Space-time estimation of grid-cell hourly ozone levels for assessment of adeterministic model

We present an approach to estimate hourly grid-cell surface ozone concentra tions based on observations from point monitoring sites in space, for compa rison with grid-based results from the SARMAP photochemical air-quality mod el for a region of northern California. Statistical estimation is carried o ut on a transformed (square root) scale, followed by back-transforming to t he original scale of ozone in parts per billion, adjusting for bias and var iance. We estimate a spatially-varying diurnal mean structure and a non-sep arable space-time correlation structure on the transformed scale. Temporal pre-whitening is followed by modelling of a spatially nonstationary, diurna lly-varying spatial correlation structure using a spatial deformation appro ach. Comparisons of SARMAP model results with the estimated grid-cell ozone levels are presented.