https://www.pe.wvu.edu/Publications/Pdfs/AIReservoirModeling.pdf

Reservoir simulation and modeling based on artificial intelligence and data mining (AI&DM)

Reservoir simulation is routinely used as a reservoir management tool. The static model that is used as the basis for simulation is the result of an integrated effort that usually includes the latest geological, geophysical and petro-physical measurements and interpretations. As such, it is inherently a model with some uncertainty. Analysis of these uncertainties and quantification of their effects on oil production and water cut using a new and efficient technique is the subject of this paper. Typical uncertainty analysis techniques require many realizations and runs of the reservoir model. In the day and age that reservoir models are getting larger and more complicated, making hundreds or sometimes thousands of simulation runs can put considerable strain on the resources of an asset team. This paper summarizes the results of uncertainty analysis on a giant oil field in the Middle East using a new technique that incorporates a Surrogate Reservoir Model (SRM). A Surrogate Reservoir Model that runs and provides results in real-time is developed to mimic the capabilities of a full field model that includes about one million grid blocks and takes 10 hours to run on a cluster of twelve 3.2 GHz CPUs. This Surrogate Reservoir Model is used as the objective function of a Monte Carlo Simulation to study the impact of the uncertainties associated with several parameters on the model outcome, i.e. oil production and water cut is analyzed. The analysis can be performed individually on each of the 165 horizontal wells. During the analyses of uncertainty, the Surrogate Reservoir Model will serve as an objective function for the Monte Carlo Simulation. In this study, uncertainties associated with several reservoir parameterts and their quantitative effect on cumulative oil production and stantaneous water cut are examined.

https://shahab.pe.wvu.edu/Publications/Pdfs/102492.pdf

Quantifying Uncertainties Associated With Reservoir Simulation Studies Using a Surrogate Reservoir Model

There has been considerable enhanced oil recovery (EOR) activity in the North Sea. Eighteen of the 19 reported EOR projects have been gas processes. Most importantly, 16 of the 18 projects are economic successes. The outlook for EOR in the North Sea is promising. In a contract signed August 27, 2007, we were authorized to conduct an EOR literature search and carry out model development work. This contract was preceded by an proposal dated August 24, 2007, and entitled " Proposal: Enhanced Oil Recovery (EOR) Field Data Literature Search. " Not all reservoirs are amenable to EOR. Effective screening practices must be employed to identify suitable candidates. Economic evaluations require an estimate of the recovery performance. Empirical methods are invariably used to predict performance for early evaluations. The objective of our literature search was to collect enough field data to develop an empirical model to predict the oil-rate history of a prospect reservoir. Owing to past and current EOR trends in the North Sea, efforts focused on miscible gas EOR. We have successfully developed an EOR rate model. This model is based on hyperbolic decline curves and material balance. The model effectively matches the production history of tertiary miscible floods. The model can easily be incorporated into pre-existing discounted cash-flow models. The public literature is rich in EOR field data references. Over 390 papers were collected on 70 separate miscible gas projects. Our search sought rate history data with specific supplemental information. The process of gathering and analyzing papers was very time-consuming but informative. In the end, seven case histories suitable for validating the empirical model were identified. All of the cases were onshore U.S. CO 2 floods. Additional testing, however, is needed as new data becomes available. The model is simple enough to add such data. The work here also includes compiled sets of screening criteria from our literature search. The screening criteria are informative. In summary, the results of this work should be helpful in evaluating prospects for gas injection EOR. APPENDICES " A " Paper Inventory (pg. 40) " B " Catalogue of Miscible-Flood Case Histories (pg.53) " C " Supplemental Empirical Correlations (pg. 85) " D " Estimating Incremental Recovery (pg. 90) " E " Catalogue of EOR Screening Criteria (pg. 93)

Enhanced oil recovery (eor) field data literature search

Waterflooding is a significantly important process in the life of an oil field to sweep previously unrecovered oil between injection and production wells and maintain reservoir pressure at levels above the bubble-point pressure to prevent gas evolution from the oil phase. This is a critical reservoir management practice for optimum recovery from oil reservoirs. Optimizing water injection volumes and optimizing well locations are both critical reservoir engineering problems to address since water injection capacities may be limited depending on the geographic location and facility limits. Characterization of the reservoir connectivity between injection and production wells can greatly contribute to the optimization process. In this study, it is proposed to use computationally efficient methods to have a better understanding of reservoir flow dynamics in a waterflooding operation by characterizing the reservoir connectivity between injection and production wells. First, as an important class of artificial intelligence methods, artificial neural networks are used as a fully data-driven modeling approach. As an additional powerful method that draws analogy between source/sink terms in oil reservoirs and electrical conductors, capacitance---resistance models are also used as a reduced-physics-driven modeling approach. After understanding each method's applicability to characterize the interwell connectivity, a comparative study is carried out to determine strengths and weaknesses of each approach in terms of accuracy, data requirements, expertise requirements, training algorithm and processing times.

/pdf/characterizing-interwell-connectivity-in-waterflooded-44ttkxtiyl.pdf

Characterizing interwell connectivity in waterflooded reservoirs using data-driven and reduced-physics models: a comparative study

A holistic review on artificial intelligence techniques for well placement optimization problem

Development of Surrogate Reservoir Models (SRM) For Fast Track Analysis of Complex Reservoirs

Simulation models are routinely used as a powerful tool for reservoir management. The underlying static models are the result of integrated efforts that usually includes the latest geophysical, geological and petrophysical measurements and interpretations. As such, these models carry an inherent degree of uncertainty. Typical uncertainty analysis techniques require many realizations and runs of the reservoir simulation model. In this day and age, as reservoir models are getting larger and more complicated, making hundreds or sometimes thousands of simulation runs can put considerable strain on the resources of an asset team, and most of the times are simply impractical. Analysis of these uncertainties and their effects on well performance using a new and efficient technique is the subject of this paper. The analysis has been performed on a giant oil field in the Middle East using a surrogate reservoir model. The surrogate reservoir model that runs and provides results in real-time is developed to mimic the capabilities of a full field simulation model that includes one million grid blocks and takes 10 hours to run using a cluster of twelve 3.2 GHz CPUs. In order to effectively demonstrate the robustness of Surrogate Reservoir Models and their capabilities as tools that can be used for uncertainty analysis, one must demonstrate that SRMs are competent in providing reasonably accurate results for multiple realizations of the reservoir being studied. In order to demonstrate such robustness and their predictive capabilities as well as their limitations, this paper will examine the performance of the surrogate reservoir models on different geologic realizations of the static model.

https://www.pe.wvu.edu/Publications/Pdfs/SPE101474.pdf

Maher Mahmoud Kenawy

Papers

Development of Surrogate Reservoir Models (SRM) For Fast Track Analysis of Complex Reservoirs

Uncertainty Analysis of a Giant Oil Field in the Middle East Using Surrogate Reservoir Model

Successful Application of Swell Packer Technology to shut-off Water Production in Horizontal Wells - Case Studies from Onshore Abu Dhabi

Producing Dry Oil From a Transition Zone: Should This Be Called a Wedge Zone?

Miscible Gas Injection Piloting and Modeling in a Giant Carbonate Reservoir