This study aims to examine the application of pattern recognition technologies to improve the time and efforts required for completing a successful history matching project. The pattern recognition capabilities of artificial intelligence and data mining techniques are used to develop a Surrogate Reservoir Model (SRM) and use it to perform the assisted history matching process. A well-known standard reservoir model, PUNQ-S3, was selected to examine the potentials of SRM in an assisted history matching process.SRM is a prototype of full field reservoir simulation model that runs in a matter of seconds. SRMs are built based on a spatiotemporal database. The database includes different types of data extracted from a few realizations of the simulation model. In this study, the SRM was developed using ten geological realizations of PUNQ-S3 reservoir simulation model. The uncertain properties are distributions of porosity, horizontal, and vertical permeability. The SRM requires low development cost and has high implementation pace. The SRM was coupled with the Differential Evolution (DE) optimization method to construct an automated history matching workflow. This workflow is able to produce multiple realizations of the reservoir, which match the past performance.The developed SRM showed a high accuracy in mimicking the behavior of reservoir simulation model. Once we select the best performing cases during history matching, we were able to also obtain relaiable future forecasts for the model. The results of this study prove the cability of SRMs in assisting history matching process using population-based sampling algorithms and other computationally intensive operations in reservoir management workflows.