Oil and gas reservoir modelling involves two broad classes of data: static (for example, core, well logs, and seismic interpretation) and dynamic (pressure and fluid production observed at wells). Integration of dynamic data together with static data enhances the quality of the reservoir models generated and provides the reservoir engineers with a better basis for reservoir simulation and management. The uncertainty of simulated production scenarios is then reduced, allowing a more realistic economic evaluation. In general, however, integrating these two sources of data is still a challenge in petroleum reservoir modelling. In this work, an approach based on the Bayesian formalism for combining static and dynamic data is discussed. The geological relevant parameters are determined by minimizing an objective function that measures the misfit between observed and calculated dynamic data using static data as prior information. The use of efficient techniques for calculating derivatives of observed data with respect to parameters and for the optimization algorithm are essential to build a computationally feasible procedure.