Format

Send to

Choose Destination
Environ Sci Technol. 2016 Apr 5;50(7):3686-94. doi: 10.1021/acs.est.5b05099. Epub 2016 Mar 21.

Satellite-Based NO2 and Model Validation in a National Prediction Model Based on Universal Kriging and Land-Use Regression.

Author information

1
Department of Epidemiology, University of Washington 4225 Roosevelt Way NE, Seattle, Washington 98105, United States.
2
Civil & Environmental Engineering, University of Washington , Wilcox 268, Seattle, Washington 98195, United States.
3
Department of Statistics, University of Washington B313 Padelford Hall, Northeast Stevens Way, Seattle, Washington 98195, United States.
4
Department of Biostatistics, University of Washington 1705 NE Pacific Street, Seattle, Washington 98195, United States.
5
Department of Environmental and Occupational Health Sciences, University of Washington 1959 Pacific Street, Seattle, Washington 98195, United States.

Abstract

Epidemiological studies increasingly rely on exposure prediction models. Predictive performance of satellite data has not been evaluated in a combined land-use regression/spatial smoothing context. We performed regionalized national land-use regression with and without universal kriging on annual average NO2 measurements (1990-2012, contiguous U.S. EPA sites). Regression covariates were dimension-reduced components of 418 geographic variables including distance to roadway. We estimated model performance with two cross-validation approaches: using randomly selected groups and, in order to assess predictions to unmonitored areas, spatially clustered cross-validation groups. Ground-level NO2 was estimated from satellite-derived NO2 and was assessed as an additional regression covariate. Kriging models performed consistently better than nonkriging models. Among kriging models, conventional cross-validated R(2) (R(2)cv) averaged over all years was 0.85 for the satellite data models and 0.84 for the models without satellite data. Average spatially clustered R(2)cv was 0.74 for the satellite data models and 0.64 for the models without satellite data. The addition of either kriging or satellite data to a well-specified NO2 land-use regression model each improves prediction. Adding the satellite variable to a kriging model only marginally improves predictions in well-sampled areas (conventional cross-validation) but substantially improves predictions for points far from monitoring locations (clustered cross-validation).

PMID:
26927327
PMCID:
PMC5104568
DOI:
10.1021/acs.est.5b05099
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for American Chemical Society Icon for PubMed Central
Loading ...
Support Center