File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Estimation of hourly full-coverage PM2.5 concentrations at 1-km resolution in China using a two-stage random forest model

TitleEstimation of hourly full-coverage PM<inf>2.5</inf> concentrations at 1-km resolution in China using a two-stage random forest model
Authors
KeywordsAOD
Random forest
Fine spatiotemporal resolution
PM 2.5
China
Issue Date2021
Citation
Atmospheric Research, 2021, v. 248, article no. 105146 How to Cite?
AbstractFine particulate matter such as PM has been the focus of increasing public concerns because of its adverse effect on environment and health risks. However, existing efforts of mapping PM concentrations are always limited by coarse spatial resolutions and temporal frequencies. Addressing this shortcoming, here we explicitly estimated hourly PM concentrations at 1-km spatial resolution in China from March 2018 to February 2019 using a two-stage random forest model. In the first stage, we used a gap-filling method to generate full-coverage Aerosol Optical Depth (AOD) by fusing AOD data from satellite (Himawari-8 and MODIS) and weather forecast model (CAMS), and additional meteorological and geographical variables. Gap-filled AOD was subsequently used to estimate hourly PM in the Stage II. Results showed that our model achieved accurate and robust estimations of PM concentrations, with an overall cross-validated R of 0.85, root mean squared error of 11.02 μg/m , and mean absolute error of 6.73 μg/m . CAMS-simulated PM , elevation, and gap-filled AOD were identified to be important variables contributing to the model performance of PM estimation. The model performance varied over the daily temporal scale. Specifically, daily estimation model performed better in spring and winter but worse in summer and autumn. We provide an alternative to generate spatially and temporally explicit mapping of PM concentrations with fine resolutions, making it possible to achieve real-time monitoring of air pollutions. The detailed spatial heterogeneity and diurnal variability of PM concentrations will also be valuable for environmental exposure assessments. 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2 3 3
Persistent Identifierhttp://hdl.handle.net/10722/299465
ISSN
2023 Impact Factor: 4.5
2023 SCImago Journal Rankings: 1.427
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorJiang, Tingting-
dc.contributor.authorChen, Bin-
dc.contributor.authorNie, Zhen-
dc.contributor.authorRen, Zhehao-
dc.contributor.authorXu, Bing-
dc.contributor.authorTang, Shihao-
dc.date.accessioned2021-05-21T03:34:28Z-
dc.date.available2021-05-21T03:34:28Z-
dc.date.issued2021-
dc.identifier.citationAtmospheric Research, 2021, v. 248, article no. 105146-
dc.identifier.issn0169-8095-
dc.identifier.urihttp://hdl.handle.net/10722/299465-
dc.description.abstractFine particulate matter such as PM has been the focus of increasing public concerns because of its adverse effect on environment and health risks. However, existing efforts of mapping PM concentrations are always limited by coarse spatial resolutions and temporal frequencies. Addressing this shortcoming, here we explicitly estimated hourly PM concentrations at 1-km spatial resolution in China from March 2018 to February 2019 using a two-stage random forest model. In the first stage, we used a gap-filling method to generate full-coverage Aerosol Optical Depth (AOD) by fusing AOD data from satellite (Himawari-8 and MODIS) and weather forecast model (CAMS), and additional meteorological and geographical variables. Gap-filled AOD was subsequently used to estimate hourly PM in the Stage II. Results showed that our model achieved accurate and robust estimations of PM concentrations, with an overall cross-validated R of 0.85, root mean squared error of 11.02 μg/m , and mean absolute error of 6.73 μg/m . CAMS-simulated PM , elevation, and gap-filled AOD were identified to be important variables contributing to the model performance of PM estimation. The model performance varied over the daily temporal scale. Specifically, daily estimation model performed better in spring and winter but worse in summer and autumn. We provide an alternative to generate spatially and temporally explicit mapping of PM concentrations with fine resolutions, making it possible to achieve real-time monitoring of air pollutions. The detailed spatial heterogeneity and diurnal variability of PM concentrations will also be valuable for environmental exposure assessments. 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2 3 3-
dc.languageeng-
dc.relation.ispartofAtmospheric Research-
dc.subjectAOD-
dc.subjectRandom forest-
dc.subjectFine spatiotemporal resolution-
dc.subjectPM 2.5-
dc.subjectChina-
dc.titleEstimation of hourly full-coverage PM<inf>2.5</inf> concentrations at 1-km resolution in China using a two-stage random forest model-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.atmosres.2020.105146-
dc.identifier.scopuseid_2-s2.0-85088951285-
dc.identifier.volume248-
dc.identifier.spagearticle no. 105146-
dc.identifier.epagearticle no. 105146-
dc.identifier.isiWOS:000594098300002-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats