volume and Issue: 20(11), P. 6022 - 6022

Published: May 31, 2023

Social distancing measures and shelter-in-place orders to limit mobility transportation were among the strategic taken control rapid spreading of COVID-19. In major metropolitan areas, there was an estimated decrease 50 90 percent in transit use. The secondary effect COVID-19 lockdown expected improve air quality, leading a respiratory diseases. present study examines impact on quality during state Mississippi (MS), USA. region is selected because its non-metropolitan non-industrial settings. Concentrations pollutants—particulate matter 2.5 (PM2.5), particulate 10 (PM10), ozone (O3), nitrogen oxide (NO2), sulfur dioxide (SO2), carbon monoxide (CO)—were collected from Environmental Protection Agency, USA 2011 2020. Because limitations data availability, Jackson, MS assumed be representative entire state. Weather (temperature, humidity, pressure, precipitation, wind speed, direction) National Oceanic Atmospheric Administration, Traffic-related (transit) Google for year statistical machine learning tools R Studio used changes if any, period. Weather-normalized modeling simulating business-as-scenario (BAU) predicted significant difference means observed values NO2, O3, CO (p < 0.05). Due lockdown, mean concentrations decreased NO2 by −4.1 ppb −0.088 ppm, respectively, while it increased O3 0.002 ppm. results agree with −50.5% as percentage change baseline, prevalence rate asthma lockdown. This demonstrates validity use simple, easy, versatile analytical assist policymakers estimating situations pandemic or natural hazards, take mitigating deterioration detected.

Language: Английский

Wind power forecasting based on a machine learning model: considering a coastal wind farm in Zhejiang as an example DOI Creative Commons

Guangcheng Gu,

Ningbo Li,

Yaying Pan

et al.

International Journal of Green Energy, Journal Year: 2024, Volume and Issue: 21(11), P. 2551 - 2558

Published: Feb. 26, 2024

The unpredictability and instability of wind have hindered the development utilization power. To harness energy ensure a secure stable power grid after integration, precise predictions generation are imperative. Here, we apply one-year data from coastal farm in Zhejiang to train Random Forest (RF) model for predicting generation. results indicate that RF (mean bias (MB) 1.33) outperforms traditional linear models (MB 87.70). An evaluation prediction-measurement shows strong agreement between model's actual measurements 1.33), especially when speeds exceed 5.7 m/s. While Weather Research Forecasting (WRF) yields less accurate (R2 0.65) compared using measured velocity 0.97) prediction, it remains acceptable as can capture forecast peak generating power, meeting daily management requirements. Therefore, our machine learning-based approach offers practical guidance reducing uncertainties. Enhancing forecasting through WRF could further improve accuracy Our study also verified future application areas China.

Language: Английский

Citations

7
Evaluation of the Impact of COVID-19 Restrictions on Air Pollution in Russia’s Largest Cities DOI Creative Commons
A.E. Morozova, Oleg Sizov,

Pavel Elagin

et al.

Atmosphere, Journal Year: 2023, Volume and Issue: 14(6), P. 975 - 975

Published: June 2, 2023

Governments around the world took unprecedented measures, such as social distancing and minimization of public/industrial activity, in response to COVID-19 pandemic 2020. This provided a unique chance assess relationships between key air pollutant emissions track reductions these various countries during lockdown. study considers atmospheric pollution 78 largest Russian cities (with populations over 250,000) March–June 2019–2021. is first for Russia. The initial data were TROPOMI measurements (Sentinel-5P satellite) pollutants carbon monoxide (CO), formaldehyde (HCHO), nitrogen dioxide (NO2), sulfur (SO2), which are main anthropogenic pollutants. downloaded from Google Earth Engine’s cloud-based geospatial platform. L3-level information subsequent analysis. indicated decrease content lockdown compared pre-pandemic post-pandemic periods. reduced economic activity due had greatest impact on NO2 concentrations. average reduction was −30.7%, while maximum found within Moscow city limits that existed before 01.07.2012 (−41% with respect 2019 level). For dioxide, only 7%, further drop 2021 (almost 20% relative 2019). monoxide, there no 2020 period (99.4% 100.9%, respectively, identified impacts NO2, SO2, HCHO, CO concentrations major generally followed patterns observed other industrialized China, India, Turkey, European countries. local concentration cities. differences leveled off time, baseline level each restored.

Language: Английский

Citations

4
An exploration of urban air health navigation system based on dynamic exposure risk forecast of ambient PM2.5 DOI Creative Commons

Pei Jiang,

C. Y. Gao,

Junrui Zhao

et al.

Environment International, Journal Year: 2024, Volume and Issue: 190, P. 108793 - 108793

Published: June 3, 2024

Under international advocacy for a low-carbon and healthy lifestyle, ambient PM2.5 pollution poses dilemma urban residents who wish to engage in outdoor exercise adopt active commuting. In this study, an Urban Air Health Navigation System (UAHNS) was designed proposed assist users by recommending routes with the least exposure dynamically issuing early risk warnings based on topologized digital maps, application programming interface (API), eXtreme Gradient Boosting (XGBoost) model, two-step spatial interpolation. A test of UAHNS's functions applications carried out Wuhan city. The results showed that, compared trained random forest (RF), LightGBM, Adaboost models, etc., XGBoost model performed better, R

Language: Английский

Citations

1
Quantifying the impact of lockdown measures on air pollution levels: A comparative study of Bhopal and Adelaide DOI
Anjali Agrawal, Sujeet Kesharvani, Gaurav Dwivedi

et al.

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 909, P. 168595 - 168595

Published: Nov. 14, 2023

Language: Английский

Citations

1
A Novel Approach to Assessing Light Extinction with Decade-Long Observations of Chemical and Optical Properties in Seoul, South Korea DOI Creative Commons
Seung-Myung Park, Jong Sung Park,

In-Ho Song

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(3), P. 320 - 320

Published: March 4, 2024

We performed continuous long-term measurements of PM2.5 mass, comprehensive chemical composition, and optical properties, including scattering absorption coefficients, from March 2011 to December 2020 at the Metropolitan Air Quality Research Center in Seoul, South Korea. peaked 38 μg/m3 2013 has been declining steadily since then, reaching 22 2020. The extinction coefficients also decreased with decline PM2.5, but correlation between two factors was not as pronounced. This deviation mainly attributed rapid changes composition over same period. mass contribution sulphate 33.9 24.1%, fraction nitrate organic carbon increased 23.4 20.0 34.1 32.2%, respectively, indicating that replaced by past decade. To assess effect changing aerosol compositions on light extinction, we compared measured those estimated via various existing approaches, revised IMPROVE algorithm. found simplified linear regression model provided best fit our data, a slope 1.03 R2 0.87, all non-linear methods, such algorithms, overestimated observed 23 48%. suggests simple scheme may be more appropriate for reflecting varying conditions long periods time, especially urban air. However, where does change much, methods are likely reproducing extinction.

Language: Английский

Citations

0
Impact of Regional Mobility on Air Quality during COVID-19 Lockdown in Mississippi, USA Using Machine Learning DOI Open Access

Francis Tuluri,

Reddy Remata,

Wilbur L. Walters

et al.

International Journal of Environmental Research and Public Health, Journal Year: 2023, Volume and Issue: 20(11), P. 6022 - 6022

Published: May 31, 2023

Social distancing measures and shelter-in-place orders to limit mobility transportation were among the strategic taken control rapid spreading of COVID-19. In major metropolitan areas, there was an estimated decrease 50 90 percent in transit use. The secondary effect COVID-19 lockdown expected improve air quality, leading a respiratory diseases. present study examines impact on quality during state Mississippi (MS), USA. region is selected because its non-metropolitan non-industrial settings. Concentrations pollutants—particulate matter 2.5 (PM2.5), particulate 10 (PM10), ozone (O3), nitrogen oxide (NO2), sulfur dioxide (SO2), carbon monoxide (CO)—were collected from Environmental Protection Agency, USA 2011 2020. Because limitations data availability, Jackson, MS assumed be representative entire state. Weather (temperature, humidity, pressure, precipitation, wind speed, direction) National Oceanic Atmospheric Administration, Traffic-related (transit) Google for year statistical machine learning tools R Studio used changes if any, period. Weather-normalized modeling simulating business-as-scenario (BAU) predicted significant difference means observed values NO2, O3, CO (p < 0.05). Due lockdown, mean concentrations decreased NO2 by −4.1 ppb −0.088 ppm, respectively, while it increased O3 0.002 ppm. results agree with −50.5% as percentage change baseline, prevalence rate asthma lockdown. This demonstrates validity use simple, easy, versatile analytical assist policymakers estimating situations pandemic or natural hazards, take mitigating deterioration detected.

Language: Английский

Citations

0