Masoud Nikravesh, Lawrence Berkeley National Laboratory and BISC Program, Computer Science Division, University of California at Berkeley, SPE; Chuck A. Dobie, Crutcher-Tufts, SPE; and Tad W. Patzek, University of California at Berkeley, SPE
Here we present the third generation of "intelligent" oil field surveillance and prediction software based on neural networks and fuzzy logic. Neural networks and fuzzy logic provide a way to incorporate disparate information because a structural relationship between input and output data is not required. The model helps to improve waterflood management and avoid reservoir damage. It can also be used to visualize the global trajectory of an entire project and allow engineers to recognize patterns of incipient reservoir damage and poor performance. The diatomaceous fields of California, which hold an estimated 10 billion bbl of oil-in-place, have been chosen to demonstrate the power of neural networks and fuzzy logic. However, this methodology is applicable directly to fluid injection into other tight fractured reservoirs such as the Austin Chalk and the West Texas Carbonates.
Petroleum reservoirs are known to exhibit inherently complex, nonlinear, time varying and nonstationary behavior. Fluids such as water or steam are injected into reservoirs to maintain pressure and displace oil. Although an oil field is a complex and highly coupled system, injectors are usually controlled individually, with constant setpoints, and without feedback among neighboring patterns.
In this study, we focus on water injection in tight reservoirs because significant quantities of crude oil remain in them, and state-of-the-art understanding of fluid movement in low permeability rock systems is not sufficient for the design and operation of large fluid injection projects. Water injection is also important for mitigating reservoir compaction and surface subsidence. Here, we compare specifically two waterflood projects. First, we examine a waterflood project (Lost Hills I) in Section 2 of the Lost Hills Diatomite (Kern County, California), operated by Mobil E&P U.S. The Lost Hills I waterflood has 123 producers and 48 injectors. The data set includes 5 years of historical injection and production rate data collected at 1 to 10-day intervals. Second, we examine a waterflood project on the Dow Chanslor lease in the Middle Belridge Diatomite (Kern County, California), operated by Crutcher-Tufts. Historically, the Dow Chanslor waterflood has had 138 producers and 36 injectors. Today, there are 70 producers and 33 injectors. The data set includes 10 years of historical injection and production rate data collected at 30-day intervals. In both projects, neural networks and fuzzy logic have been used to divide the oil field into regions with similar characteristic behavior.
The diatomaceous fields of California, which represent a $42 billion resource, have been chosen to develop and demonstrate the potential of neural networks and fuzzy logic approaches for an optimal fluid injection policy.