Immiscible Displacement Of Oil Research Articles

CO2-Enhanced Radial Borehole Development of Shale Oil: Production Simulation and Parameter Analysis

Shale oil resources, noted for their broad distribution and significant reserves, are increasingly recognized as vital supplements to traditional oil resources. In response to the high fracturing costs and swift decline in productivity associated with shale oil horizontal wells, this research introduces a novel approach utilizing CO2 for enhanced shale oil recovery in radial boreholes. A compositional numerical simulation method is built accounted for component diffusion, adsorption, and non-Darcy flow, to explore the viability of this technique. The study examines how different factors—such as initial reservoir pressure, permeability, numbers of radial boreholes, and their branching patterns—influence oil production and CO2 storage. Our principal conclusions indicate that with a constant CO2 injection rate, lower initial reservoir pressures predominantly lead to immiscible oil displacement, hastening the occurrence of CO2 gas channeling. Therefore, maintaining higher initial or injection pressures is critical for effective miscible displacement in CO2-enhanced recovery using radial boreholes. Notably, the adsorption of CO2 in shale oil results in the displacement of lighter hydrocarbons, an effect amplified by competitive adsorption. While CO2 diffusion tends to prompt earlier gas channeling, its migration towards areas of lower concentration within the reservoir reduces the extent of channeling CO2. Nonetheless, when reservoir permeability falls below 0.01 mD, the yield from CO2-enhanced recovery using radial boreholes is markedly low. Hence, selecting high-permeability “sweet spot” regions within shale oil reservoirs for the deployment of this method is advisable. To boost oil production, utilizing longer and broader radial boreholes, increasing the number of boreholes, or setting the phase angle to 0° are effective strategies. Finally, by comparing the production of shale oil enhanced by CO2 with that of a dual horizontal well fracturing system enhanced by CO2, it was found that although the former’s oil production is only 50.6% of the latter, its cost is merely 11.1%, thereby proving its economic viability. These findings present a new perspective for the economically efficient extraction of shale oil, offering potential guidance for industrial practices.

Effect of Initial Water Saturation on Oil Displacement Efficiency by Nanosuspensions

This article deals with the study of the initial water saturation effect of a porous medium on the oil recovery factor using a water-based nanosuspension. The initial water saturation of the porous medium in the computations varied within the range from 0 to 90%. The nanoparticle SiO2 concentration varied from 0 to 1 wt%. The particle sizes were equal to 5, 18, 22, and 50 nm. Experimentally measured wetting angles and the interfacial tension coefficient depending on the concentration and size of nanoparticles were used in computations. A mathematical model was developed, describing the transfer and diffusion of nanoparticles within the aqueous phase during immiscible displacement of oil by nanosuspension from a porous medium. Using the developed model, a systematic computational study of the effect of the initial water saturation of the core micromodel on the oil recovery factor using nanosuspension was carried out. It was revealed that with an increase in the initial water saturation, the oil recovery factor monotonically decreased in the case of displacement both by water and nanosuspension. It was shown that with an increase in the concentration of nanoparticles and a decrease in their size, the oil recovery factor increased. At that, the relative increase in the recovery factor had a maximum at an initial water saturation equal to 60%.

Multi-scale flow patterns during immiscible displacement of oil by water in a layer-inhomogeneous porous media

This paper presents the results of numerical study of the relationship between micro-and macroscale flows during immiscible displacement in a two-layer porous medium. A feature of the proposed approach is the allowance for large-scale capillarity induced flow due to curvature of the displacement front in macro-inhomogeneous porous medium. The physical mechanisms determining the development of viscous instability in a layer-inhomogeneous porous medium are considered, the methods for suppressing viscous fingers formation based on the stabilization of the displacement front due the action of capillary forces are proposed.

Mechanistic study of the effects of dynamic fluid/fluid and fluid/rock interactions during immiscible displacement of oil in porous media by low salinity water: Direct numerical simulation

Low salinity waterflooding (LSWF) is a process in which by lowering the ionic strength and/or manipulation of the composition of the injection water, the long term equilibrium in oil/brine/rock system is disturbed to reach a new state of equilibrium through which the oil production will be enhanced due to fluid/fluid and/or rock/fluid interactions. In spite of recent advances in the simulation of the LSWF at core scale and beyond, there are very few works that have modelled and simulated this process at the pore scale specially using direct numerical simulation (DNS). As a result the effects of wettability alteration and/or Interfacial Tension (IFT) change on the distribution of the phases at pore scale, as well as dynamics and mechanisms of the oil displacements in porous media are neither thoroughly investigated nor well understood. With this objective, the present study takes into account modelling both rock/fluid (dynamic contact angle) and fluid/fluid (dynamic oil/water IFT as well as diffusion between high salinity and low salinity water) interactions. Additionally, the proposed model is capable to effectively capture the time scale pertinent in the wettability alteration by LSWF via reaction rate and near solid surface diffusion coefficients. The model is developed and incorporated into OpenFOAM and both the Navier-Stokes equation for oil/water two-phase flow and the advection-diffusion equation for ion transport are solved. The developed model is validated against one dimensional (1D) sinusoidal micromodel experiments reported in the literature, and then applied to two dimensional (2D) heterogeneous micromodel to investigate the sole effect of wettability alteration as well as its coupled effect with IFT variations. Different degrees of contact angle alteration, different trends of IFT variations reported in the literature, as well as different injection scenarios (secondary or tertiary) are considered. 1D sinusoidal micromodel simulations visualize a dominant dynamic recovery mechanism which boosts the low salinity effect (LSE) via coalescence of the detached or partially detached residual oil blobs which forms a large oil ganglion towards the downstream and can effectively produce the residual oil saturation at shorter period of time compared to the case if such a coalescence didn't happen. The sensitivity analysis in 2D heterogeneous micromodel shows that the performance of the LSWF is a function of the degree of wettability alteration as well as IFT variations. Although the IFT decreasing trend with salinity can enhance the oil production through synergetic effect, the IFT increasing trend has a detrimental effect on the oil production and surpasses the effectiveness of wettability alteration interactions. The results confirm the importance of fluid/fluid interactions such as IFT variation on the LSE which has been previously ignored in numerical simulation LSWF altogether. The presented simulations shed the lights to the reasons behinds some of the discrepancies reported in the literature.

Similitude Analysis of Experiment and Modelling of Immiscible Displacement Effects with Scaling and Dimensional Approach

This paper presents the use of scaling and dimensional analysis to assess the viability of conventional modelling of immiscible displacement occurring when water is injected into the oil-saturated, porous rock—a conventional secondary oil-recovery method. A brief description of the laboratory tests of oil displacement with water performed on long core sets taken from wells operating on a Polish oil reservoir was presented. A dimensionless product generator based on dimensional analysis and Buckingham Π theorem was used to generate all possible combinatorial sets of dimensionless products for physical variables describing the phenomenon. The mathematical model of the phenomenon was transformed to its dimensionless form, using a selected set of the products. The results of the laboratory tests were analyzed as functions of the products. Statistically verified quantities describing both dependent and independent experiment variables were subject to a regression analysis to study dependencies of the experimental results upon selected dimensionless products. The degrees of the dependencies were determined and compared with the model coefficients. The conclusions are drawn for the purposes of model application to correctly describe the laboratory and, consequently, field scale processes of immiscible oil displacement by water.

Characterization of Viscous Fingering and Channeling for the Assessment of Polymer-Based Heavy Oil Displacements

The ability to determine a predictive stability criterion is of great practical importance for designing stable polymer-based displacements. Where one usually resorts to a limited number of core-scale experiments or coarse-scale reservoir simulations, the first ones are potentially impacted by length scale issues, while the second ones possibly smooth out sharp displacing fronts and physical instability due to numerical diffusion. This paper proposes a new hydrodynamical stability criterion based on the previous linear stability analysis results. This criterion is tested for 2D polymer oil displacement by performing high viscosity contrasts, high-resolution numerical experiments at pilot scale. We investigate mesh resolution issues and several perturbation ideas. Different factors are considered such as mobility ratios, polymer adsorption and degradation and heterogeneities. The analysis is based on a combination of reservoir simulation and image processing techniques. We show the development of viscous fingering in homogeneous porous media is driven by the shock mobility ratio defined as the ratio of the total fluids upstream mobility over the total fluids downstream mobility. This stability criterion proves to predict both the polymer upstream and polymer-free downstream saturation fronts stability, typical of a polymer displacement, whether polymer adsorbs on the rock or degradates, or not. The observed fingers dynamical behavior is in line with previous works addressing single-phase miscible flow or immiscible oil displacement in porous media: fingers transversally merge while growing in the flow direction. Time evolution of fingers spreading and number is linear. Investigation on porous media of variable heterogeneity distributions shows how viscous fingering couples with heterogeneity and leads to even more marked, distorted and unstable flow patterns. In those cases, flow patterns are not solely driven by the porous medium heterogeneity. The more unstable the flow is, the more sensitive it is to heterogeneity. In-depth fingers analysis shows a very specific time evolution behavior, quite different from viscous fingering in homogeneous media. Such a flow pattern is related to production data such as water and polymer breakthrough times and/or oil recovery profiles as a function of time, which can be used in turn to interpret displacement stability and porous medium heterogeneity features.

Immiscible fluid displacement in a porous media: Effect of surfactants introduced ab initio versus surfactants formed in-situ

Experiments were performed to study the immiscible displacement of oil from a capillary tube using an aqueous phase fluid. One set of experiments were performed where surfactant was introduced into the aqueous phase liquid at concentrations below the critical micellar concentration prior to displacement, i.e. ab initio. In a second set of experiments surfactant was formed at the interface in-situ via a saponification chemical reaction. For both experiment conditions we measured surface tension using the pendant drop method to estimate adsorption and desorption Biot numbers for the ab initio case; whereas for surfactant produced via chemical reaction this data provided an estimate for rates of change in surface tension that were used to estimate a Damkohler number. The results suggest that surfactants created via saponification reaction tend to have an effect on the interface and film thickness that is entirely absent in non-reactive immiscible displacement experiments.

The Dynamics of Nanoparticle-enhanced Fluid Displacement in Porous Media - A Pore-scale Study

This work provides new insights into the dynamics of silica nanoparticle-based removal of organic fluids (here oil) from naturally occurring porous media. We have used 4D (time-resolved 3D) imaging at pore-scale using X-ray computed micro-tomography (μCT) technique. The captured 3D tomographic time-series data reveal the dynamics of immiscible oil displacement from a carbonate rock upon injection of nanoparticle (NP) suspensions (0.06 and 0.12 wt% SiO2 in deionised water). Our analysis shows significant pore-scale remobilisation of initially trapped oil upon injection of the NP suspensions, specifically, at higher concentration. Our data shows that oil clusters become significantly smaller with larger fluid/fluid interface as a result of the higher concentration NP injection. This paper demonstrates that use of 2D radiograms collected during fluid injections allows monitoring flow dynamics at time resolutions down to a few seconds using conventional laboratory-based μCT scanners. Here, as an underlying mechanism for oil remobilisation, we present the first 4D evidence of in-situ formation of an oil in water emulsion induced by nanoparticles.

Relevance of analytical Buckley\u2013Leverett solution for immiscible oil displacement by various gases

To generate the valid numerical simulation model, the sufficient amount of gathered data from the oil field is required. However, it is not always possible to acquire such data at the initial stage of project development. Buckley and Leverett (Pet Trans AIME 146(01):107–116, 1942) developed the analytical solution allowing to easily assess the oil displacement efficiency. One of the main assumptions of this model is incompressibility of oil and injected fluid. For slightly compressible water and oil such assumption is rational. However, that is not always the case when the gas is injected. This research aims to identify the conditions at which the usage of the incompressible gas model is appropriate. Likewise, the cases when the model of compressible gas is required are also evaluated. To accomplish the goals of this research, the comparative analysis between the injection of compressible and incompressible gases was undertaken using the numerical solution of the correspondent reservoir engineering problems. The validation of the numerical model was performed showing that it matches the analytical Buckley–Leverett solution. The findings of this research indicate that the relative and absolute density change with the pressure of the injected gas has the profound impact on the convergence between two models under consideration. With the increase in the injection pressure, the discrepancy between the models of compressible and incompressible gas raises for all the considered injection fluids (CO_2, CH_4 and N_2). Due to a steep slope of density–pressure curve for CO_2 at low initial reservoir pressure, the incompressible model cannot accurately predict the oil displacement efficiency by this gas at any reasonable injection pressure. All one-dimensional results are also representative for two-dimensional simulations (2D). However, the mismatch between two models increases considerably for 2D simulation scenarios. This study might be beneficial for those considering or researching the possibility of immiscible gas flooding by various gases at the particular oil field. Knowing some basic reservoir and technological parameters, the presented results might be used as simple screening criteria allowing to estimate the relevance of analytical Buckley–Leverett solution.

A New Analytical Model for Developing Fractional Flow Curve Using Production Data

The immiscible displacement of oil by water through a porous and permeable reservoir rock can be described by the use of a fractional flow curves (fw versus Sw). Water flooding project parameters can be obtained from the fractional flow curve. However, developing a representative fractional flow curve for a specific reservoir can be quite challenging when fluid and special core analysis data is limited or compromised. Hence, a mathematical model for dependence of fw on Swis developed by solving material balance algorithm using production data. The results of the model were compared with forecasts from the conventional Bucklett Leverett fractional flow equation and Corey’s correlation and were found to be favorable with less time and effort.

Immiscible displacement of oil by water in a microchannel: Asymmetric flow behavior and nonlinear stability analysis of core-annular flow

The immiscible displacement of oil by water in a circular microchannel was investigated. A fused silica microchannel with an inner diameter of 250 μm and a length of 7 cm was initially filled with a viscous silicone oil. Only water then was injected into the channel. We describe our flow observations based on the two-dimensional images captured in the middle of the channel. The water finger displaced the oil and left an oil film on the channel wall. While the oil was being displaced at the core, the flow resistance decreased, which resulted in increases in water flow rate and inertia. Eventually, the water finger reached the channel exit and formed a core-annular flow pattern. The wavelength of the waves formed at the oil-water interface also increased with the increase in inertia. The initially symmetric interfacial waves became asymmetric with time. Also, the water core shifted from the center of the channel and left a thinner oil film on one side of the microchannel. Under all flow rates tested in this study, as long as the water was continuously injected, the water core was stable and no breakup into droplets was observed. We also discuss the flow stability based on nonlinear and linear stability analyses performed on the core-annular flow. Compared to the linear analysis, which ignores the inertia effects, the nonlinear analysis, which includes the inertia effects, predicts longer interfacial wavelengths by a factor of 1/sqrt[1-a(o)/2(We(w) + We(o)a(o)(2)/1-a(o)(2))] where We(w) and We(o) are the Weber numbers of the water and the oil phases, respectively, and a(o) is the unperturbed water core radius made dimensionless by the channel radius.

SPH simulation of oil displacement in cavity-fracture structures

This paper presents a study of the immiscible displacement of oil by water in cavity-fracture structures using smoothed particle hydrodynamics (SPH). The surface tension and wetting behavior are incorporated into the equation of motion, and pseudo periodic boundary conditions are applied. As for “middle-fractured” structure, it is found that the ultimate oil recovery is almost determined by the height of fracture regardless of its orientation, and the result compares well with corresponding experiments. Besides, the water-wet wall is favorable to higher oil recovery. A systematic exploration is carried out on “upper-fractured” structure for the feasibility of gravity drainage, where a critical width of fracture is found, beyond which the oil in the cavity can be driven out. The possible development of SPH in this background for large-scale simulation is prospected finally.

Using wavelets to characterize the wettability of porous materials

Visualization experiments of rate-controlled immiscible displacement of oil by water are performed on a model porous medium of controlled fractional wettability, fabricated by mixing water-wet glass microspheres with strongly oil-wet polytetrafluoroethylene microspheres and packing them between two transparent glass plates. The growth pattern is video recorded and the transient response of the pressure drop across the pore network is measured for various fractions of oil-wet particles. The space-averaged capillary pressure coincides to the pressure drop measured across the porous medium. The oscillating transient signal of the capillary pressure is analyzed with multilevel wavelets to produce the best level wavelet details or best level capillary pressure spectrum (BLCPS) by minimizing the "entropy" of wavelet approximation. Invasion of water in oil-wet areas is reflected in high-frequency and low-amplitude fluctuations of the BLCPS. Correspondingly, invasion of water in water-wet areas is associated with low-frequency and high-amplitude fluctuations of the BLCPS. The displacement growth pattern is reflected in the "energy" and "frequency" of the BLCPS which along with the time-averaged capillary pressure are correlated with two parameters quantifying the spatial variation of wettability over the porous medium: the frontal wettability of the active interface of the fluids before each invasion step and the regional wettability of the area invaded by the displacing fluid.

Immiscible displacement of oil by water in consolidated porous media due to capillary imbibition under ultrasonic waves

Numerous studies done in the last four decades have demonstrated that acoustic stimulation may enhance recovery in oil reservoirs. This technology is not only technically feasible, but also serves as an economical, environmentally friendly alternative to currently accepted enhanced oil recovery (EOR) method. It requires low capital expenditure, and yields almost immediate improvement without any additional EOR agents. Despite a vast body of empirical and theoretical support, this method lacks sufficient understanding to make meaningful and consistent engineering predictions. This is in part due to the complex nature of the physical processes involved, as well as due to a shortage of fundamental/experimental research. Much of what the authors believe is happening within acoustically stimulated porous media is speculative and theoretical. This paper focuses on the effects of ultrasound on the interfacial forces between immiscible fluids. Capillary (spontaneous) imbibition of an aqueous phase into oil (or air)-saturated Berea sandstone and Indiana limestone samples experiments were conducted. Solutions of water, brine (15,000 and 150,000 ppm NaCl), anionic surfactant (sodium dodecyl diphenyloxide disulfonate), nonionic surfactant (alcohol ethoxylate) and polymer (xanthan gum) were prepared as the aqueous phase. Both counter-current and co-current geometries were tested. Due to the intrinsically unforced, gentle nature of the process, and their strong dependence on wettability, interfacial tension, viscosity and density, such experiments provide valuable insight into some of the governing mechanisms behind ultrasonic stimulation.

A node‐centred finite volume formulation for the solution of two‐phase flows in non‐homogeneous porous media

AbstractThe simulation of two‐phase flow of oil and water in inhomogeneous porous media represents a great challenge because rock properties such as porosity and permeability can change abruptly throughout the reservoir. This fact can produce velocities which vary several orders of magnitude within very short distances. The presence of complex geometrical features such as faults and deviated wells is quite common in reservoir modelling, and unstructured mesh procedures, such as finite elements (FE) and finite volume (FV) methods can offer advantages relative to standard finite differences (FD) due to their ability to deal with complex geometries and the easiness of incorporating mesh adaptation procedures. In fluid flow problems FV formulations are particularly attractive as they are naturally conservative in a local basis. In this paper, we present an unstructured edge‐based finite volume formulation which is used to solve the partial differential equations resulting from the modelling of the immiscible displacement of oil by water in inhomogeneous porous media. This FV formulation is similar to the edge‐based finite element formulation when linear triangular elements are employed. Flow equations are modelled using a fractional flux approach in a segregated manner through an IMplicit Pressure‐Explicit Saturation (IMPES) procedure. The elliptic pressure equation is solved using a two‐step approach and the hyperbolic saturation equation is approximated through an artificial diffusion method adapted for use on unstructured meshes. Some representative examples are shown in order to illustrate the potential of the method to solve fluid flows in porous media with highly discontinuous properties. Copyright © 2006 John Wiley & Sons, Ltd.

Immiscible displacement of fluids in permeable media in the presence of suspended particles

Immiscible liquid–liquid displacement in the presence of suspended particles in a permeable medium is considered, and the necessary and sufficient conditions for instability are obtained. It is found that the value of the critical wavelength decreases due to the presence of suspended particles, as compared to the no-particle case. Consequently, in the immiscible displacement of oil by water, the low recovery of oil in field reservoirs may be understood as being due to the presence of dust (or suspended) particles in the fluids. By incorporating the effects of suspended particles, as we do in the theory presented here, a better agreement is obtained between the calculated and observed wavelengths of maximum instability.

Effect of Nitrogen On the Solubility And Diffusivity of Carbon Dioxide Into Oil And Oil Recovery By the Immiscible WAG Process

Abstract In the immiscible displacement of oil by carbon dioxide gas, the solubility and diffusivity of carbon dioxide are important factors that determine the efficiency of the process, because an increase in the carbon dioxide solubility and diffusivity into oil leads to an increase in oil recovery. It is shown by experimental studies that the solubility and diffusivity of carbon dioxide into oil are governed by the saturation pressure, reservoir temperature, composition of the oil and purity of the gas. The solubility and diffusivity of carbon dioxide into Aberfeldy heavy oil were measured, using impure carbon dioxide gas containing nitrogen as the main contaminant gas. It was noted that increasing the concentration of nitrogen in the carbon dioxide stream decreased the solubility and diffusivity of carbon dioxide in oil, consequently leading to a reduction in the swelling of the oil by carbon dioxide. Displacement experiments were also conducted to observe the effect of using impure carbon dioxide in place of pure carbon dioxide in the immiscible displacement WAG process. It was noted that the presence of nitrogen in carbon dioxide adversely affected oil recovery by the process and that increasing the nitrogen concentration up to 30 mole% could result in 10% loss in oil recovery. Introduction The solubility of carbon dioxide is the most important effect in the immiscible displacement of oil by carbon dioxide gas since it was found by Rojas(1) that among other mechanisms, an increase in the carbon dioxide solubility in oil leads to an increase in oil recovery. This is true because the solubility of carbon dioxide greatly reduces the viscosity of the oil and promotes the swelling of the oil. Viscosity reduction and swelling of the oil lower the water-oil mobility ratio, consequently leading to an increased oil recovery. Early work in 1926 by Beecher and Parkhurst(2) showed that carbon dioxide was more soluble on a molar basis in a 30.2 °API oil than air and natural gas. Svreck and Mehrota's data(3) for carbon dioxide, methane and nitrogen showed that and Mehrotra's data(3), carbon dioxide is the most soluble and nitrogen the least soluble in bitumen. The solubility of carbon dioxide in oil is governed by the saturation pressure, reservoir temperature, composition of the oil and purity of the gas. Miller and Jones(4) and Chung, Jones, and Nguyen(5) measured the solubility of carbon dioxide in Canyon and Wilmington heavy oils and found that the solubility of carbon dioxide in heavy crude oils increased with pressure but decreased with temperature and reduced API gravity. Briggs and Puttagunta(6) reported sets of data for carbon dioxide solubility in Aberfeldy oil and swelling of oil at 20.6 °C. Their data showed that both carbon dioxide solubility and oil swelling increased when pressure increased. Later, Sayegh and Sarbar(7) established that carbon dioxide is more soluble in oil at lower temperatures than at higher ones.

Reactive transport and immiscible flow in geological media. II. Applications

The conceptual framework developed in Dagan & Cvetkovic (1996) is applied to spe­cific cases of flow and reactive transport in geological media. Two types of reactions are considered: Langmuir sorption and mineral dissolution. Two-phase immiscible displacement of oil by water (Buckley-Leverett flow) is also analysed. Both reactions and heterogeneity enhance the field-scale dispersive effects. The relative influence of the heterogeneity and reactions on the field-scale dispersion depends on the scale of the transport problem relative to the heterogeneity integral scale on the one hand, and the reaction parameters on the other. The dispersive effect due to sorption non-linearity may dominate over the effects of heterogeneity. Similarly, for heavier oil, i. e. for small water to oil viscosity ratio, the effect of nonlinearity in the two-phase im­miscible dynamics will generally dominate over the heterogeneity for large transport times. If the characteristic transport time, defined as the ratio between the reservoir scale and the flow velocity, is comparable to the heterogeneity characteristic time I/U , heterogeneous fingering and nonlinear two-phase dynamics yield comparable rates of dispersion.

A neural network prediction model of fluid displacements in porous media

This paper presents the development and design of an artificial neural network that is able to predict the breakthrough oil recovery of immiscible displacement of oil by water in a two-dimensional vertical cross section. The data used in training the neural network was obtained from the results of fine-mesh numerical simulations. Several network architectures were investigated and trained using the back propagation with momentum algorithm. The neural network that gave the best predictive performance was a two-hidden layer network with 8 neurons in the first hidden layer and 8 neurons in the second hidden layer. This network also performed well against a cross validation test. The reservoir simulation data used so far in the training process was for a homogeneous reservoir, the more general case is still under investigation.

An artificial neural network for the prediction of immiscible flood performance

Despite several decades of artificial neural network reserach in other engineering disciplines, only recently work has been reported on its use as a prediction tool in petroleum engineering applications. Existing methods for the prediction of fluid flow in porous medium include numerical simulation techniques and laboratory core flood experiments. Both of these methods are generally expensive and time consuming. However, neural networks, once successfully trained, can be used to predict reservoir performance in a short time with a personal computer. An artificial neural network was developed using data obtained from fine-mesh numerical simulation to predict the breakthrough oil recovery of immiscible displacement of oil by water in a two-dimensional vertical cross section. The network is able to predict the results of the fine-mesh numerical simulations without actually performing these simulation runs. Various neural network connections were investigated using the back-propagation with momentum algorithm for error minimization. This paper describes the design, development, and testing of the neural network.