TY - JOUR

T1 - Development of Europe-Wide Models for Particle Elemental Composition Using Supervised Linear Regression and Random Forest

AU - Chen, Jie

AU - De Hoogh, Kees

AU - Gulliver, John

AU - Hoffmann, Barbara

AU - Hertel, Ole

AU - Ketzel, Matthias

AU - Weinmayr, Gudrun

AU - Bauwelinck, Mariska

AU - Van Donkelaar, Aaron

AU - Hvidtfeldt, Ulla A.

AU - Atkinson, Richard

AU - Janssen, Nicole A.H.

AU - Martin, Randall V.

AU - Samoli, Evangelia

AU - Andersen, Zorana J.

AU - Oftedal, Bente M.

AU - Stafoggia, Massimo

AU - Bellander, Tom

AU - Strak, Maciej

AU - Wolf, Kathrin

AU - Vienneau, Danielle

AU - Brunekreef, Bert

AU - Hoek, Gerard

N1 - Publisher Copyright: © 2020 American Chemical Society.

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

U2 - 10.1021/acs.est.0c06595

DO - 10.1021/acs.est.0c06595

M3 - Journal article

C2 - 33237771

AN - SCOPUS:85097473908

VL - 54

SP - 15698

EP - 15709

JO - Environmental Science &amp; Technology

JF - Environmental Science &amp; Technology

SN - 0013-936X

IS - 24

ER -