• Energy Research

In the present paper, we analyze numerically the disproportionate permeability reduction (DPR) water-shutoff (WSO) treatments in oil production well, i.e., the ability to reduce relative permeability (RP) to water more than to oil. The technique consists of bullhead injection of polymer solutions (gelant) into the near-wellbore formation without zone isolation. By assuming the low dissolution of polymer in oil and the low mobility of the gel in porous medium, we reduced the compositional model of the process to a simple two-phase model, with RP and capillary pressure (PC) dependent on the water and gel saturation. We proposed the extension of the LET correlations used to calculate RP and PC for the case of three phases (oil–water–gel). The problem is divided into two stages: the polymer injection and the post-treatment production. Both of these processes are described by the same formal mathematical model, which results from incompressible two-phase flow equations formulated in terms of normalized saturation and global pressure. The thermal effects caused by the injection of a relatively cold aqueous solution are taken into account. The numerical solution shows favorable results for the DPR WSO treatments. Other techniques, such as the creation of impermeable barrier and downhole water sink (DWS) technology, are also tested in order to check the validity of the developed numerical model with experimental data.

Defining distinctive areas of the physical properties of rocks plays an important role in reservoir evaluation and hydrocarbon production as core data are challenging to obtain from all wells. In this work, we study the evaluation of lithofacies values using the machine learning algorithms in the determination of classification from various well log data of Kazakhstan and Norway. We also use the wavelet-transformed data in machine learning algorithms to identify geological properties from the well log data. Numerical results are presented for the multiple oil and gas reservoir data which contain more than 90 released wells from Norway and 10 wells from the Kazakhstan field. We have compared the the machine learning algorithms including KNN, Decision Tree, Random Forest, XGBoost, and LightGBM. The evaluation of the model score is conducted by using metrics such as accuracy, Hamming loss, and penalty matrix. In addition, the influence of the dataset features on the prediction is investigated using the machine learning algorithms. The result of research shows that the Random Forest model has the best score among considered algorithms. In addition, the results are consistent with outcome of the SHapley Additive exPlanations (SHAP) framework.