Novel approach for predicting water alternating gas injection recovery factor

Abstract

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.

Assessment of Oil Recovery Methods for Reservoirs in the Flemish Pass Basin

“…Research by Belazreg et al highlights machine learning and the development of a predictive model for WAG recovery based on a two-step approach of reservoir simulation and data mining [23]. For this research, one thousand dynamic reservoir models, with a range of input parameters, were simulated [23].…”

“…Research by Belazreg et al highlights machine learning and the development of a predictive model for WAG recovery based on a two-step approach of reservoir simulation and data mining [23]. For this research, one thousand dynamic reservoir models, with a range of input parameters, were simulated [23]. The results fed into two selected data mining techniques, regression and group method of data handling (GMDH), in order to build a predictive model for WAG recovery [23].…”

“…For this research, one thousand dynamic reservoir models, with a range of input parameters, were simulated [23]. The results fed into two selected data mining techniques, regression and group method of data handling (GMDH), in order to build a predictive model for WAG recovery [23]. Ultimately, the GMDH technique prevailed while using 70% of the input data for machine learning, and 30% for validation purposes [23].…”

Identifying Applications of Machine Learning and Data Analytics Based Approaches for Optimization of Upstream Petroleum Operations

“…In the work done by Belazreg et al, [ 54 ] data mining (DM) and simulation approaches have been used together to develop a predictive tool for recovery factor determination in an immiscible hydrocarbon water alternate gas (WAG) process. First, simulation was performed over the WAG model.…”

“…Optimized CNN-based studies can be further examined to obtain higher accuracy. [54] More of the EOR methods can be included to increase the applicability of the method. [55] The performance accuracy and reliability of soft sensor models in online implementation are well demonstrated but the R value is relatively low.…”