Energized pre-fracturing has emerged as an effective approach for enhancing reservoir energy, fracture complexity and oil recovery in tight reservoirs. However, the mechanisms by which fracture propagation induced by different energized pre-pad fluids governs subsequent imbibition-driven oil recovery remain insufficiently understood. To address this issue, an integrated experimental framework was established to investigate the coupled evolution of fracture networks and pore-scale oil displacement during energized pre-fracturing. By combining X-ray computed tomography for quantitative fracture characterization and dynamic nuclear magnetic resonance for monitoring imbibition-driven oil recovery, the interactions between fracture-scale architecture and pore-scale fluid redistribution were systematically elucidated. The results demonstrate that, compared to conventional fracturing, energized pre-fracturing not only lowers breakdown pressure but also promotes the formation of more complex, highly connected fracture networks, which in turn substantially enhance ultimate oil recovery. Notably, gaseous pre-pad fluids exhibit clear advantages over aqueous systems, with supercritical CO₂ generating the lowest breakdown pressure and the most intricate multi-branch fracture networks, as indicated by higher fracture fractal dimension and area ratio. These fracture characteristics significantly facilitate imbibition efficiency, resulting in higher oil recovery. Pore-scale analysis further reveals that oil mobilization is dominated by contributions from micropores and mesopores, underscoring the critical role of energized pre-fracturing in activating oil stored in small-scale pore systems. The proposed multi-scale methodology, integrating fluid properties, fracture network evolution, and imbibition dynamics, provides a mechanistic basis and practical guidance for optimizing energized fracturing and improving the efficient development of tight conglomerate reservoirs.

Accurate diagnosis of fracture geometry and conductivity is of great challenge due to the complex morphology of volumetric fracture network. In this study, a DNN (deep neural network) model was proposed to predict fracture parameters for the evaluation of the fracturing effects. Field experience and the law of fracture volume conservation were incorporated as physical constraints to improve the prediction accuracy due to small amount of data. A combined neural network was adopted to input both static geological and dynamic fracturing data. The structure of the DNN was optimized and the model was validated through k-fold cross-validation. Results indicate that this DNN model is capable of predicting the fracture parameters accurately with a low relative error of under 10% and good generalization ability. The adoptions of the combined neural network, physical constraints, and k-fold cross-validation improve the model performance. Specifically, the root-mean-square error (RMSE) of the model decreases by 71.9% and 56% respectively with the combined neural network as the input model and the consideration of physical constraints. The mean square error (MRE) of fracture parameters reduces by 75% because the k-fold cross-validation improves the rationality of data set dividing. The model based on the DNN with physical constraints proposed in this study provides foundations for the optimization of fracturing design and improves the efficiency of fracture diagnosis in tight oil and gas reservoirs.