TY - JOUR
T1 - Performance of Multi-City Land Use Regression Models for Nitrogen Dioxide and Fine Particles
AU - Wang, Meng
AU - Beelen, Rob
AU - Bellander, Tom
AU - Birk, Matthias
AU - Cesaroni, Giulia
AU - Cirach, Marta
AU - Cyrys, Josef
AU - de Hoogh, Kees
AU - Declercq, Christophe
AU - Dimakopoulou, Konstantina
AU - Eeftens, Marloes
AU - Eriksen, Kirsten T.
AU - Forastiere, Francesco
AU - Galassi, Claudia
AU - Grivas, Georgios
AU - Heinrich, Joachim
AU - Hoffmann, Barbara
AU - Ineichen, Alex
AU - Korek, Michal
AU - Lanki, Timo
AU - Lindley, Sarah
AU - Modig, Lars
AU - Mölter, Anna
AU - Nafstad, Per
AU - Nieuwenhuijsen, Mark J.
AU - Nystad, Wenche
AU - Olsson, David
AU - Raaschou-Nielsen, Ole
AU - Ragettli, Martina
AU - Ranzi, Andrea
AU - Stempfelet, Morgane
AU - Sugiri, Dorothea
AU - Tsai, Ming Yi
AU - Udvardy, Orsolya
AU - Varró, Mihaly J.
AU - Vienneau, Danielle
AU - Weinmayr, Gudrun
AU - Wolf, Kathrin
AU - Yli-Tuomi, Tarja
AU - Hoek, Gerard
AU - Brunekreef, Bert
N1 - 1552-9924 Wang, Meng Beelen, Rob Bellander, Tom Birk, Matthias Cesaroni, Giulia Cirach, Marta Cyrys, Josef de Hoogh, Kees Declercq, Christophe Dimakopoulou, Konstantina Eeftens, Marloes Eriksen, Kirsten T Forastiere, Francesco Galassi, Claudia Grivas, Georgios Heinrich, Joachim Hoffmann, Barbara Ineichen, Alex Korek, Michal Lanki, Timo Lindley, Sarah Modig, Lars Molter, Anna Nafstad, Per Nieuwenhuijsen, Mark J Nystad, Wenche Olsson, David Raaschou-Nielsen, Ole Ragettli, Martina Ranzi, Andrea Stempfelet, Morgane Sugiri, Dorothea Tsai, Ming-Yi Udvardy, Orsolya Varro, Mihaly J Vienneau, Danielle Weinmayr, Gudrun Wolf, Kathrin Yli-Tuomi, Tarja Hoek, Gerard Brunekreef, Bert G0801056/Medical Research Council/United Kingdom Journal Article Research Support, Non-U.S. Gov't United States Environ Health Perspect. 2014 Aug;122(8):843-9. doi: 10.1289/ehp.1307271. Epub 2014 May 2.
PY - 2014
Y1 - 2014
N2 - Background: Land use regression (LUR) models have been developed mostly to explain intraurban variations in air pollution based on often small local monitoring campaigns. Transferability of LUR models from city to city has been investigated, but little is known about the performance of models based on large numbers of monitoring sites covering a large area. Objectives: We aimed to develop European and regional LUR models and to examine their transferability to areas not used for model development. Methods: We evaluated LUR models for nitrogen dioxide (NO2) and particulate matter (PM; PM2.5, PM2.5 absorbance) by combining standardized measurement data from 17 (PM) and 23 (NO2) ESCAPE (European Study of Cohorts for Air Pollution Effects) study areas across 14 European countries for PM and NO2. Models were evaluated with cross-validation (CV) and hold-out validation (HV). We investigated the transferability of the models by successively excluding each study area from model building. Results: The European model explained 56% of the concentration variability across all sites for NO2, 86% for PM2.5, and 70% for PM2.5 absorbance. The HV R2s were only slightly lower than the model R2 (NO2, 54%; PM2.5, 80%; PM2.5 absorbance, 70%). The European NO2, PM2.5, and PM2.5 absorbance models explained a median of 59%, 48%, and 70% of within-area variability in individual areas. The transferred models predicted a modest-to-large fraction of variability in areas that were excluded from model building (median R2: NO2, 59%; PM2.5, 42%; PM2.5 absorbance, 67%). Conclusions: Using a large data set from 23 European study areas, we were able to develop LUR models for NO2 and PM metrics that predicted measurements made at independent sites and areas reasonably well. This finding is useful for assessing exposure in health studies conducted in areas where no measurements were conducted.
AB - Background: Land use regression (LUR) models have been developed mostly to explain intraurban variations in air pollution based on often small local monitoring campaigns. Transferability of LUR models from city to city has been investigated, but little is known about the performance of models based on large numbers of monitoring sites covering a large area. Objectives: We aimed to develop European and regional LUR models and to examine their transferability to areas not used for model development. Methods: We evaluated LUR models for nitrogen dioxide (NO2) and particulate matter (PM; PM2.5, PM2.5 absorbance) by combining standardized measurement data from 17 (PM) and 23 (NO2) ESCAPE (European Study of Cohorts for Air Pollution Effects) study areas across 14 European countries for PM and NO2. Models were evaluated with cross-validation (CV) and hold-out validation (HV). We investigated the transferability of the models by successively excluding each study area from model building. Results: The European model explained 56% of the concentration variability across all sites for NO2, 86% for PM2.5, and 70% for PM2.5 absorbance. The HV R2s were only slightly lower than the model R2 (NO2, 54%; PM2.5, 80%; PM2.5 absorbance, 70%). The European NO2, PM2.5, and PM2.5 absorbance models explained a median of 59%, 48%, and 70% of within-area variability in individual areas. The transferred models predicted a modest-to-large fraction of variability in areas that were excluded from model building (median R2: NO2, 59%; PM2.5, 42%; PM2.5 absorbance, 67%). Conclusions: Using a large data set from 23 European study areas, we were able to develop LUR models for NO2 and PM metrics that predicted measurements made at independent sites and areas reasonably well. This finding is useful for assessing exposure in health studies conducted in areas where no measurements were conducted.
KW - Air Pollutants/analysis Environmental Monitoring Models, Theoretical Nitrogen Dioxide/analysis Particulate Matter/analysis
UR - https://www.scopus.com/pages/publications/84905264861
U2 - 10.1289/ehp.1307271
DO - 10.1289/ehp.1307271
M3 - Article
SN - 0091-6765
VL - 122
SP - 843
EP - 849
JO - Environmental Health Perspectives
JF - Environmental Health Perspectives
IS - 8
ER -