Experimental evaluation of compressibility coefficients for fractures and intergranular pores of an oil and gas reservoir

The paper is devoted to studies of the volumetric response of rocks caused by changes in their stress state. Changes in the volume of fracture and intergranular components of the pore space based on measurements of the volume of pore fluid extruded from a rock sample with an increase in its all-round compression have been experimentally obtained and analyzed. Determination of the fracture and intergranular porosity components is based on the authors' earlier proposed method of their calculation using the values of longitudinal wave velocity and total porosity. The results of experimental and analytical studies of changes in porosity and its two components (intergranular and fractured) under the action of effective stresses are considered. This approach allowed the authors to estimate the magnitude of the range of changes in the volumetric compressibility of both intergranular pores and fractures in a representative collection of 37 samples of the Vendian-age sand reservoir of the Chayanda field. The method of separate estimation of the compressibility coefficients of fractures and intergranular pores is proposed, their values and dependence on the effective pressure are experimentally obtained. It is determined that the knowledge of the values of fracture and intergranular porosity volumetric compressibility will increase the reliability of estimates of changes in petrophysical parameters of oil and gas reservoirs caused by changes in the stress state during the development of hydrocarbon fields.

A Novel Approach to Oil Layer Recognition Model Using Whale Optimization Algorithm and Semi-Supervised SVM

The dataset distribution of actual logging is asymmetric, as most logging data are unlabeled. With the traditional classification model, it is hard to predict the oil and gas reservoir accurately. Therefore, a novel approach to the oil layer recognition model using the improved whale swarm algorithm (WOA) and semi-supervised support vector machine (S3VM) is proposed in this paper. At first, in order to overcome the shortcomings of the Whale Optimization Algorithm applied in the parameter-optimization of the S3VM model, such as falling into a local optimization and low convergence precision, an improved WOA was proposed according to the adaptive cloud strategy and the catfish effect. Then, the improved WOA was used to optimize the kernel parameters of S3VM for oil layer recognition. In this paper, the improved WOA is used to test 15 benchmark functions of CEC2005 compared with five other algorithms. The IWOA–S3VM model is used to classify the five kinds of UCI datasets compared with the other two algorithms. Finally, the IWOA–S3VM model is used for oil layer recognition. The result shows that (1) the improved WOA has better convergence speed and optimization ability than the other five algorithms, and (2) the IWOA–S3VM model has better recognition precision when the dataset contains a labeled and unlabeled dataset in oil layer recognition.

A Comparison of Machine Learning Algorithms in Predicting Lithofacies: Case Studies from Norway and Kazakhstan

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.