Development of Europe-Wide Models for Particle Elemental Composition Using Supervised Linear Regression and Random Forest

Jie Chen*, Kees De Hoogh, John Gulliver, Barbara Hoffmann, Ole Hertel, Matthias Ketzel, Gudrun Weinmayr, Mariska Bauwelinck, Aaron Van Donkelaar, Ulla A. Hvidtfeldt, Richard Atkinson, Nicole A.H. Janssen, Randall V. Martin, Evangelia Samoli, Zorana J. Andersen, Bente M. Oftedal, Massimo Stafoggia, Tom Bellander, Maciej Strak, Kathrin WolfDanielle Vienneau, Bert Brunekreef, Gerard Hoek

*Corresponding author for this work

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

2 Citations (Scopus)
126 Downloads (Pure)

Abstract

We developed Europe-wide models of long-term exposure to eight elements (copper, iron, potassium, nickel, sulfur, silicon, vanadium, and zinc) in particulate matter with diameter <2.5 μm (PM2.5) using standardized measurements for one-year periods between October 2008 and April 2011 in 19 study areas across Europe, with supervised linear regression (SLR) and random forest (RF) algorithms. Potential predictor variables were obtained from satellites, chemical transport models, land-use, traffic, and industrial point source databases to represent different sources. Overall model performance across Europe was moderate to good for all elements with hold-out-validation R-squared ranging from 0.41 to 0.90. RF consistently outperformed SLR. Models explained within-area variation much less than the overall variation, with similar performance for RF and SLR. Maps proved a useful additional model evaluation tool. Models differed substantially between elements regarding major predictor variables, broadly reflecting known sources. Agreement between the two algorithm predictions was generally high at the overall European level and varied substantially at the national level. Applying the two models in epidemiological studies could lead to different associations with health. If both between- and within-area exposure variability are exploited, RF may be preferred. If only within-area variability is used, both methods should be interpreted equally.

Original languageEnglish
JournalEnvironmental Science and Technology
Volume54
Issue24
Pages (from-to)15698-15709
Number of pages12
ISSN0013-936X
DOIs
Publication statusPublished - 15 Dec 2020

Fingerprint

Dive into the research topics of 'Development of Europe-Wide Models for Particle Elemental Composition Using Supervised Linear Regression and Random Forest'. Together they form a unique fingerprint.

Cite this