Subsurface Natural Fracture Identification Using an Integrated Ensemble Learning Method

Natural fractures play a crucial role in the storage and seepage of oil shale. However, identifying fractures using conventional logging techniques presents challenges due to complex response characteristics and severe data imbalance. Here, we propose a highly accurate integrated ensemble learning method, called BSI-extreme gradient boosting (XGBoost), for identifying the natural fracture development, which combines several steps including isolation forests (iForests), synthetic minority oversampling techniques (SMOTEs), and XGBoost, and incorporates rock brittleness as a controlling factor in the model construction process. The proposed model effectively addresses several challenges encountered in fracture identification, including complex logging response characteristics, low precision and recall of fractured labels, and excessive sensitivity of ensemble learning to noise. To do so, the relationship between fracture density and brittle mineral content is analyzed through core analysis and X-ray diffraction (XRD). Then, conventional logging and rock brittleness are used as features for training the model. Herein, by screening the outliers of iForest, SMOTE oversampling, and feature selection, optimal hyperparameters of the model are obtained through the grid search method. The results demonstrated that using BSI-XGBoost, the testing set achieved an accuracy of 92.45%. Comparatively, this accuracy is 4.86% higher than the original XGBoost model and 3.73% higher than the B-XGBoost model, which incorporated brittleness curves but did not include oversampling and outlier removal. Collectively, this workflow provided an effective method for intelligent identification of fractures in oil shale with high accuracy based on easily accessible conventional logging curves.