Reservoir simulation has become the industry standard for reservoir management. It is now used in all phases of field development in the oil and gas industry. The full field reservoir models that have become the major source of information and prediction for decision making are continuously updated and major fields now have several versions of their model with each new version being a major improvement over the previous one. The newer versions have the latest information (geologic, geophysical and petro-physical measurements, interpretations and calculations based on new logs, seismic data, injection and productions, etc.) incorporated in them along with adjustments that usually are the result of single-well or multi-well history matching.
A typical reservoir model consists of hundreds of thousands and in many cases millions of grid blocks. As the size of the reservoir models grow the time required for each run increases. Schemes such as grid computing and parallel processing helps to a certain degree but cannot close the gap that exists between simulation runs and real-time processing. On the other hand with the new push for smart fields (a.k.a. i-fields) in the industry that is a natural growth of smart completions and smart wells, the need for being able to process information in real time becomes more pronounced. Surrogate Reservoir Models (SRMs) are the natural solution to address this necessity. SRMs are prototypes of the full field models that can run in fractions of a second rather than in hours or days. They mimic the capabilities of a full field model with high accuracy. These models can be developed regularly (as new versions of the full field models become available) off-line and can be put online for automatic history matching and real-time processing that can guide important decisions. SRMs can efficiently be used for real-time optimization, real-time decision making as well as analysis under uncertain conditions.
This paper presents a unified approach for development of SRMs using the state-of-the-art in intelligent systems techniques. An example for developing an SRM for a giant oil field in the Middle East is presented and the results of the analysis using the SRM for this field is discussed. In this example application SRM is used in order to analyze the impact of the uncertainties associated with several input parameters into the full field model.