The purpose of the present study is to investigate the sensitivity of ozone (O<sub>3</sub>) predictions in the Mexico City Metropolitan Area (MCMA) to meteorological initial uncertainties and planetary boundary layer (PBL) parameterization schemes using state-of-the-art meteorological and photochemical prediction models through ensemble forecasts. The simulated periods (3, 9, 15 and 29 March 2006) represent four typical meteorological episodes ("South-Venting", "O<sub>3</sub>-North", "O<sub>3</sub>-South" and "Convection-North", respectively) in the Mexico City basin during the MCMA-2006/MILAGRO campaign. Our results demonstrate that the uncertainties in meteorological initial conditions have significant impacts on O<sub>3</sub> predictions, including peak time O<sub>3</sub> concentrations ([O<sub>3</sub>]), horizontal and vertical O<sub>3</sub> distributions, and temporal variations. The ensemble spread of the simulated peak [O<sub>3</sub>] averaged over the city's ambient monitoring sites can reach up to 10 ppb. The increasing uncertainties in meteorological fields during peak O<sub>3</sub> period contribute to the largest unpredictability in O<sub>3</sub> simulations, while the impacts of wind speeds and PBL height on [O<sub>3</sub>] are more straightforward and important. The magnitude of the ensemble spreads varies with different PBL schemes and meteorological episodes. The uncertainties in O<sub>3</sub> predictions caused by PBL schemes mainly come from their ability to represent the mixing layer height; but overall, these uncertainties are smaller than those from the uncertainties in meteorological initial conditions.