Dynamic Layered Pressure Map Generation in a Mature Waterflooding Reservoir Using Artificial Intelligence Approach
- Yuanjun Li (University of Southern California) | Andrei Popa (Chevron) | Andrew Johnson (Chevron) | Iraj Ershaghi (University of Southern California) | Steve Cassidy (Chevron)
- Document ID
- Society of Petroleum Engineers
- SPE Western Regional Meeting, 22-26 April, Garden Grove, California, USA
- Publication Date
- Document Type
- Conference Paper
- 2018. Society of Petroleum Engineers
- 5.4.1 Waterflooding, 7.6 Information Management and Systems, 5.4 Improved and Enhanced Recovery, 7 Management and Information, 5 Reservoir Desciption & Dynamics, 7.6.6 Artificial Intelligence, 7.6.7 Neural Networks
- neural networks, reservoir pressure, Waterflooding, fall-off tests, fuzzy-kriging
- 13 in the last 30 days
- 205 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 9.50|
|SPE Non-Member Price:||USD 28.00|
In this paper, we present an Artificial Neural Network (ANN) solution approach to estimate average reservoir pressure from partial data recorded from fall-off tests. The methodology, while relatively simple, is entirely based on calibrating data from well tests with full fall-off information. Compared with conventional reservoir pressure estimation models, which usually require a long shut-in time and manual analysis for an individual well, this approach provides an efficient way of processing large data sets. Using data from injection well fall-off tests can avoid cost from non-producing periods of production wells. Also, utilizing injection profile tracers with shut-in pressure trends at the surface, we can infer the sand face pressure trends assuming a hydrostatic column during a shut-in period, greatly reducing instrumentation costs and downhole jewelry requirements.
This methodology is extremely helpful for mapping average pressure around injection wells in a reservoir with hundreds of injection wells with multiple flow units. In principle, maps generated from fall-off tests can be used as diagnostic tools to assist in formulating water flooding plans, ameliorating oil production capability, arranging well pattern density and preserving reservoir stability by providing an overview of internal oilfield conditions. Because of its practical simplicity and maneuverability, this new methodology can rapidly offer actionable data and generate remarkable business value.
|File Size||1 MB||Number of Pages||14|
Arehart, R. A. (1990). Drill-Bit Diagnosis with Neural Networks. Society of Petroleum Engineers. doi:10.2118/19558-PA.
Arpat, B. G., Caers, J., & Haas, A. (2001). Characterization of West-Africa Submarine Channel Reservoirs: A Neural Network Based Approach to Integration of Seismic Data. Society of Petroleum Engineers. doi:10.2118/71345-MS.
Brink, J. L., Patzek, T. W., Silin, D. B., & Fielding, E. J. (2002). Lost Hills Field Trial - Incorporating New Technology for Reservoir Management. Society of Petroleum Engineers. doi:10.2118/77646-MS.
Chacon, A., Djebrouni, A., & Tiab, D. (2004). Determining the Average Reservoir Pressure from Vertical and Horizontal Well Test Analysis Using the Tiab's Direct Synthesis Technique. Society of Petroleum Engineers. doi:10.2118/88619-MS.
Crump, J. G., & Hite, R. H. (2008). A New Method for Estimating Average Reservoir Pressure: The Muskat Plot Revisited. Society of Petroleum Engineers. doi:10.2118/102730-PA.
Dastan, A., Kamal, M. M., Collins, J. R., & Neubauer, E. B. (2012). Calculation of Average Reservoir Pressure During Primary and Secondary Recovery and Under Variable Boundary Conditions. Society of Petroleum Engineers. doi:10.2118/159568-MS.
De Roos, M. C., Oldenziel, T., & van Kruijsdijk, C. P. (2001). Neural Network as an Alternative to Rock Physics Modeling in Time-Lapse Seismic Reservoir Monitoring. Offshore Technology Conference. doi:10.4043/13162-MS.
Gharbi, R. B., & Elsharkawy, A. M. (1990). Neural Network Model for Estimating the PVT Properties of Middle East Crude Oils. Society of Petroleum Engineers. doi:10.2118/56850-PA.
Hasan, A. R., & Kabir, C. S. (1983). Pressure Buildup Analysis: A Simplified Approac. Society of Petroleum Engineers. doi:10.2118/10542-PA.
Hegeman, P. S., Dong, C., Varotsis, N., & Gaganis, V. (2009). Application of Artificial Neural Networks to Downhole Fluid Analysis. Society of Petroleum Engineers. doi:10.2118/123423-PA.
Larson, V. C. (1963). Understanding the Muskat Method of Analysing Pressure Build-up Curves. Petroleum Society of Canada. doi:10.2118/63-03-05.
Mead, H. N. (1981). A Practical Approach to Transient Pressure Behavior. Society of Petroleum Engineers. doi:10.2118/9901-MS.
Miller, C. C., Dyes, A. B., & Hutchinson, C. A. (1950). The Estimation of Permeability and Reservoir Pressure from Bottom Hole Pressure Build-Up Characteristics. Society of Petroleum Engineers. doi:10.2118/950091-G.
Mohaghegh, S., Arefi, R., Ameri, S., & Rose, D. (1995). Design and Development of An Artificial Neural Network for Estimation of Formation Permeability. Society of Petroleum Engineers. doi:10.2118/28237-PA.
Muskat, M. (1937). Use of Data Oil the Build-up of Bottom-hole Pressures. Society of Petroleum Engineers. doi:10.2118/937044-G.
Poe, B., & Varma, G. (2016). Novel Methodology to Estimate Reservoir Pressure and Productivity Index in Unconventional and Conventional Reservoirs Using Production Data. Offshore Technology Conference. doi:10.4043/26429.
Popa, A. S., & Patel, A. N. (2012). Neural Networks for Production Curve Pattern Recognition Applied to Cyclic Steam Optimization in Diatomite Reservoirs. Society of Petroleum Engineers. doi:10.2118/153185-MS.
Popa, A. S., O'Toole, C., Munoz, J., Cassidy, S., Tubbs, D., & Ershaghi, I. (2017). A Neural Network Approach for Modeling Water Distribution System. Society of Petroleum Engineers. doi:10.2118/185678-MS.
Raghavan, R. (1980). The Effect of Producing Time on Type Curve Analysis. Society of Petroleum Engineers. doi:10.2118/6997-PA.
Soliman, M. Y. (1986). Analysis of Buildup Tests with Short Producing Time. Society of Petroleum Engineers. doi:10.2118/11083-PA.