To address the evaluation difficulty of hydrocarbon saturation in low resistivity reservoirs, an innovative method for calculating oil saturation is proposed using a nuclear magnetic resonance (NMR)-constrained triple-water resistivity model. This model explicitly distinguishes three conductive water phases: movable water, capillary-bound water, and clay-bound water. Resistivity response equations are established for both water-saturated and hydrocarbon-bearing rocks. A cooperative inversion framework is proposed based on NMR and conventional logging data, incorporating high-precision NMR-derived parameters as constraints during conventional logging inversion. The pore component volumes are obtained with the NMR T₂ spectrum decomposition and served as a priori information for the nonlinear optimization of porosity exponents. This enables the construction of a pore component inversion algorithm using conventional logging data, thereby extending water saturation calculation applicability in complex reservoirs. The method incorporates data-driven optimization to effectively reduce the reliance on core-based calibration data (mercury injection, petrophysical experiments, cation exchange capacity (CEC) tests). Application in a Bohai Bay Basin low resistivity reservoir demonstrates superior saturation calculation accuracy compared to traditional models. The integration of multi-physics logging inversion with nonlinear optimization effectively enhances conductivity mechanism characterization in reservoirs with complex pore systems, providing a robust technical solution for quantitative evaluation of low resistivity oil reservoirs.

The shear wave (S-wave) velocity is a critical rock elastic parameter in shale reservoirs, especially for evaluating shale fracability. To effectively supplement S-wave velocity under the condition of no actual measurement data, this paper proposes a physically-data driven method for the S-wave velocity prediction in shale reservoirs based on the class activation mapping (CAM) technique combined with a physically constrained two-dimensional Convolutional Neural Network (2D-CNN). High-sensitivity log curves related to S-wave velocity are selected as the basis from the data sensitivity analysis. Then, we establish a petrophysical model of complex multi-mineral components based on the petrophysical properties of porous medium and the Biot-Gassmann equation. This model can help reduce the dispersion effect and constrain the 2D-CNN. In deep learning, the 2D-CNN model is optimized using the Adam, and the class activation maps (CAMs) are obtained by replacing the fully connected layer with the global average pooling (GAP) layer, resulting in explainable results. The model is then applied to wells A, B1, and B2 in the southern Songliao Basin, China and compared with the unconstrained model and the petrophysical model. The results show higher prediction accuracy and generalization ability, as evidenced by correlation coefficients and relative errors of 0.98 and 2.14%, 0.97 and 2.35%, 0.96 and 2.89% in the three test wells, respectively. Finally, we present the defined C-factor as a means of evaluating the extent of concern regarding CAMs in regression problems. When the results of the petrophysical model are added to the 2D feature maps, the C-factor values are significantly increased, indicating that the focus of 2D-CNN can be significantly enhanced by incorporating the petrophysical model, thereby imposing physical constraints on the 2D-CNN. In addition, we establish the SHAP model, and the results of the petrophysical model have the highest average SHAP values across the three test wells. This helps to assist in proving the importance of constraints.