Assisted History-Matching Based on Multiobjective Surrogate Reservoir Model for Tight Oil Reservoirs

Abstract

History matching and quantifying uncertainty in hydrocarbon production forecasts are considered important steps in reservoir simulations and are key processes for providing crucial information for decision making in the development of oil and gas fields. However, history matching of unconventional reservoirs with complicated fracture system is very computationally expensive and time consuming, and most of the data used are subject to high uncertainty. In addition, the objectives of history matching are usually conflicting, such as improving match of oil rate will deteriorate match of water rate. Previous studies on assisted history matching have mainly focused on optimizing a single-objective function, where the production and pressure data are combined as a single misfit value. In this study, the proposed algorithm extends the application of the proxy model to deal with multiobjective optimization in the context of reservoir history matching. Then, the resulted proxy model were conducted to analyze history-matching quality and obtain uncertainty prediction. Result suggests that the multiobjective surrogate reservoir model scheme not only could obtain reliable history matches and provide accurate uncertainty estimation, but the complexity of gridded fractures is mitigated through the workflow. The benefit of using the multiobjective surrogate reservoir model is to obtain a various set of history matched models while reducing the number of expensive reservoir simulation runs. The proposed methodology might also be useful for reservoirs in which simulation models could not reflect the production history and for those with high uncertainties in reservoir characterization.