No abstract

Forward and inverse gravity modeling is carried out on a suite of reservoir simulations of a proposed water injection in the Prudhoe Bay reservoir, Alaska. A novel surveillance technique is developed in which surface gravity observations are used to monitor the progress of a gas cap waterflood in the reservoir at 8200-ft (2500-m) depth. This cost‐effective method requires that high‐precision gravity surveys be repeated over periods of years. Differences in the gravity field with time reflect changes in the reservoir fluid densities. Preliminary field tests at Prudhoe Bay indicates survey accuracy of 5–10 μGal can be achieved for gravity data using a modified Lacoste & Romberg “G” type meter or Scintrex CG-3M combined with the NAVSTAR Global Positioning System (GPS). Forward gravity modeling predicts variations in surface measurements of 100 μGal after 5 years of water injection, and 180–250 μGal after 15 years. We use a constrained least‐squares method to invert synthetic gravity data for subsurface density distributions. The modeling procedure has been formulated and coded to allow testing of the models for sensitivity to gravity sampling patterns, noise types, and various constraints on model parameters such as density, total mass, and moment of inertia. Horizontal‐feature resolution of the waterflood is about 5000 ft (1520 m) for constrained inverse models from synthetic gravity with 5 μGal standard deviation (SD) noise. The inversion method can account for total mass of injected water to within a few percent. Worst‐case scenarios result from inversion of gravity data which are contaminated by high levels (greater than 10–15 μGal SD) of spatially correlated noise, in which case the total mass estimate from inverse models may over or underestimate the mass by 10–20%. The results of the modeling indicate that inversion of time‐lapse gravity data is a viable technique for the monitoring of reservoir gas cap waterfloods.

The 4D microgravity method is becoming a mature technology. A project to develop practical measurement and interpretation techniques was conducted at Prudhoe Bay, Alaska, from 1994 through 2002. Beginning in 2003 these techniques have been systematically applied to monitor a waterflood in the gas cap of the Prudhoe Bay reservoir. Approximately 300 stations in a [Formula: see text] area are reoccupied in each survey year with sub-[Formula: see text] precision absolute gravity and centimeter precision Global Positioning System (GPS) geodetic measurements. The 4D gravity measured over epochs 2005–2003, 2006–2003, and 2007–2003 has been successfully modeled to track the mass of water injected since late in 2002. A new and improved version of the A-10 field-portable absolute gravity meter was developed in conjunction with this project and has proven to be a key element in the success of the 4D methodology. The use of an absolute gravity meter in a field survey of this magnitude is unprecedented. There are substantial differences between a 4D absolute microgravity survey and a conventional gravity survey in terms of station occupation procedures, GPS techniques, and the 4D elevation correction. We estimate that the overall precision of the 4D gravity signal in each epoch is less than [Formula: see text].

Between March 2003 and March 2007, four high-precision 4D absolute microgravity surveys were performed at Prudhoe Bay, Alaska. These surveys are part of an ongoing effort to monitor the progress of a very large water-injection project in the gas cap of the Prudhoe Bay reservoir at a depth of [Formula: see text]. These carefully acquired gravity data must be modeled and interpreted in terms of water movement within the reservoir. A constrained linear inversion scheme was tested on reservoir simulations during the planning and development phase of this project (preinjection). The inver-sion methodology has been applied to data for three epochs (2005–2003, 2006–2003, and 2007–2003), and mass-distribution models have been produced for the reservoir. The time evolution of the water-mass distribution in the reservoir is visualized from these three snapshot models. The waterflood is expanding into the gas cap at the expected rate but is exhibiting nonsymmetric behavior that is consistent with a greater degree of structural control than expected. The waterflood seems to be restrained episodically and guided by fault barriers. These barriers are overcome and fault-bounded blocks filled with water in stages.