Production prediction plays an important role in decision making, development planning, and economic evaluation during the exploration and development period. However, applying traditional methods for production forecasting of newly developed wells in the conglomerate reservoir is restricted by limited historical data, complex fracture propagation, and frequent operational changes. This study proposed a Gated Recurrent Unit (GRU) neural network-based model to achieve batch production forecasting in M conglomerate reservoir of China, which tackles the limitations of traditional decline curve analysis and conventional time-series prediction methods. The model is trained by four features of production rate, tubing pressure (TP), choke size (CS), and shut-in period (SI) from 70 multistage hydraulic fractured horizontal wells. Firstly, a comprehensive data preprocessing is implemented, including excluding unfit wells, data screening, feature selection, partitioning data set, z-score normalization, and format conversion. Then, the four-feature model is compared with the model considering production only, and it is found that with frequent oilfield operations changes, the four-feature model could accurately capture the complex variance pattern of production rate. Further, Random Forest (RF) is employed to optimize the prediction results of GRU. For a fair evaluation, the performance of the proposed model is compared with that of simple Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) neural network. The results show that the proposed approach outperforms the others in prediction accuracy and generalization ability. It is worth mentioning that under the guidance of continuous learning, the GRU model can be updated as soon as more wells become available.

Post-fracturing well shut-in is traditionally due to the elastic closure of hydraulic fractures and proppant compaction. However, for shale gas wells, the extension of shut-in time may improve the post-fracturing gas production due to formation energy supplements by fracturing-fluid imbibition. This paper presents a methodology using numerical simulation to simulate the hydrodynamic equilibrium phenomenon of a hydraulically fractured shale gas reservoir, including matrix imbibition and fracture network crossflow, and further optimize the post-fracturing shut-in time. A mathematical model, which can describe the fracturing-fluid hydrodynamic transport during the shut-in process, and consider the distinguishing imbibition characteristics of a hydraulically fractured shale reservoir, i.e., hydraulic pressure, capillarity and chemical osmosis, is developed. The key concept, i.e., hydrodynamic equilibrium time, for optimizing the post-fracturing shut-in schedule, is proposed. The fracturing-fluid crossflow and imbibition profiles are simulated, which indicate the water discharging and sucking equilibrium process in the coupled fracture–matrix system. Based on the simulation, the hydrodynamic equilibrium time is calculated. The influences of hydraulic pressure difference, capillarity and chemical osmosis on imbibition volume, and hydrodynamic equilibrium time are also investigated. Finally, the optimal shut-in time is determined if the gas production rate is pursued and the fracturing-fluid loss is allowable. The proposed simulation method for determining the optimal shut-in time is meaningful to the post-fracturing shut-in schedule.

No abstract