20 Oct 2021

20 Oct 2021

Review status: this preprint is currently under review for the journal AMT.

Continuous mapping of fine particulate matter (PM2.5) air quality in East Asia at daily 6×6 km2 resolution by application of a random forest algorithm to 2011–2019 GOCI geostationary satellite data

Drew C. Pendergrass1, Daniel J. Jacob1, Shixian Zhai1, Jhoon Kim2,3, Ja-Ho Koo2, Seoyoung Lee2, Minah Bae4, and Soontae Kim4 Drew C. Pendergrass et al.
  • 1School of Engineering and Applied Sciences, Harvard University, Cambridge, Mass., USA
  • 2Department of Atmospheric Sciences, Yonsei University, Seoul, South Korea
  • 3Particulate Matter Research Institute, Samsung Advanced Institute of Technology (SAIT), Suwon, South Korea
  • 4Department of Environmental and Safety Engineering, Ajou University, Suwon., South Korea

Abstract. We use 2011–2019 aerosol optical depth (AOD) observations from the Geostationary Ocean Color Imager (GOCI) instrument over East Asia to infer 24-h daily surface fine particulate matter (PM2.5) concentrations at continuous 6x6 km2 resolution over eastern China, South Korea, and Japan. This is done with a random forest (RF) algorithm applied to the gap-filled GOCI AODs and other data and trained with PM2.5 observations from the three national networks. The predicted 24-h PM2.5 concentrations for sites entirely withheld from training in a ten-fold crossvalidation procedure correlate highly with network observations (R2 = 0.89) with single-value precision of 26–32 % depending on country. Prediction of annual mean values has R2 = 0.96 and single-value precision of 12 %. The RF algorithm is only moderately successful for diagnosing local exceedances of the National Ambient Air Quality Standard (NAAQS) because these exceedances are typically within the single-value precisions of the RF, and also because of RF smoothing of extreme PM2.5 concentrations. The area-weighted and population-weighted trends of RF PM2.5 concentrations for eastern China, South Korea, and Japan show steady 2015–2019 declines consistent with surface networks, but the surface networks in eastern China and South Korea underestimate population exposure. Further examination of RF PM2.5 fields for South Korea identifies hotspots where surface network sites were initially lacking and shows 2015–2019 PM2.5 decreases across the country except for flat concentrations in the Seoul metropolitan area. Inspection of monthly PM2.5 time series in Beijing, Seoul, and Tokyo shows that the RF algorithm successfully captures observed seasonal variations of PM2.5 even though AOD and PM2.5 often have opposite seasonalities. Application of the RF algorithm to urban pollution episodes in Seoul and Beijing demonstrates high skill in reproducing the observed day-to-day variations in air quality as well as spatial patterns on the 6 km scale. Comparison to a CMAQ simulation for the Korean peninsula demonstrates the value of the continuous RF PM2.5 fields for testing air quality models, including over North Korea where they offer a unique resource.

Drew C. Pendergrass et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2021-273', Anonymous Referee #1, 03 Dec 2021
  • RC2: 'Comment on amt-2021-273', Anonymous Referee #2, 04 Dec 2021

Drew C. Pendergrass et al.

Drew C. Pendergrass et al.


Total article views: 457 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
345 101 11 457 3 11
  • HTML: 345
  • PDF: 101
  • XML: 11
  • Total: 457
  • BibTeX: 3
  • EndNote: 11
Views and downloads (calculated since 20 Oct 2021)
Cumulative views and downloads (calculated since 20 Oct 2021)

Viewed (geographical distribution)

Total article views: 427 (including HTML, PDF, and XML) Thereof 427 with geography defined and 0 with unknown origin.
Country # Views %
  • 1


Latest update: 08 Dec 2021
Short summary
This paper uses a machine learning algorithm to infer high resolution maps of particulate air quality in eastern China, Japan, and the Korean peninsula using data from a geostationary satellite, along with meteorology. We then perform extensive evaluation of this inferred air quality and use it to diagnose trends in the region. We hope this paper and the associated data will be valuable to other scientists interested in epidemiology, air quality, remote sensing, and machine learning.