Using Karhunen–Loéve decomposition and artificial neural network to model miscible fluid displacement in porous media

Abstract In this paper, we describe an approach to model fluid displacements in porous media that combines two powerful techniques, namely Karhunen–Loeve (KL) decomposition and artificial neural networks (ANNs). The KL decomposition, for data compression and feature identification, is used to extract coherent structures or eigenfunctions using fluid concentration maps obtained from fine-mesh numerical simulations of miscible fluid displacements of oil by solvent in a two-dimensional vertical cross-section. Twenty KL eigenfunctions that capture 98.8% of the total energy are extracted. Corresponding data coefficients are constructed by projecting the fluid concentration maps of the numerical simulations onto the KL eigenfunctions. Processing these data coefficients through an ANN is found to be a powerful tool in predicting the fluid displacements of the fine-mesh numerical simulations without actually performing these simulations.

[1]  E. J. Peters,et al.  A stability theory for miscible displacement , 1984 .

[2]  Ekwere J. Peters,et al.  A Microcomputer-Based Imaging System for the Visualization of Fluid Displacements , 1990 .

[3]  T. M. Geffen,et al.  A Laboratory Study of Solvent Flooding , 1957 .

[4]  V. A. Krasil’nikov,et al.  Atmospheric turbulence and radio-wave propagation , 1962 .

[5]  V. Ralph Algazi,et al.  On the optimality of the Karhunen-Loève expansion (Corresp.) , 1969, IEEE Trans. Inf. Theory.

[6]  C. S. Matthews,et al.  Sweep Efficiency by Miscible Displacement in a Five-Spot , 1966 .

[7]  Nejib Smaoui,et al.  Artificial neural network-based low-dimensional model for spatio-temporally varying cellular flames , 1997 .

[8]  L. Sirovich.  Turbulence and the dynamics of coherent structures. I. Coherent structures , 1987 .

[9]  E. J. Peters,et al.  On scaling immiscible displacements in permeable media , 1993 .

[10]  K. S. Lee,et al.  Areal Sweep Efficiency of Pseudoplastic Fluids in a Five-Spot Hele-Shaw Model , 1968 .

[11]  Ridha Gharbi,et al.  Scaling coreflood experiments to heterogeneous reservoirs , 1993 .

[12]  Ridha Gharbi,et al.  Prediction of Frictional Drag and Transmission of Slack-off Force in Horizontal Wells Using Neural Networks , 1998 .

[13]  E. J. Peters,et al.  Characterization of heterogeneities in permeable media with computed tomography imaging , 1992 .

[14]  J. W. Gardner,et al.  An Investigation of Phase Behavior-Macroscopic Bypassing Interaction in CO2 Flooding , 1984 .

[15]  A. Hansen,et al.  Aerodynamics of Horizontal-Axis Wind Turbines , 1993 .

[16]  Athanasios Papoulis,et al.  Probability, Random Variables and Stochastic Processes , 1965 .

[17]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[18]  N. Smaoui,et al.  Application of Artificial Neural Network for Estimating Tight Gas Sand Intrinsic Permeability , 1996 .

[19]  U. G. Araktingi,et al.  Viscous Fingering, Gravity Segregation, and Reservoir Heterogeneity in Miscible Displacements in Vertical Cross Sections , 1990 .

[20]  E. Lorenz.  Deterministic nonperiodic flow , 1963 .

[21]  Christie,et al.  Detailed Simulation of Unstable Processes in Miscible Flooding , 1987 .

[22]  Ann Muggeridge,et al.  3D Simulation of Viscous Fingering and WAG Schemes , 1993 .

[23]  E. J. Peters,et al.  Visualization of fluid displacements in porous media using computed tomography imaging , 1990 .

[24]  C. A. Andrews,et al.  Adaptive data compression , 1967 .

[25]  David V. Boger,et al.  The Influence of Rheological Properties on Mobility Control in Polymer-Augmented Waterflooding , 1988 .

[26]  Mary F. Wheeler,et al.  Simulation of miscible viscous fingering using a modified method of characteristics: effects of gravity and heterogeneity , 1989 .

[27]  J. M. Dumore,et al.  Stability Considerations in Downward Miscible Displacements , 1964 .

[28]  I. Jolliffe.  Principal Component Analysis , 2002 .

[29]  Nejib Smaoui,et al.  A new approach combining Karhunen-Loéve decomposition and artificial neural network for estimating tight gas sand permeability , 1997 .

[30]  G. Croes,et al.  Dimensionally Scaled Experiments and the Theories on the Water-Drive Process , 1955 .

[31]  J. Todd.  Book Review: Digital image processing (second edition). By R. C. Gonzalez and P. Wintz, Addison-Wesley, 1987. 503 pp. Price: £29.95. (ISBN 0-201-11026-1) , 1988 .

[32]  Ridha Gharbi,et al.  Neural Network Model for Estimating The PVT Properties of Middle East Crude Oils , 1996 .

[33]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[34]  U. G. Araktingi,et al.  Viscous Fingering in Heterogeneous Porous Media , 1993 .

[35]  Ali Elkamel,et al.  An artificial neural network for the prediction of immiscible flood performance , 1995 .

[36]  B. Habermann.  The Efficiency of Miscible Displacement as a Function of Mobility Ratio , 1960 .

[37]  Michael Gorman,et al.  Cellular pattern formation in circular domains. , 1997, Chaos.

[38]  George M. Homsy,et al.  Viscous fingering in porous media , 1987 .

[39]  P. Holmes,et al.  The Proper Orthogonal Decomposition in the Analysis of Turbulent Flows , 1993 .

[40]  R. Giordano,et al.  The Effects of Permeability Variations on Flow in Porous Media , 1985 .

[41]  R. J. Blackwell,et al.  Factors Influencing the Efficiency of Miscible Displacement , 1959 .

[42]  P. van Meurs,et al.  The Instability of Slow, Immiscible, Viscous Liquid-Liquid Displacements in Permeable Media , 1959 .

[43]  M. Christie.  High-Resolution Simulation of Unstable Flows in Porous Media , 1989 .

[44]  Dieter Armbruster,et al.  Analyzing the dynamics of cellular flames , 1996 .

[45]  E. J. Peters,et al.  Scaling miscible fluid displacements in porous media , 1998 .