Water alternating gas (WAG) injection process is a proven EOR technology that has been successfully deployed in many fields around the globe. The performance of WAG process is measured by its incremental recovery factor over secondary recovery. The application of this technology remains limited due to the complexity of the WAG injection process which requires time-consuming in-depth technical studies. This research was performed for a purpose of developing a predictive model for WAG incremental recovery factor based on integrated approach that involves reservoir simulation and data mining. A thousand reservoir simulation models were developed to evaluate WAG injection performance over waterflooding. Reservoir model parameters assessed in this research study were horizontal and vertical permeabilities, fluids properties, WAG injection scheme, fluids mobility, trapped gas saturation, reservoir pressure, residual oil saturation to gas, and injected gas volume. The outcome of the WAG simulation models was fed to the two selected data mining techniques, regression and group method of data handling (GMDH), to build WAG incremental recovery factor predictive model. Input data to the machine learning technique were split into two sets: 70% for training the model and 30% for model validation. Predictive models that calculate WAG incremental recovery factor as a function of the input parameters were developed. The predictive models correlation coefficient of 0.766 and 0.853 and root mean square error of 3.571 and 2.893 were achieved from regression and GMDH methods, respectively. GMDH technique demonstrated its strength and ability in selecting effective predictors, optimizing network structure, and achieving more accurate predictive model. The achieved WAG incremental recovery factor predictive models are expected to help reservoir engineers perform quick evaluation of WAG performance and assess a WAG project risk prior launching detailed time-consuming and costly technical studies.

Water alternating gas (WAG) injection process is a proven enhanced oil recovery (EOR) technology with many successful field applications around the world. WAG pilot projects demonstrate that WAG incremental recovery factor typically ranges from 5 to 10% of original oil in place, though up to 20% has been observed in some fields. Despite its proven success, WAG application growth has been very slow. One of the reasons is the unavailability of robust analytical predictive tools that could estimate WAG incremental recovery factor, which is required for preliminary economic analysis before committing to expensive and time-consuming detailed technical studies and field pilot test that often requires a lot of input data. A seminumerical model for WAG incremental recovery factor prediction was developed based on data mining of published WAG pilots to fill this gap. An extensive review of published WAG pilot projects was carried out, and consequently, 33 projects from 28 fields around the world were selected for this research study. Field WAG incremental recovery factor and parameters with total of one hundred and seventy-seven (177) observations were inputted to the predictive model. A predictive model was developed using both regression and group method of data handling (GMDH) techniques; 70% of the 33 WAG pilot projects data were used as validation, whereas remaining 30% of data set were used for validation. The predictive model results achieved with coefficient of determination (R 2) from the regression method were ranging from 0.892 to 0.946 and 0.854 to 0.917 for training and validation sets, respectively. However, the prediction model coefficient of determination (R 2) using GMDH method was ranging from 0.964 to 0.981 and 0.934 to 0.974 for training and validation, respectively. The developed predictive model can predict WAG incremental recovery factor versus multiple input parameters that include rock type, WAG process type, hydrocarbon pore volume of injected gas, reservoir permeability, oil gravity, oil viscosity, reservoir pressure, and reservoir temperature. The results of the study demonstrated that few input parameters have a significant impact on WAG incremental recovery factor as reservoir permeability and hydrocarbon pore volume of injected gas. This research study uses a novel approach in pre-defining the expected incremental WAG recovery factor before committing resources for building complex numerical reservoir simulation models and running WAG pilot tests, which are very time-consuming and costly and require extensive data input.

With the increasing demand in domestic energy requirement and with declining production rates from mature fields of offshore Malaysia, PETRONAS has embarked on an aggressive campaign to address the decline in rates as well as increase the reserves through proven Enhanced Oil Recovery (EOR) application. An immiscible Water Alternating Gas (WAG) process is found to be the most favorable EOR method due to gas supply availability, proven world-wide application, and promising results in improving injection fluid sweep efficiency and reducing residual oil saturation. To reduce the uncertainty of EOR technical studies under low oil price, a comprehensive integrated procedure is required to study WAG performance and define key factors that impact flow efficiency under three-phase flow conditions for a more representative full-field reservoir simulation study results. This procedure involves a detailed comprehensive parametric study of the cycle dependent hysteresis starting from extensive literature review, followed by laboratory experiments and extracting pertinent WAG parameters from coreflood history matching and finally applying these parameters in full-field reservoir simulation study. This study demonstrated that the WAG cycle dependency of relative permeability during WAG process is one of the key factors that has significant impact on WAG performance and recovery factor. This feature cannot be captured by conventional three-phase flow models used by reservoir simulators. The study indicates additional recovery factor of about 1%-2% compared to the base-case WAG model without WAG hysteresis.

Predicting the incremental recovery factor with an enhanced oil recovery (EOR) technique is a very crucial task. It requires a significant investment and expert knowledge to evaluate the EOR incremental recovery factor, design a pilot, and upscale pilot result. Water-alternating-gas (WAG) injection is one of the proven EOR technologies, with an incremental recovery factor typically ranging from 5 to 10%. The current approach of evaluating the WAG process, using reservoir modeling, is a very time-consuming and costly task. The objective of this research is to develop a fast and cost-effective mathematical model for evaluating hydrocarbon-immiscible WAG (HC-IWAG) incremental recovery factor for medium-to-light oil in undersaturated reservoirs, designing WAG pilots, and upscaling pilot results. This integrated research involved WAG literature review, WAG modeling, and selected machine learning techniques. The selected machine learning techniques are stepwise regression and group method of data handling. First, the important parameters for the prediction of the WAG incremental recovery factor were selected. This includes reservoir properties, rock and fluid properties, and WAG injection scheme. Second, an extensive WAG and waterflood modeling was carried out involving more than a thousand reservoir models. Third, WAG incremental recovery factor mathematical predictive models were developed and tested, using the group method of data handling and stepwise regression techniques. HC-IWAG incremental recovery factor mathematical models were developed with a coefficient of determination of about 0.75, using 13 predictors. The developed WAG predictive models are interpretable and user-friendly mathematical formulas. These developed models will help the subsurface teams in a variety of ways. They can be used to identify the best candidates for WAG injection, evaluate and optimize the WAG process, help design successful WAG pilots, and facilitate the upscaling of WAG pilot results to full-field scale. All this can be accomplished in a short time at a low cost and with reasonable accuracy.

Prior to initiating a reservoir simulation study, the readiness of a complete set of fluid analysis data should be assured and quality checked. This usually includes, but not limited to, identification of any vertical and lateral variation of reservoir fluid properties. Identification of these trends can have tremendous impact on the results of the reservoir simulation project. Recently, a reservoir simulation study was conducted on a brown reservoir in a Middle Eastern field. This reservoir is geologically characterized by various faults which were developed after fluid migration. The presence of these faults has resulted in communicated reservoir compartments. Application of traditional workflow in analyzing the PVT data was insufficient to identify any trend in the fluid properties or account for any vertical and lateral differences in reservoir fluid properties. This paper explains the work done to characterize fluid properties for a structurally complex sandstone reservoir, where most of the downhole fluid samples were collected in the 1960s. Unfortunately, the sampling depth was not reported for most of the samples at that time, with no production logging data available to identify the production zones within the large perforation interval. Laboratory measurements indicate under-saturated oil with variation that could be correlated with depth. Samples were obtained from three geological subzones; Layers-1, 2 and 3, where a shale layer is believed to be partially separating Layer 1 from the other layers. Part of the challenge is that a large number of samples were collected from different sublayers as a combination, which increases sampling depth uncertainty. Defining properties trend versus depth was the main challenge in the study. This uncertainty was addressed by developing an iterative "what-if?" analysis scenarios by integrating geological parameters. A new model was prepared that considered the initial conditions of the reservoir fluid before any migration or tectonic activities took place. Applying the proposed approach, resulted in a clear trend of hydrocarbon properties variation with depth and provided a clear observation of the presence of one PVT region in the reservoir. Based on the results of this study, one PVT region with a solution gas-oil ratio trend versus depth was applied into the reservoir model, which resulted in a reliable dynamic simulation model.