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.

Reservoir simulation models are used extensively to model complex physics associated with fluid flow in porous media. Such models are usually large with high computational cost. The size and computational footprint of these models make it impractical to perform comprehensive studies which involve thousands of simulation runs. Uncertainty analysis associated with the geological model and field development planning are good examples of such studies. In order to address this problem, efforts have been made to develop proxy models which can be used as a substitute for a complex reservoir simulation model in order to reproduce the outputs of the reservoir models in short periods of time (seconds). In this study, by using artificial intelligence techniques a Grid-Based Surrogate Reservoir Model (SRM G) is developed. Gridbased SRM is a replica of the complex reservoir simulation models that is trained, calibrated and validated to accurately reproduce grid block level results. This technology is applied to a CO 2 sequestration project in Australia. This paper presents the development of the reservoir simulation model and the Grid-based SRM. The SRM is able to generate pressure and gas saturation at the grid block level. The results demonstrate that this technique is capable of generating the reservoir simulation output very accurately within seconds.

While CO2 Capture and Sequestration (CCS) is considered a part of the solution to overcoming the ever increasing level of CO2 in the atmosphere, one must be sure that significant new hazards are not created by the CO2 injection process. The risks involved in different stages of a CO2 sequestration project are related to geological and operational uncertainties. This paper presents the application of a grid-based Surrogate Reservoir Model (SRM) to a real case CO2 sequestration project in which CO2 were injected into a depleted gas reservoir. An SRM is a customized model that accurately mimics reservoir simulation behavior by using Artificial Intelligence & Data Mining techniques. Initial steps for developing the SRM included constructing a reservoir simulation model with a commercial software, history matching the model with available field data and then running the model under different operational scenarios or/and different geological realizations. The process was followed by extracting some static and dynamic data from a handful of simulation runs to construct a spatio-temporal database that is representative of the process being modeled. Finally, the SRM was trained, calibrated, and validated. The most widely used Quantitative Risk Analysis (QRA) techniques, such as Monte Carlo simulation, require thousands of simulation runs to effectively perform the uncertainty analysis and subsequently risk assessment of a project. Performing a comprehensive risk analysis that requires several thousands of simulation runs becomes impractical when the time required for a single simulation run (especially in a geologically complex reservoir) exceeds only a few minutes. Making use of surrogate reservoir models (SRMs) can make this process practical since SRM runs can be performed in minutes. Using this Surrogate Reservoir Model enables us to predict the pressure and CO2 distribution throughout the reservoir with a reasonable accuracy in seconds. Consequently, application of SRM in analyzing the uncertainty associated with reservoir characteristics and operational constraints of the CO2 sequestration project is presented.

No abstract

Developing proxy models has a long history in our industry. Proxy models provide fast approximated solutions that substitute large numerical simulation models. They serve specific useful purposes such as assisted history matching and production/injection optimization. Most common proxy models are either reduced models or response surfaces. While the former accomplishes the run-time speed by grossly approximating the problem the latter accomplishes it by grossly approximating the solution space. Nevertheless, they are routinely developed and used in order to generate fast solutions to changes in the input space. Regardless of the type of model simplifications that is used, these conventional proxy models can only provide, at best, responses at the well locations, i.e. pressure or rate profiles at the well.