Data Entry: Please note that the research database will be replaced by UNIverse by the end of October 2023. Please enter your data into the system https://universe-intern.unibas.ch. Thanks
Development of Europe-wide models for particle elemental composition using supervised linear regression and random forest
JournalArticle (Originalarbeit in einer wissenschaftlichen Zeitschrift)
ID
4652475
Author(s)
Chen, J.; de Hoogh, K.; Gulliver, J.; Hoffmann, B.; Hertel, O.; Ketzel, M.; Weinmayr, G.; Bauwelinck, M.; van Donkelaar, A.; Hvidtfeldt, U. A.; Atkinson, R.; Janssen, N. A. H.; Martin, R. V.; Samoli, E.; Andersen, Z. J.; Oftedal, B. M.; Stafoggia, M.; Bellander, T.; Strak, M.; Wolf, K.; Vienneau, D.; Brunekreef, B.; Hoek, G.
Development of Europe-wide models for particle elemental composition using supervised linear regression and random forest
Journal
Environmental science & technology
Volume
54
Number
24
Pages / Article-Number
15698-15709
Mesh terms
Air Pollutants, analysis; Air Pollution, analysis; Environmental Monitoring; Europe; Linear Models; Particulate Matter, analysis; Zinc, analysis
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 mum (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.