The water cutting rate is recorded dynamically during the production process of a well. If the remaining oil saturation of the reservoir can be deduced based on the water cutting rate, it will give guidance to improve the reservoir recovery and can save expensive drilling costs. In the oil–water two-phase seepage experiment on core samples, the oil and water relative permeability reflects the relationship between the water cutting rate and water saturation, that is, percolating saturation formula. The relative permeability test data of 17 rock samples from six seal coring wells in Daqing Changyuan were used to optimize and construct the coefficients of the index percolating saturation formula that vary with the pore structure parameters of reservoirs, to form an index percolating saturation formula with variable coefficients that is more consistent with the regional geological characteristics of the reservoir. Based on this, the formula of water saturation calculated by the water cutting rate is deduced. And the high-precision formula for calculating the irreducible water saturation and residual oil saturation by effective porosity, absolute permeability, and shale content is given. The derivative formula of water saturation on the water cutting rate was established, and the parameters of 17 rock samples were calculated. It was found that the variation velocity of water saturation of each sample with the water cutting rate presented a “U” shape, which was consistent with the actual characteristics that the variation velocity of the water saturation in the early, middle, and late stages of oilfield development first decreased, then stabilized, and finally increased rapidly. The research results were applied to the prediction of remaining oil saturation in the research area, and the water saturation about six producing wells was calculated by using their present water cutting rates, and the remaining oil distribution profile was predicted effectively. The analysis of four layers of two newly drilled infill wells and reasonable oil recovery suggestions were given to achieve good results.

Pore and permeability are distributed discontinuously and unevenly in the dominant sedimentary model of the lateral accretion body inside the meandering river point bar of the Fuyang reservoir of the Yushulin oilfield. Based on the water flooding experiments of field core samples, the influence of pore permeability conditions on residual oil distribution type and water cutting rate was studied by using the microscopic visualization technology enabled through a photolithographically fabricated glass model. It is found that the residual oil in samples shows five discontinuous types, which are cluster, columnar, oil droplet, membrane, and blind end. In the stages with low, medium, and high water cutting rates, the proportion of clustered residual oil in the samples with different permeability is high, reflecting the situation that it is difficult for injected water to spread widely in tight oil reservoirs. With the decrease of permeability, the proportion of membrane and blind end residual oil gradually increases, which indicates that the thin pore throat can produce large restrictions on residual oil, resulting in residual oil enrichment. At the same time, the water flooding experiment was carried out by changing the displacement direction and periodic water injection. It was found that changing the displacement direction was beneficial to the recovery of residual oil in the thin pore throat and avoided the dominant seepage of injected water in the big pore throat, and the recovery rate was increased by more than 2.14%. Periodic water injection, which was conducive to adjusting the displacement pressure difference, reduced the constraining force of the throat on residual oil and increased the recovery rate by more than 3.98%. The actual well area with closed coring wells and dynamic production data is preferred for the application of experimental research results. Changing displacement direction and periodic water injection increased the residual oil recovery by more than 3%.

Breakthrough pressure (BP) is a key parameter for evaluating the sealing capacity of shale caprocks, whereas direct laboratory measurements are time-consuming and costly, limiting their use in continuous regional assessment. This study develops a conventional-log-based workflow for BP prediction in the Quan-4 Member (K1q4) caprock underlying the Qingshankou shale oil interval in the Gulong Sag, Songliao Basin. Four routinely available logs—gamma ray (GR), acoustic interval transit time (AC), bulk density (DEN), and compensated neutron log (CNL)—were integrated with core-measured BP data. A GR-AC multiple-regression baseline and five machine-learning algorithms, including stochastic gradient descent (SGD), extremely randomized trees (ERT), Random Forest (RF), extreme gradient boosting (XGBoost), and adaptive boosting (AdaBoost), were compared under a unified workflow. The training set was used for normalization, model fitting, grid search, and internal five-fold cross-validation, whereas the held-out test set and external prediction wells were kept separate for performance evaluation. The results show that BP generally increases with GR and DEN and decreases with AC and CNL, indicating that clay content, compaction, and pore connectivity jointly control the logging response of caprock sealing capacity. Among the evaluated models, AdaBoost achieved the best overall performance, with RMSE, MAE, and R² values of 1.33 MPa, 0.97 MPa, and 0.89 on the held-out test set, and 1.19 MPa, 0.92 MPa, and 0.94 in external prediction wells. Train–test diagnostics, learning curves, and SHAP analysis indicate stable performance and physically plausible feature contributions within the present dataset. The proposed workflow can therefore provide a practical supplement to laboratory BP measurements for caprock evaluation in the study area, although broader application still requires well-level independent validation and explicit prediction-uncertainty quantification.