Implicit Approximation of Neural Network and Applications
- Dao-lun Li (University of Science and Technology of China) | De-tang Lu (University of Science and Technology of China) | Wen-shu Zha (University of Science and Technology of China)
- Document ID
- Society of Petroleum Engineers
- SPE Reservoir Evaluation & Engineering
- Publication Date
- December 2009
- Document Type
- Journal Paper
- 921 - 928
- 2009. Society of Petroleum Engineers
- 1 in the last 30 days
- 603 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 10.00|
|SPE Non-Member Price:||USD 30.00|
It is common practice that one of the reservoir properties is recognized as a complex function of several interrelated factors in neural-network applications used in oil-reservoir studies. Few methods are based on one reservoir property being recognized as a function of time and the spatial locations, which means that the reservoir-property data can be described as a time vector series. It is a great challenge for the artificial neural network to describe a time vector series because the neural network is unable to approximate a multivariate vector function effectively. By combining the principle of implicit curves and surfaces with the neural network, we present a novel way to process the time vector series. The method includes the following steps: mapping data, constructing an explicit function, training the neural network, extracting the isoline, and inverse mapping.
This paper presents an application to predict the isotope-logging data in 2002 with the known data from 2001 and 2003.
|File Size||687 KB||Number of Pages||8|
Blane, M.M., Lei, Z., Civi, H., and Cooper, D.B. 2000. The 3L algorithm for fittingimplicit polynomials curves and surface to data. IEEE Transactions onPattern Analysis and Machine Intelligence 22 (3): 298-313.doi:10.1109/34.841760.
Carcenac, M. 2004. An Implicit Surface Modeling Technique Based on a ModularNeural Network Architecture. Turk J Elec Engin 12 (1):11-26.
Carcenac, M. and Acan, A. 2000. Modeling an Isosurface witha Neural Network. Proc., 8th Pacific Conference on Computer Graphicsand Applications (PG 2000), Hong Kong, 3-5 October, 165-174. doi:10.1109/PCCGA.2000.883938.
Cretu, A.-M., Petriu, E.M., and Patry, G.G. 2003. Neural NetworkArchitecture for 3D Object Representation. Proc, IEEE InternationalWorkshop on Haptic, Audio and Visual Environments and Their Applications (HAVE2003), Ottawa, Ontario, Canada, September, 31-36.
Frank, R.J., Davey, N., and Hunt, S.P. 2000. Input Window Size and NeuralNetwork Predictors. Proc., IEEE-INNS-ENNS International JointConference on Neural Networks (IJCNN 2000), Como, Italy, 24-27 July, Vol. 2,237-242. doi: 10.1109/IJCNN.2000.857903.
Helle, H.B., Bhatt, A., and Ursin, B. 2001. Porosity andpermeability prediction from wireline logs using artificial neural networks: aNorth Sea case study. Geophysical Prospecting 49 (4):431-444. doi:10.1046/j.1365-2478.2001.00271.x.
Keogh, E., Chu, S., Hart, D., and Pazzani, M.J. 2001. An Online Algorithmfor Segmenting Time Series. In Proceedings of the 2001 IEEE InternationalConference on Data Mining, 289-296. Washington, DC: IEEE ComputerSociety.
Li, D., Lu, D., Kong, X., and Wu, G. 2005. Implicit curves and surfacesbased on BP neural network. Journal of Information & ComputationalScience 2 (2): 259-271.
Lim, J.-S., Park, H.-J., and Kim, J. 2006. A New Neural Network Approach toReservoir Permeability Estimation From Well Logs. Paper SPE 100989presented at the SPE Asia Pacific Oil and Gas Conference and Exhibition,Adelaide, Australia, 11-13 September. doi: 10.2118/100989-MS.
Mohaghegh, S. 2000. Virtual-Intelligence Applications inPetroleum Engineering: Part 1--Neural Networks. J. Pet Tech 52 (9): 64-73. SPE-58046-MS. doi: 10.2118/58046-MS.
Mohaghegh, S.D. 2005. RecentDevelopments in Application of Artificial Intelligence in PetroleumEngineering. J. Pet Tech 57 (4): 86-91. SPE-89033-MS.doi: 10.2118/89033-MS.
Morse, B.S., Yoo, T.S., Rheingans, P., Chen, D.T., and Subramanian, K.R.2001. Interpolating Implicit Surfaces From Scattered Surface Data UsingCompactly Supported Radial Basis Functions. Proc., IEEE InternationalConference on Shape Modeling and Applications (SMI 2004), Genova, Italy, 7-11May, 89-98.
Park, S., Lee, D., and Chu, W.W. 1999. Fast Retrieval of SimilarSubsequences in Long Sequence Databases. Proc., 3rd IEEE Knowledge andData Engineering Exchange Workshop, Chicago, November 1999, 60-67.
Sang, H.L., Arun, K., and Datta-Gupta, A. 2002. Electrofacies Characterization andPermeability Predictions in Complex Reservoirs. SPE Res Eval &Eng 5 (3): 237-248. SPE-78662-PA. doi: 10.2118/78662-PA.
Savchenko, V.V., Pasko, A.A., Okunev, O.G., and Kunii, T.L. 1995. Function Representation ofSolids Reconstructed From Scattered Surface Points and Contours.Computer Graphics Forum 14 (4): 181-188.doi:10.1111/1467-8659.1440181.
Tang, H. and Ji, H. 2006. Incorporation of SpatialCharacteristics Into Volcanic Facies and Favorable Reservoir Prediction.SPE Res Eval & Eng 9 (4):565-573. SPE-90847-PA. doi:10.2118/90847-PA.
Taubin G., Cukierman, F., Sullivan, S., Ponce J., and Kriegman D.J. 1995. Parameterized Families ofPolynomials for Bounded Algebraic Curve and Surface Fitting. IEEETransactions on Pattern Analysis and Machine Intelligence 16(3): 287-303. doi: 10.1109/34.276128.
Taubin, G. 1991. Estimation ofplanar curves, surfaces and nonplanar space curves defined by implicitequations with applications to edge and range image segmentation. IEEETransactions on Pattern Analysis and Machine Intelligence 13(11):1115-1138. doi: 10.1109/34.103273.
Turk, G. and O'Brien, J.F. 1998. Variational Implicit Surfaces. TechnicalReport GIT-GVU-99-15, Georgia Institute of Technology, Atlanta, Georgia.
Yang, J., Rivard, H., and Zmeureanu, R. 2005. On-line building energyprediction using adaptive artificial neural networks. Energy andBuildings 37 (12): 1250-1259.doi:10.1016/j.enbuild.2005.02.005.