Artificial Intelligence Assisted History Matching -- Proof of Concept

History matching is the process of adjusting uncertain reservoir parameters until an acceptable match with the measured production data is obtained. Complexity and sub-optimal knowledge of reservoir characteristics makes this process time-consuming with high computational cost. In the past, computer-assisted history matching has attempted to make this process faster; however, the degree of success of these techniques continues to be a subject for debate.;In this study, the objective is to prove and examine the application of a relatively new Artificial Intelligence based technology (Surrogate Reservoir Model -- SRM) to assist the history match process. SRM is a prototype of full-field reservoir simulation model that runs in fractions of a second. The capability of generating meaningful outputs in a short time period with acceptable accuracy makes SRM a unique tool for assisted history matching.;In this project, an SRM was created for a synthetic case study of a heterogeneous and complex oil field, with 24 production wells and 30 years of production history. The history matching was performed for this field using SRM and tuning static data (permeability). The result of this study is a proof of concept and shows that SRM is able to reproduce the numerical simulator results faster and with an acceptable accuracy. These characteristics make SRM a fast and effective tool for assisted history matching