Evaluation of Land Use Regression Models for NO2 and Particulate Matter in 20 European Study Areas: The ESCAPE Project
详细信息 查看全文
- 作者：Meng Wang ; Rob Beelen ; Xavier Basagana ; Thomas Becker ; Giulia Cesaroni ; Kees de Hoogh ; Audrius Dedele ; Christophe Declercq ; Konstantina Dimakopoulou ; Marloes Eeftens ; Francesco Forastiere ; Claudia Galassi ; Regina Gra啪ulevi膷ien臈 ; Barbara Hoffmann ; Joachim Heinrich ; Minas Iakovides ; Nino K眉nzli ; Michal Korek ; Sarah Lindley ; Anna M枚lter ; Gioia Mosler ; Christian Madsen ; Mark Nieuwenhuijsen ; Harish Phuleria ; Xanthi Pedeli ; Ole Raaschou-Nielsen ; Andrea Ranzi ; Euripides Stephanou ; Dorothee Sugiri ; Morgane Stempfelet ; Ming-Yi Tsai ; Timo Lanki ; Orsolya Udvardy ; Mih谩ly J. Varr贸 ; Kathrin Wolf ; Gudrun Weinmayr ; Tarja Yli-Tuomi ; Gerard Hoek ; Bert Brunekreef
- 刊名：Environmental Science & Technology (ES&T)
- 出版年：2013
- 出版时间：May 7, 2013
- 年：2013
- 卷：47
- 期：9
- 页码：4357-4364
- 全文大小：414K
- 年卷期：v.47,no.9(May 7, 2013)
- ISSN：1520-5851
文摘
Land use regression models (LUR) frequently use leave-one-out-cross-validation (LOOCV) to assess model fit, but recent studies suggested that this may overestimate predictive ability in independent data sets. Our aim was to evaluate LUR models for nitrogen dioxide (NO2) and particulate matter (PM) components exploiting the high correlation between concentrations of PM metrics and NO2. LUR models have been developed for NO2, PM2.5 absorbance, and copper (Cu) in PM10 based on 20 sites in each of the 20 study areas of the ESCAPE project. Models were evaluated with LOOCV and 鈥渉old-out evaluation (HEV)鈥?using the correlation of predicted NO2 or PM concentrations with measured NO2 concentrations at the 20 additional NO2 sites in each area. For NO2, PM2.5 absorbance and PM10 Cu, the median LOOCV R2s were 0.83, 0.81, and 0.76 whereas the median HEV R2 were 0.52, 0.44, and 0.40. There was a positive association between the LOOCV R2 and HEV R2 for PM2.5 absorbance and PM10 Cu. Our results confirm that the predictive ability of LUR models based on relatively small training sets is overestimated by the LOOCV R2s. Nevertheless, in most areas LUR models still explained a substantial fraction of the variation of concentrations measured at independent sites.