Application of Neural Networks to Modeling Fluid Contacts in Prudhoe Bay
- M.N. Panda (Arco Exploration and Production Technology) | D.E. Zaucha (Arco Exploration and Production Technology) | G. Perez (Arco Exploration and Production Technology) | A.K. Chopra (Arco Exploration and Production Technology)
- Document ID
- Society of Petroleum Engineers
- SPE Journal
- Publication Date
- September 1996
- Document Type
- Journal Paper
- 303 - 312
- 1996. Society of Petroleum Engineers
- 7.6.6 Artificial Intelligence, 5.5 Reservoir Simulation, 5.2 Reservoir Fluid Dynamics, 5.1 Reservoir Characterisation, 5.1.1 Exploration, Development, Structural Geology, 5.6.4 Drillstem/Well Testing, 5.1.8 Seismic Modelling, 4.3.4 Scale, 5.4.1 Waterflooding, 2.4.3 Sand/Solids Control, 6.1.5 Human Resources, Competence and Training, 5.1.5 Geologic Modeling, 2.2.2 Perforating, 3.3.1 Production Logging
- 0 in the last 30 days
- 217 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 35.00|
Modeling the dynamic behavior of fluid movement in an oil reservoir is complicated because of non-linear interactions between the reservoir heterogeneity and fluid flow. Simple regression, geostatistical and numerical simulation techniques have been used in the past to model fluid movement with various degrees of success. Most of these methods, however, suffer from common drawbacks that they are time consuming and difficult to automate. This paper presents a new method based on artificial neural networks (ANNs) to model dynamic gas-oil contacts in the Prudhoe Bay reservoir. This method is fast, efficient, and highly automated and requires minimum user intervention.
The proposed method uses oil, gas, and water production, perforation history, permeability, sand and shale distribution, and surveillance data at surrounding wells as input to an ANN to predict the fluid distribution at a target well. A two-step method is developed to design an ANN. The first step trains the network using previously measured data as input and output, and thus establishing the internal rules of the network. The second step uses the trained network to estimate the fluid distribution at target wells. Results show that the ANN method can predict fluid distribution at target wells more accurately and consistently than the conventional regression-based methods.
The Prudhoe Bay field on the north coast of Alaska is the largest oil field in the North America, with total estimated original oil in place (OOIP) of about 22 billion barrels. The field is overlain by a large gas cap and a major portion of the field is being produced by gravity drainage. Waterflood operations are confined to the down-structure and peripheral areas of the field. Geographically, Prudhoe Bay can be roughly divided into two regions based on the development strategy and current recovery mechanisms: gravity drainage and water and miscible gas flooding (Fig. 1). This paper deals only with the gravity drainage area.
Characterizing fluid movement in a reservoir is a critical engineering task because it forts key elements for field development, reservoir management, and predicting reservoir performance for different mechanisms. The benefits of such a characterization include reduction of gas and water handling costs, selection of completion and re-completion intervals, and development of better reservoir simulation models. In Prudhoe Bay, the interactions between different drive mechanisms, such as gravity drainage, gas cap expansion, waterflooding, miscible displacement, and the reservoir architecture and heterogeneities (shales, faults, and fractures) result in complex gas and water movement through time. Shales of varying sizes, which may not be continuous between wells, have a significant effect on the gas movement.
|File Size||676 KB||Number of Pages||9|