Artificial Intelligence Based Estimation of Water Saturation Using Electrical Measurements Data in a Carbonate Reservoir

2015 ◽  
Author(s):  
B.S. Bageri ◽  
F.A. Anifowose ◽  
A. Abdulraheem
Keyword(s):  
Artificial Intelligence ◽  
Water Saturation ◽  
Carbonate Reservoir ◽  
Electrical Measurements

Artificial Intelligence Used to Evaluate 23 Single-Well Surfactant-Soak Treatments

2006 ◽  
Vol 9 (03) ◽  
pp. 209-216 ◽  
Author(s):  
William W. Weiss ◽  
Xina Xie ◽  
Jason Weiss ◽  
Vishu Subramanian ◽  
Archie R. Taylor ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Field Test ◽  
Water Saturation ◽  
Field Tests ◽  
Recovery Process ◽  
Carbonate Reservoir ◽  
Reservoir Rock ◽  
Wettability Alteration ◽  
Single Well ◽  
Phosphoria Formation

Summary Following a series of laboratory imbibition-cell experiments, field tests were conducted to determine the effectiveness of surfactant-soak treatments as a single-well enhanced-oil-recovery (EOR) technique. The tests were conducted in the dolomite interval of the Phosphoria formation. Artificial intelligence was applied to analyze the mixed test results. The analysis suggested that the gamma ray log can be used to predict results and that a minimum amount of surfactant is required to improve production. Introduction Water imbibition as a recovery process was tested in the Spraberry field during the 1950s (Elkins and Skov 1962, 1963). This early work was followed by a test of the process in Cottonwood Creek field during the 1960s (Willingham and McCaleb 1967). Around the time of these field tests, a patent was issued (Graham et al. 1957) that suggested surfactants could enhance the imbibition recovery process. A later patent (Stone et al. 1970) implied that a Spraberry field test was designed, but results were not reported. Forty years later, researchers (Spindler et al. 2000; Standnes and Austad 2000; Chen et al. 2000) returned to the subject of wettability alteration. One description of a field test of the surfactant-soak process has been published (Chen et al. 2000). A great deal of effort was expended during the 1970s and 1980s in designing systems and field testing surfactant fluids with ultralow interfacial tensions (IFTs) as a flooding EOR process. Maintaining the integrity of the chemical slug from the injection well to the producing wells was fraught with problems. However, slug-integrity problems are diminished in single-well EOR applications. Recent laboratory work focused on the easily performed and interpreted imbibition-cell experiments. These experiments (with and without surfactants) and the reported success of pressure pulsing at Cottonwood Creek prompted further laboratory testing with reservoir rock and fluids (Xie 2002; Xie et al. 2004). This recent work indicated that a nonionic surfactant could substantially increase recovery from Phosphoria wells in the Cottonwood Creek field. The shallow-shelf carbonate reservoir is characterized as a steeply dipping, algal reef of the Phosphoria formation producing sour, 27°API, black oil from a dolomitized interval. Thickness of the dolomite varies from 20 to 100 ft. The average porosity is ~10% with ~1.0 md matrix permeability. The connate-water saturation is ~10%. Pan American Petroleum reported the low-pressure and low-temperature reservoir to be naturally fractured and oil-wet (Willingham and McCaleb 1967). Their description was based on laboratory core studies. Tests performed in the 1990s generated U.S. Bureau of Mines (USBM) wettability values of -0.1, -0.12, -0.18, and -0.26. The Cottonwood Creek field is located in the Bighorn basin of Wyoming, as shown in Fig. 1, and is operated by Continental Resources Inc.

Simulation of Miscible Displacement in Full-Diameter Carbonate Cores

1982 ◽  
Vol 22 (05) ◽  
pp. 647-657 ◽  
Author(s):  
J.P. Batycky ◽  
B.B. Maini ◽  
D.B. Fisher
Keyword(s):  
Oil Recovery ◽  
Water Saturation ◽  
Accurate Determination ◽  
Miscible Displacement ◽  
Carbonate Reservoir ◽  
Core Material ◽  
Immiscible Fluid ◽  
Displacement Efficiency ◽  
Carbonate Cores ◽  
Capacitance Model

Abstract Miscible gas displacement data obtained from full-diameter carbonate reservoir cores have been fitted to a modified miscible flow dispersion-capacitance model. Starting with earlier approaches, we have synthesized an algorithm that provides rapid and accurate determination of the three parameters included in the model: the dispersion coefficient, the flowing fraction of displaceable volume, and the rate constant for mass transfer between flowing and stagnant volumes. Quality of fit is verified with a finite-difference simulation. The dependencies of the three parameters have been evaluated as functions of the displacement velocity and of the water saturation within four carbonate cores composed of various amounts of matrix, vug, and fracture porosity. Numerical simulation of a composite core made by stacking three of the individual cores has been compared with the experimental data. For comparison, an analysis of Berea sandstone gas displacement also has been provided. Although the sandstone displays a minor dependence of gas recovery on water saturation, we found that the carbonate cores are strongly affected by water content. Such behavior would not be measurable if small carbonate samples that can reflect only matrix properties were used. This study therefore represents a significant assessment of the dispersion-capacitance model for carbonate cores and its ability to reflect changes in pore interconnectivity that accompany water saturation alteration. Introduction Miscible displacement processes are used widely in various aspects of oil recovery. A solvent slug injected into a reservoir can be used to displace miscibly either oil or gas. The necessary slug size is determined by the rate at which deterioration can occur as the slug is Another commonly used miscible process involves addition of a small slug within the injected fluids or gases to determine the nature and extent of inter well communication. The quantity of tracer material used is dictated by analytical detection capabilities and by an understanding of the miscible displacement properties of the reservoir. We can develop such understanding by performing one-dimensional (1D) step-change miscible displacement experiments within the laboratory with selected reservoir core material. The effluent profiles derived from the experiments then are fitted to a suitable mathematical model to express the behavior of each rock type through the use of a relatively small number of parameters. This paper illustrates the efficient application of the three-parameter, dispersion-capacitance model. Its application previously has been limited to use with small homogeneous plugs normally composed of intergranular and intencrystalline porosity, and its suitability for use with cores displaying macroscopic heterogeneity has been questioned. Consequently, in addition to illustrating its use with a homogeneous sandstone, we fit data derived from previously reported full-diameter carbonate cores. As noted earlier, these cores were heterogeneous, and each of them displayed different dual or multiple types of porosity characteristic of vugular and fractured carbonate rocks. Dispersion-Capacitance Model The displacement efficiency of one fluid by a second immiscible fluid within a porous medium depends on the complexity of rock and fluid properties. SPEJ P. 647^

Real-Time EM Look-Ahead Resistivity for Mapping of Oil/Water Contact While Drilling at Low Deviated Well, New Perspective for Mature Oil Fields Development: A Case Study Of Umm Gudair Field, Kuwait

2021 ◽  
Author(s):  
Nasser Faisal Al-Khalifa ◽  
Mohammed Farouk Hassan ◽  
Deepak Joshi ◽  
Asheshwar Tiwary ◽  
Ihsan Taufik Pasaribu ◽  
...  
Keyword(s):  
Water Saturation ◽  
High Water ◽  
Carbonate Reservoir ◽  
Water Contact ◽  
Saturation Zone ◽  
Look Ahead ◽  
Production History ◽  
Oil Water ◽  
High Water Cut ◽  
Water Cut

Abstract The Umm Gudair (UG) Field is a carbonate reservoir of West Kuwait with more than 57 years of production history. The average water cut of the field reached closed to 60 percent due to a long history of production and regulating drawdown in a different part of the field, consequentially undulating the current oil/water contact (COWC). As a result, there is high uncertainty of the current oil/water contact (COWC) that impacts the drilling strategy in the field. The typical approach used to develop the field in the lower part of carbonate is to drill deviated wells to original oil/water contact (OOWC) to know the saturation profile and later cement back up to above the high-water saturation zone and then perforate with standoff. This method has not shown encouraging results, and a high water cut presence remains. An innovative solution is required with a technology that can give a proactive approach while drilling to indicate approaching current oil/water contact and geo-stop drilling to give optimal standoff between the bit and the detected water contact (COWC). Recent development of electromagnetic (EM) look-ahead resistivity technology was considered and first implemented in the Umm Gudair (UG) Field. It is an electromagnetic-based signal that can detect the resistivity features ahead of the bit while drilling and enables proactive decisions to reduce drilling and geological or reservoir risks related to the well placement challenges.

Artificial Intelligence Coreflooding Simulator for Special Core Data Analysis

2021 ◽  
pp. 1-29
Author(s):  
Eric Sonny Mathew ◽  
Moussa Tembely ◽  
Waleed AlAmeri ◽  
Emad W. Al-Shalabi ◽  
Abdul Ravoof Shaik
Keyword(s):  
Artificial Intelligence ◽  
Steady State ◽  
History Matching ◽  
Water Saturation ◽  
Flow Behavior ◽  
Model Performance ◽  
Analysis Data ◽  
Coefficient Of Determination ◽  
Water Drainage ◽  
Data Set

Two of the most critical properties for multiphase flow in a reservoir are relative permeability (Kr) and capillary pressure (Pc). To determine these parameters, careful interpretation of coreflooding and centrifuge experiments is necessary. In this work, a machine learning (ML) technique was incorporated to assist in the determination of these parameters quickly and synchronously for steady-state drainage coreflooding experiments. A state-of-the-art framework was developed in which a large database of Kr and Pc curves was generated based on existing mathematical models. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from the corefloods including pressure drop and water saturation profile, along with other conventional core analysis data, were fed as features into the ML model. The entire data set was split into 70% for training, 15% for validation, and the remaining 15% for the blind testing of the model. The 70% of the data set for training teaches the model to capture fluid flow behavior inside the core, and then 15% of the data set was used to validate the trained model and to optimize the hyperparameters of the ML algorithm. The remaining 15% of the data set was used for testing the model and assessing the model performance scores. In addition, K-fold split technique was used to split the 15% testing data set to provide an unbiased estimate of the final model performance. The trained/tested model was thereby used to estimate Kr and Pc curves based on available experimental results. The values of the coefficient of determination (R2) were used to assess the accuracy and efficiency of the developed model. The respective crossplots indicate that the model is capable of making accurate predictions with an error percentage of less than 2% on history matching experimental data. This implies that the artificial-intelligence- (AI-) based model is capable of determining Kr and Pc curves. The present work could be an alternative approach to existing methods for interpreting Kr and Pc curves. In addition, the ML model can be adapted to produce results that include multiple options for Kr and Pc curves from which the best solution can be determined using engineering judgment. This is unlike solutions from some of the existing commercial codes, which usually provide only a single solution. The model currently focuses on the prediction of Kr and Pc curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

Prediction and Optimization of WAG Flooding by Using LSTM Neural Network Model in Middle East Carbonate Reservoir

2021 ◽  
Author(s):  
Ruijie Huang ◽  
Chenji Wei ◽  
Baozhu Li ◽  
Jian Yang ◽  
Suwei Wu ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Numerical Simulation ◽  
Short Term Memory ◽  
Oil Production ◽  
Simulation Method ◽  
Analysis Data ◽  
Carbonate Reservoir ◽  
Parameters Optimization ◽  
Model Based

Abstract Production prediction continues to play an increasingly significant role in reservoir development adjustment and optimization, especially in water-alternating-gas (WAG) flooding. As artificial intelligence continues to develop, data-driven machine learning method can establish a robust model based on massive data to clarify development risks and challenges, predict development dynamic characteristics in advance. This study gathers over 15 years actual data from targeted carbonate reservoir and establishes a robust Long Short-Term Memory (LSTM) neural network prediction model based on correlation analysis, data cleaning, feature variables selection, hyper-parameters optimization and model evaluation to forecast oil production, gas-oil ratio (GOR), and water cut (WC) of WAG flooding. In comparison to traditional reservoir numerical simulation (RNS), LSTM neural networks have a huge advantage in terms of computational efficiency and prediction accuracy. The calculation time of LSTM method is 864% less than reservoir numerical simulation method, while prediction error of LSTM method is 261% less than RNS method. We classify producers into three types based on the prediction results and propose optimization measures aimed at the risks and challenges they faced. Field implementation indicates promising outcome with better reservoir support, lower GOR, lower WC, and stabler oil production. This study provides a novel direction for application of artificial intelligence in WAG flooding development and optimization.

scholarly journals Joint Acoustic and Electrical Measurements for Unfrozen Water Saturation Estimate—A Review

2019 ◽  
Author(s):  
C. Lyu ◽  
S. A. Ghoreishian Amiri ◽  
H. Gao ◽  
T. Ingeman-Nielsen ◽  
G. Grimstad
Keyword(s):  
Water Saturation ◽  
Unfrozen Water ◽  
Electrical Measurements

scholarly journals 3D Geostatistical Modeling and Uncertainty Analysis in a Carbonate Reservoir, SW Iran

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Mohammad Reza Kamali ◽  
Azadeh Omidvar ◽  
Ezatallah Kazemzadeh
Keyword(s):  
Uncertainty Analysis ◽  
Stochastic Models ◽  
Reservoir Characterization ◽  
Water Saturation ◽  
Estimation Error ◽  
Sensitivity Study ◽  
Carbonate Reservoir ◽  
Sequential Gaussian Simulation ◽  
Sarvak Formation ◽  
Geostatistical Methods

The aim of geostatistical reservoir characterization is to utilize wide variety of data, in different scales and accuracies, to construct reservoir models which are able to represent geological heterogeneities and also quantifying uncertainties by producing numbers of equiprobable models. Since all geostatistical methods used in estimation of reservoir parameters are inaccurate, modeling of “estimation error” in form of uncertainty analysis is very important. In this paper, the definition of Sequential Gaussian Simulation has been reviewed and construction of stochastic models based on it has been discussed. Subsequently ranking and uncertainty quantification of those stochastically populated equiprobable models and sensitivity study of modeled properties have been presented. Consequently, the application of sensitivity analysis on stochastic models of reservoir horizons, petrophysical properties, and stochastic oil-water contacts, also their effect on reserve, clearly shows any alteration in the reservoir geometry has significant effect on the oil in place. The studied reservoir is located at carbonate sequences of Sarvak Formation, Zagros, Iran; it comprises three layers. The first one which is located beneath the cap rock contains the largest portion of the reserve and other layers just hold little oil. Simulations show that average porosity and water saturation of the reservoir is about 20% and 52%, respectively.

Modeling Original Water Saturation in the Transition Zone of a Carbonate Oil Reservoir

2006 ◽  
Vol 9 (06) ◽  
pp. 681-687 ◽  
Author(s):  
Shawket G. Ghedan ◽  
Bertrand M. Thiebot ◽  
Douglas A. Boyd
Keyword(s):  
Simulation Model ◽  
Transition Zone ◽  
Water Saturation ◽  
Carbonate Reservoir ◽  
Reservoir Rock ◽  
High Porosity ◽  
Height Functions ◽  
Transition Zones ◽  
Irreducible Water Saturation ◽  
Original Water

Summary Accurately modeling water-saturation variation in transition zones is important to reservoir simulation for predicting recoverable oil and guiding field-development plans. The large transition zone of a heterogeneous Middle East reservoir was challenging to model. Core-calibrated, log-derived water saturations were used to generate saturation-height-function groups for nine reservoir-rock types. To match the large span of log water saturation (Sw) in the transition zone from the free-water level (FWL) to minimum Sw high in the oil column, three saturation-height functions per rock type (RT) were developed, one each for the low-, medium-, and high-porosity range. Though developed on a different scale from the simulation-model cells, the saturation profiles generated are a good statistical match to the wireline-log-interpreted Sw, and bulk volume of water (BVW) and fluid volumetrics agree with the geological model. RT-guided saturation-height functions proved a good method for modeling water saturation in the simulation model. The technique emphasizes the importance of oil/brine capillary pressures measured under reservoir conditions and of collecting an adequate number of Archie saturation and cementation exponents to reduce uncertainties in well-log interpretation. Introduction The heterogeneous carbonate reservoir in this study is composed of both limestone and dolomite layers frequently separated by non-reservoir anhydrite layers (Ghedan et al. 2002). Because of its heterogeneity, this reservoir, like other carbonate reservoirs, contains long saturation-transition zones of significant sizes. Transition zones are conventionally defined as that part of the reservoir between the FWL and the level at which water saturation reaches a minimum near-constant (irreducible water saturation, Swirr) high in the reservoir (Masalmeh 2000). For the purpose of this paper, however, we define transition zones as those parts of the reservoir between the FWL and the dry-oil limit (DOL), where both water and oil are mobile irrespective of the saturation level. Both water and oil are mobile in the transition zone, while only oil is mobile above the transition zone. By either definition, the oil/water transition zone contains a sizable part of this field's oil in place. Predicting the amount of recoverable oil in a transition zone through simulation depends on (among other things) the distribution of initial oil saturation as a function of depth as well as the mobility of the oil in these zones (Masalmeh 2000). Therefore, the characterization of transition zones in terms of original water and oil distribution has a potentially large effect on reservoir recoverable reserves and, in turn, reservoir economics.

Sign in / Sign up

Export Citation Format

Share Document