Estimation of PM2.5concentration over East Asia using GOCI-II aerosol optical properties and machine learning model

Jeewoo Lee; Jhoon Kim; Yeseul Cho; Seoyoung Lee

doi:10.1063/5.0183244

Estimation of PM_2.5concentration over East Asia using GOCI-II aerosol optical properties and machine learning model

Jeewoo Lee, Jhoon Kim, Yeseul Cho, Seoyoung Lee

Department of Atmospheric Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Airborne particulate matter of diameter≤2.5 μm (PM2.5) is associated with detrimental effects on human health. The paucity of in-situ surface PM2.5 observations is a major obstacle to elucidation of the temporal and spatial variability of PM2.5 concentration. We used hourly aerosol optical products from the 2nd Geostationary Ocean Color Imager (GOCI-II) to estimate hourly PM2.5 concentrations over East Asia during January 2021. Additional input variables included meteorological and atmospheric trace gas data. Temporospatially weighted PM2.5 concentrations were used in assessing variations in ground-level PM2.5 levels. An oversampling technique and the Random Forest machine-learning method were applied. Results indicate stable model performance over the region with dynamic fluctuations in PM2.5 concentration, with 10-fold cross-validation results yielding R2 and RMSE values of 0.909 and 8.434 μg m-3, respectively.

Original language	English
Title of host publication	AIP Conference Proceedings
Editors	Alkiviadis F. Bais, Peter Pilewskie, Manfred Wendisch
Publisher	American Institute of Physics Inc.
Edition	1
ISBN (Electronic)	9780735447790
DOIs	https://doi.org/10.1063/5.0183244
Publication status	Published - 2024 Jan 18
Event	International Radiation Symposium 2022 on Radiation Processes in the Atmosphere and Ocean, IRS 2022 - Thessaloniki, Greece Duration: 2022 Jul 4 → 2022 Jul 8

Publication series

Name	AIP Conference Proceedings
Number	1
Volume	2988
ISSN (Print)	0094-243X
ISSN (Electronic)	1551-7616

Conference

Conference	International Radiation Symposium 2022 on Radiation Processes in the Atmosphere and Ocean, IRS 2022
Country/Territory	Greece
City	Thessaloniki
Period	22/7/4 → 22/7/8

Bibliographical note

Publisher Copyright:
© 2024 Author(s).

All Science Journal Classification (ASJC) codes

General Physics and Astronomy

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1063/5.0183244

Cite this

Lee, J., Kim, J., Cho, Y., & Lee, S. (2024). Estimation of PM_2.5concentration over East Asia using GOCI-II aerosol optical properties and machine learning model. In A. F. Bais, P. Pilewskie, & M. Wendisch (Eds.), AIP Conference Proceedings (1 ed.). Article 080006 (AIP Conference Proceedings; Vol. 2988, No. 1). American Institute of Physics Inc.. https://doi.org/10.1063/5.0183244

@inproceedings{116f24cff3b742e09d161881532bc359,

title = "Estimation of PM2.5concentration over East Asia using GOCI-II aerosol optical properties and machine learning model",

abstract = "Airborne particulate matter of diameter≤2.5 μm (PM2.5) is associated with detrimental effects on human health. The paucity of in-situ surface PM2.5 observations is a major obstacle to elucidation of the temporal and spatial variability of PM2.5 concentration. We used hourly aerosol optical products from the 2nd Geostationary Ocean Color Imager (GOCI-II) to estimate hourly PM2.5 concentrations over East Asia during January 2021. Additional input variables included meteorological and atmospheric trace gas data. Temporospatially weighted PM2.5 concentrations were used in assessing variations in ground-level PM2.5 levels. An oversampling technique and the Random Forest machine-learning method were applied. Results indicate stable model performance over the region with dynamic fluctuations in PM2.5 concentration, with 10-fold cross-validation results yielding R2 and RMSE values of 0.909 and 8.434 μg m-3, respectively.",

author = "Jeewoo Lee and Jhoon Kim and Yeseul Cho and Seoyoung Lee",

note = "Publisher Copyright: {\textcopyright} 2024 Author(s).; International Radiation Symposium 2022 on Radiation Processes in the Atmosphere and Ocean, IRS 2022 ; Conference date: 04-07-2022 Through 08-07-2022",

year = "2024",

month = jan,

day = "18",

doi = "10.1063/5.0183244",

language = "English",

series = "AIP Conference Proceedings",

publisher = "American Institute of Physics Inc.",

number = "1",

editor = "Bais, {Alkiviadis F.} and Peter Pilewskie and Manfred Wendisch",

booktitle = "AIP Conference Proceedings",

edition = "1",

}

Lee, J, Kim, J, Cho, Y & Lee, S 2024, Estimation of PM_2.5concentration over East Asia using GOCI-II aerosol optical properties and machine learning model. in AF Bais, P Pilewskie & M Wendisch (eds), AIP Conference Proceedings. 1 edn, 080006, AIP Conference Proceedings, no. 1, vol. 2988, American Institute of Physics Inc., International Radiation Symposium 2022 on Radiation Processes in the Atmosphere and Ocean, IRS 2022, Thessaloniki, Greece, 22/7/4. https://doi.org/10.1063/5.0183244

Estimation of PM_2.5concentration over East Asia using GOCI-II aerosol optical properties and machine learning model. / Lee, Jeewoo; Kim, Jhoon; Cho, Yeseul et al.
AIP Conference Proceedings. ed. / Alkiviadis F. Bais; Peter Pilewskie; Manfred Wendisch. 1. ed. American Institute of Physics Inc., 2024. 080006 (AIP Conference Proceedings; Vol. 2988, No. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Estimation of PM2.5concentration over East Asia using GOCI-II aerosol optical properties and machine learning model

AU - Lee, Jeewoo

AU - Kim, Jhoon

AU - Cho, Yeseul

AU - Lee, Seoyoung

PY - 2024/1/18

Y1 - 2024/1/18

N2 - Airborne particulate matter of diameter≤2.5 μm (PM2.5) is associated with detrimental effects on human health. The paucity of in-situ surface PM2.5 observations is a major obstacle to elucidation of the temporal and spatial variability of PM2.5 concentration. We used hourly aerosol optical products from the 2nd Geostationary Ocean Color Imager (GOCI-II) to estimate hourly PM2.5 concentrations over East Asia during January 2021. Additional input variables included meteorological and atmospheric trace gas data. Temporospatially weighted PM2.5 concentrations were used in assessing variations in ground-level PM2.5 levels. An oversampling technique and the Random Forest machine-learning method were applied. Results indicate stable model performance over the region with dynamic fluctuations in PM2.5 concentration, with 10-fold cross-validation results yielding R2 and RMSE values of 0.909 and 8.434 μg m-3, respectively.

AB - Airborne particulate matter of diameter≤2.5 μm (PM2.5) is associated with detrimental effects on human health. The paucity of in-situ surface PM2.5 observations is a major obstacle to elucidation of the temporal and spatial variability of PM2.5 concentration. We used hourly aerosol optical products from the 2nd Geostationary Ocean Color Imager (GOCI-II) to estimate hourly PM2.5 concentrations over East Asia during January 2021. Additional input variables included meteorological and atmospheric trace gas data. Temporospatially weighted PM2.5 concentrations were used in assessing variations in ground-level PM2.5 levels. An oversampling technique and the Random Forest machine-learning method were applied. Results indicate stable model performance over the region with dynamic fluctuations in PM2.5 concentration, with 10-fold cross-validation results yielding R2 and RMSE values of 0.909 and 8.434 μg m-3, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85184591408&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85184591408&partnerID=8YFLogxK

U2 - 10.1063/5.0183244

DO - 10.1063/5.0183244

M3 - Conference contribution

AN - SCOPUS:85184591408

T3 - AIP Conference Proceedings

BT - AIP Conference Proceedings

A2 - Bais, Alkiviadis F.

A2 - Pilewskie, Peter

A2 - Wendisch, Manfred

PB - American Institute of Physics Inc.

T2 - International Radiation Symposium 2022 on Radiation Processes in the Atmosphere and Ocean, IRS 2022

Y2 - 4 July 2022 through 8 July 2022

ER -