English
 
Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Gaussian Markov random fields improve ensemble predictions of daily 1 km PM2.5 and PM10 across France

Hough, I., Sarafian, R., Shtein, A., Zhou, B., Lepeule, J., Kloog, I. (2021): Gaussian Markov random fields improve ensemble predictions of daily 1 km PM2.5 and PM10 across France. - Atmospheric Environment, 264, 118693.
https://doi.org/10.1016/j.atmosenv.2021.118693

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Hough, Ian1, Author
Sarafian, Ron1, Author
Shtein, Alexandra1, Author
Zhou, Bin2, Author              
Lepeule, Johanna1, Author
Kloog, Itai1, Author
Affiliations:
1External Organizations, ou_persistent22              
2Potsdam Institute for Climate Impact Research, ou_persistent13              

Content

show
hide
Free keywords: -
 Abstract: Understanding the health impacts of particulate matter (PM) requires spatiotemporally continuous exposure estimates. We developed a multi-stage ensemble model that estimates daily mean PM2.5 and PM10 at 1 km spatial resolution across France from 2000 to 2019. First, we alleviated the sparsity of PM2.5 monitors by imputing PM2.5 at more common PM10 monitors. We also imputed missing satellite aerosol optical depth (AOD) based on modelled AOD from atmospheric reanalyses. Next, we trained three base learners (mixed models, Gaussian Markov random fields, and random forests) to predict daily PM concentrations based on AOD, meteorology, and other variables. Finally, we generated ensemble predictions using a generalized additive model with spatiotemporally varying weights that exploit the strengths and weaknesses of each base learner. The Gaussian Markov random field dominated the ensemble, outperforming mixed models and random forests at most locations on most days. Rigorous cross-validation showed that the ensemble predictions were quite accurate, with mean absolute error (MAE) of 2.72 μg/m3 and R2 of 0.76 for PM2.5; PM10 MAE was 4.26 μg/m3 and R2 0.71. Our predictions are available to improve epidemiological studies of acute and chronic PM exposure in urban and rural France.

Details

show
hide
Language(s):
 Dates: 2021-11
 Publication Status: Finally published
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1016/j.atmosenv.2021.118693
PIKDOMAIN: RD2 - Climate Resilience
Organisational keyword: RD2 - Climate Resilience
Research topic keyword: Health
Research topic keyword: Atmosphere
Regional keyword: Europe
Model / method: Machine Learning
MDB-ID: No data to archive
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Atmospheric Environment
Source Genre: Journal, SCI, Scopus, p3
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 264 Sequence Number: 118693 Start / End Page: - Identifier: CoNE: https://publications.pik-potsdam.de/cone/journals/resource/141022
Publisher: Elsevier