Preprints
https://doi.org/10.5194/acp-2021-751
https://doi.org/10.5194/acp-2021-751

  29 Oct 2021

29 Oct 2021

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

Technical note: Investigating sub-city gradients of air quality: lessons learned with low-cost PM2.5 and AOD monitors and machine learning

Michael Cheeseman1, Bonne Ford1, Zoey Rosen2, Eric Wendt3, Alex DesRosiers1, Aaron J. Hill1, Christian L'Orange3, Casey Quinn3, Marilee Long2, Shantanu H. Jathar3, John Volckens3, and Jeffrey R. Pierce1 Michael Cheeseman et al.
  • 1Department of Atmospheric Science, Colorado State University, Fort Collins, 80521, USA
  • 2Department of Journalism & Media Communication, Colorado State University, Fort Collins, 80521, USA
  • 3Department of Mechanical Engineering, Colorado State University, Fort Collins, 80521, USA

Abstract. Accurate sub-city fine particulate matter (PM2.5) estimates could improve epidemiological and health-impact studies in cities with heterogeneous distributions of PM2.5, yet most cities globally lack the monitoring density necessary for sub-city-scale estimates. To estimate spatiotemporal variability in PM2.5, we use machine learning (Random Forests; RFs) and concurrent PM2.5 and AOD measurements from the Citizen Enabled Aerosol Measurements for Satellites (CEAMS) low-cost sensor network as well as PM2.5 measurements from the Environmental Protection Agency’s (EPA) reference monitors during wintertime in Denver, CO, USA. The RFs predicted PM2.5 in a 5-fold cross validation (CV) with relatively high skill (95% confidence interval R2=0.74–0.84 for CEAMS; R2=0.68–0.75 for EPA) though the models were aided by the spatiotemporal autocorrelation of the PM2.5 measurements. We found that the most important predictors of PM2.5 were factors associated with pooling of pollution in wintertime, such as low planetary boundary layer heights (PBLH), stagnant wind conditions, and, to a lesser degree, elevation. In general, spatial predictors were less important than spatiotemporal predictors because temporal variability exceeded spatial variability in our dataset. Finally, although concurrent AOD was an important predictor in our RF model for hourly PM2.5, it did not improve model performance with high statistical significance. Regardless, we found that low-cost PM2.5 measurements incorporated into an RF model were useful in interpreting meteorological and geographic drivers of PM2.5 over wintertime Denver. We also explored how the RF model performance and interpretation changes based on different model configurations and data processing.

Michael Cheeseman et al.

Status: open (until 29 Dec 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Michael Cheeseman et al.

Michael Cheeseman et al.

Viewed

Total article views: 470 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
341 122 7 470 20 5 8
  • HTML: 341
  • PDF: 122
  • XML: 7
  • Total: 470
  • Supplement: 20
  • BibTeX: 5
  • EndNote: 8
Views and downloads (calculated since 29 Oct 2021)
Cumulative views and downloads (calculated since 29 Oct 2021)

Viewed (geographical distribution)

Total article views: 492 (including HTML, PDF, and XML) Thereof 492 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 01 Dec 2021
Download
Short summary
This article predicts concentrations of airborne particulate matter over wintertime Denver, CO, USA, using meteorological and geographic information, as well as low-cost aerosol optical depth (AOD) measurements captured by citizen scientists. Machine learning methods revealed that low boundary layer heights and stagnant air were the best predictors of poor air quality, while AOD provided little skill in predicting particulate matter for this location and time period.
Altmetrics