Reservoir automatic history matching: Methods, challenges, and future directions

Reservoir history matching refers to the process of continuously adjusting parameters reservoir model, so that its dynamic response will match historical observation data, which is a prerequisite for making forecasts based on model. With development optimization theory and machine learning algorithms, automatic has made numerous breakthroughs practical applications. In this perspective, existing methods are summarized divided into model-driven surrogate-driven according whether simulator needs be run during process. Then, basic principles these their limitations in applications outlined. Finally, future trends discussed. Document Type : Perspective Cited as: Liu, P., Zhang, K., Yao, J. matching: Methods, challenges, directions. Advances Geo-Energy Research, 2023, 7(2): 136-140. https://doi.org/10.46690/ager.2023.02.07