Space-time Modeling of Daily Sulfate Levels Combining Observations and CMAQ Output

• Activity Number: 85
• Type: Contributed
• Date/Time: Monday, August 9, 2004 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics and the Environment
• Author(s): Mikyoung Jun*+ and Michael L. Stein
• Companies: University of Chicago and University of Chicago
• Keywords: space-time covariance function ; air quality model ; model evaluation ; space-time process ; separable covariance function

Abstract

New statistical procedures to evaluate the Models-3/Community Multiscale Air Quality (CMAQ), a numerical, deterministic model which produces multiple air pollutants' concentration and deposition levels over U.S. and some parts of Canada, using observed data are introduced. Certain space-time correlations are used to assess dynamic aspects of CMAQ and to compare the space-time structure of CMAQ to that of observations. We show that developing statistical models of the difference of CMAQ output and observations should be easier than developing models for the observations or CMAQ output directly, which has direct implications on strategies for developing maps of sulfate concentrations using observations and model output. Statistical evidence against separable covariance functions, which are often used for space-time or multivariate spatial processes, are given. Space-time modeling results for the difference of CMAQ output and observations based on various space-time covariance functions will be compared. The development of space-time covariance function on a sphere across time will be discussed.