Premium
A dynamic process convolution approach to modeling ambient particulate matter concentrations
Author(s) -
Calder Catherine A.
Publication year - 2008
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/env.852
Subject(s) - particulates , bivariate analysis , environmental science , convolution (computer science) , meteorology , atmospheric sciences , statistics , mathematics , computer science , geography , physics , chemistry , organic chemistry , machine learning , artificial neural network
Elevated levels of particulate matter (PM) in the ambient air have been shown to be associated with certain adverse human health effects. As a result, monitoring networks that track PM levels have been established across the United States. Some of the older monitors measure PM less than 10 µm in diameter (PM 10 ), while the newer monitors track PM levels less than 2.5 µm in diameter (PM 2.5 ); it is now believed that this fine component of PM is more likely to be related to the negative health effects associated with PM. We propose a bivariate dynamic process convolution model for PM 2.5 and PM 10 concentrations. Our aim is to extract information about PM 2.5 from PM 10 monitor readings using a latent variable approach and to provide better space‐time interpolations of PM 2.5 concentrations compared to interpolations made using only PM 2.5 monitoring information. We illustrate the approach using PM 2.5 and PM 10 readings taken across the state of Ohio in 2000. Copyright © 2007 John Wiley & Sons, Ltd.