Spatio-temporal methods have been developed for the estimation of concentrations of pollutants such as particulate matter and nitrogen dioxide for application in epidemiological studies. A limited number of city-specific spatio-temporal ozone (O3) models have been proposed until today. Our aim was to develop a spatio-temporal land use regression (LUR) model that estimates daily concentrations of O3, for the whole year, as well as the warm (April-September) and cold season (October-March), within the greater Athens area. We developed models using a semiparametric approach including linear and smooth functions of spatial and temporal covariates and a bivariate smooth thin plate function. The final set of explanatory variables was selected based on the adjusted-R2. We tested the final model in temporal and spatial terms following a leave-one out monitor approach. The adjusted-R2 in the leave-one-out cross validation was 0.73 for the annual model (warm: 0.65 and cold: 0.70). The spatial terms in our annual model explained 32.9% and the temporal 63.2% of the variability in O3. The developed models showed good validity when comparing predicted and observed measurements for the 2015 data. Spatio-temporal LUR modeling provides a useful tool for estimating O3 spatio-temporal variability with adequate accuracy for subsequent use in epidemiological studies.