Application of Machine Learning and Artificial Intelligence in Proxy Modeling for Fluid Flow in Porous Media

Shohreh Amini,Shahab Mohaghegh

doi:10.3390/fluids4030126

Abstract

Reservoir simulation models are the major tools for studying fluid flow behavior in hydrocarbon reservoirs. These models are constructed based on geological models, which are developed by integrating data from geology, geophysics, and petro-physics. As the complexity of a reservoir simulation model increases, so does the computation time. Therefore, to perform any comprehensive study which involves thousands of simulation runs, a very long period of time is required. Several efforts have been made to develop proxy models that can be used as a substitute for complex reservoir simulation models. These proxy models aim at generating the outputs of the numerical fluid flow models in a very short period of time. This research is focused on developing a proxy fluid flow model using artificial intelligence and machine learning techniques. In this work, the proxy model is developed for a real case CO2 sequestration project in which the objective is to evaluate the dynamic reservoir parameters (pressure, saturation, and CO2 mole fraction) under various CO2 injection scenarios. The data-driven model that is developed is able to generate pressure, saturation, and CO2 mole fraction throughout the reservoir with significantly less computational effort and considerably shorter period of time compared to the numerical reservoir simulation model.

Highlights

Developing a reservoir simulation model and conducting it for thousands of different scenarios provides us with a solution space which can be used for extensive uncertainty analysis.this technique essentially will be impractical for a geologically complex reservoir simulation model with millions of grid blocks, even if it requires only few hours for a single run to be accomplished. applying new technologies, such as cloud computing, can accelerate the process of running huge reservoir simulation models, it has its own complications; first of all these technologies are expensive and secondly, it would not be fast enough for a decision-making process
The results of this study showed that neural networks can be used as a fast and efficient tool for assisted history matching process [23]
The work flow which was followed to develop the fluid flow proxy model is presented in detail

Summary

Introduction

Developing a reservoir simulation model and conducting it for thousands of different scenarios provides us with a solution space which can be used for extensive uncertainty analysis. Applying new technologies, such as cloud computing, can accelerate the process of running huge reservoir simulation models, it has its own complications; first of all these technologies are expensive and secondly, it would not be fast enough for a decision-making process. Encountering such a problem motivates the quest to find an alternative approach. There is no proxy model that can generate exactly the same output as the original model, they can be significantly beneficial in approximating the desired outputs

Methods

Results

Discussion

Conclusion