Idioma:

Concentrations of criteria pollutants in the contiguous U.S., 1979 - 2015: Role of prediction model parsimony in integrated empirical geographic regression

Kim, Sun-Young ; Bechle, Matthew ; Hankey, Steve ; Sheppard, Lianne ; Szpiro, Adam A ; Marshall, Julian D Giorgi, Emanuele

PloS one, 2020-02, Vol.15 (2), p.e0228535 [Periódico revisado por pares]

United States: Public Library of Science

Texto completo disponível

Citações Citado por

Enviar para

Título:
Concentrations of criteria pollutants in the contiguous U.S., 1979 - 2015: Role of prediction model parsimony in integrated empirical geographic regression
Autor: Kim, Sun-Young ; Bechle, Matthew ; Hankey, Steve ; Sheppard, Lianne ; Szpiro, Adam A ; Marshall, Julian D
Giorgi, Emanuele
Assuntos: Air Pollutants - analysis ; Air pollution ; Air Pollution - analysis ; Air Pollution - history ; Air Pollution - statistics & numerical data ; Air pollution measurements ; Analysis ; Atmospheric pollution ; Cancer ; Carbon Monoxide - analysis ; Computer and Information Sciences ; Datasets ; Earth Sciences ; Ecology and Environmental Sciences ; Empirical models ; Environmental engineering ; Environmental Exposure - analysis ; Environmental Exposure - statistics & numerical data ; Environmental Monitoring - history ; Environmental Monitoring - statistics & numerical data ; Estimates ; Geography ; Health sciences ; Heterogeneity ; History, 20th Century ; History, 21st Century ; Humans ; Kriging interpolation ; Land cover ; Land use ; Models, Statistical ; Monitoring ; Nitrogen dioxide ; Nitrogen Dioxide - analysis ; Outdoor air quality ; Ozone ; Ozone - analysis ; Particulate matter ; Particulate Matter - analysis ; Particulate matter monitoring ; Performance evaluation ; Physical Sciences ; Pollutants ; Pollution ; Population ; Prediction models ; Regression Analysis ; Regression models ; Research and Analysis Methods ; Social Sciences ; Spatial Analysis ; Sulfur dioxide ; Sulfur Dioxide - analysis ; Time Factors ; United States - epidemiology ; Variables ; Vegetation
É parte de: PloS one, 2020-02, Vol.15 (2), p.e0228535
Notas: Competing Interests: The authors have declared that no competing interests exist.
Descrição: National-scale empirical models for air pollution can include hundreds of geographic variables. The impact of model parsimony (i.e., how model performance differs for a large versus small number of covariates) has not been systematically explored. We aim to (1) build annual-average integrated empirical geographic (IEG) regression models for the contiguous U.S. for six criteria pollutants during 1979-2015; (2) explore systematically the impact on model performance of the number of variables selected for inclusion in a model; and (3) provide publicly available model predictions. We compute annual-average concentrations from regulatory monitoring data for PM10, PM2.5, NO2, SO2, CO, and ozone at all monitoring sites for 1979-2015. We also use ~350 geographic characteristics at each location including measures of traffic, land use, land cover, and satellite-based estimates of air pollution. We then develop IEG models, employing universal kriging and summary factors estimated by partial least squares (PLS) of geographic variables. For all pollutants and years, we compare three approaches for choosing variables to include in the PLS model: (1) no variables, (2) a limited number of variables selected from the full set by forward selection, and (3) all variables. We evaluate model performance using 10-fold cross-validation (CV) using conventional and spatially-clustered test data. Models using 3 to 30 variables selected from the full set generally have the best performance across all pollutants and years (median R2 conventional [clustered] CV: 0.66 [0.47]) compared to models with no (0.37 [0]) or all variables (0.64 [0.27]). Concentration estimates for all Census Blocks reveal generally decreasing concentrations over several decades with local heterogeneity. Our findings suggest that national prediction models can be built by empirically selecting only a small number of important variables to provide robust concentration estimates. Model estimates are freely available online.
Editor: United States: Public Library of Science
Idioma: Inglês

Links

View this record in MEDLINE/PubMed

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Concentrations of criteria pollutants in the contiguous U.S., 1979 - 2015: Role of prediction model parsimony in integrated empirical geographic regression

Kim, Sun-Young ; Bechle, Matthew ; Hankey, Steve ; Sheppard, Lianne ; Szpiro, Adam A ; Marshall, Julian D Giorgi, Emanuele

United States: Public Library of Science

Buscando em bases de dados remotas. Favor aguardar.