Fluid Flow Simulation in Naturally Fractured Porous Media Using Deep Learning

Abstract

Reservoir simulation has been used to replicate reservoir conditions and thus, reservoir performance. The downside is that it is computationally demanding, it is time-consuming andit requires certain level of expertise in programming and knowledge in reservoir engineering. Another issue with reservoir simulators is that they tend to be slow or they can be expensive. To overcome these challenges, this thesis proposes an alternative approach based on the development of an AI model trained using the characteristics of the reservoir of interest.