Terrestrial tight oil has extremely strong diagenesis heterogeneity, so a large number of rock thin slices are needed to reveal the real microscopic pore-throat structure characteristics. In addition, difficult identification, high cost, long time, strong subjectivity and other problems exist in the identification of tight oil rock thin slices, and it is difficult to meet the needs of fine description and quantitative characterization of the reservoir. In this paper, a method for identifying the characteristics of rock thin slices in tight oil reservoirs based on the deep learning technique was proposed. The present work has the following steps: first, the image preprocessing technique was studied. The original image noise was removed by filtering, and the image pixel size was unified by a normalization technique to ensure the quality of samples; second, the self-labeling image data augmentation technique was constructed to solve the problem of sparse samples; third, the Mask R-CNN algorithm was introduced and improved to synchronize the segmentation and recognition of rock thin slice components in tight oil reservoirs; Finally, it was demonstrated through experiments that the SMR method has significant advantages in accuracy, execution speed and migration.

The diagenetic facies of tight oil reservoirs reflect the diagenetic characteristics and micro-pore structure of reservoirs, determining the formation and distribution of sweet spot zones. By establishing the correlation between diagenetic facies and logging curves, we can effectively identify the vertical variation of diagenetic facies types and predict the spatial variation of reservoir quality. However, it is still challenging work to establish the correlation between logging and diagenetic facies, and there are some problems such as low accuracy, high time consumption and high cost. To this end, we propose a lithofacies identification method for tight oil reservoirs based on hybrid intelligence using the Fuyu oil layer of the Sanzhao depression in Songliao Basin as the target area. Firstly, the geological characteristics of the selected area were analyzed, the definition and classification scheme of diagenetic facies and the dominant diagenetic facies were discussed, and the logging response characteristics of various diagenetic facies were summarized. Secondly, based on the standardization of logging curves, the logging image data set of various diagenetic facies was built, and the imbalanced data set processing was performed. Thirdly, by integrating CNN (Convolutional Neural Networks) and ViT (Visual Transformer), the C-ViTM hybrid intelligent model was constructed to identify the diagenetic facies of tight oil reservoirs. Finally, the effectiveness of the method is demonstrated through experiments with different thicknesses, accuracy and single-well identification. The experimental results show that the C-ViTM method has the best identification effect at the sample thickness of 0.5 m, with Precision of above 86%, Recall of above 90% and F1 score of above 89%. The calculation result of the Jaccard index in the identification of a single well was 0.79, and the diagenetic facies of tight reservoirs can be identified efficiently and accurately. At the same time, it also provides a new idea for the identification of the diagenetic facies of old oilfields with only logging image data sets.