Applying an optimized low risk model for fast history matching in a giant oil reservoir

In this paper, the latest approaches for automated history matching (AHM) were applied to a real brown field having 14 active wells with multiple responses (production rate, bottom hole pressure and well block pressure) located in the south of Iran. A modified support vector machine was employed to create a proxy model incorporated based on design of experimental. Thereafter, all model parameters were adjusted to reproduce the observed history within the created proxy model. Accordingly, the proposed proxy model was successfully constructedusing1086samplesbasedonanR ² coefficientofabout0.9forthetrainedandtestdataset.Finally,theprocess was optimized by two main algorithms to reach the best solutions, which are genetic and particle swarm optimization.