Injecting CO2 into coal seams to enhance coal bed methane (ECBM) recovery has been identified as a viable method for increasing methane extraction. This process also has significant potential for sequestering large volumes of CO2, thereby reducing the concentration of greenhouse gases in the atmosphere. However, for deep coal seams where formation pressure is relatively high, there is limited research on CO2 injection into systems with higher methane adsorption equilibrium pressure. Existing studies, mostly confined to the low-pressure stage, fail to effectively reveal the impact of factors such as temperature, high-pressure CO2 injection, and coal types on enhancing the recovery and sequestration of CO2-displaced methane. Thus, this study aims to investigate the influence of temperature, pressure, and coal types on ECBM recovery and CO2 sequestration in deep coal seams. A series of CO2 core flooding tests were conducted on various coal cores, with CO2 injection pressures ranging from 8 to 18 MPa. The CO2 and methane adsorption rates, as well as methane displacement efficiency, were calculated and recorded to facilitate result interpretation. Based on the results of these physical experiments, numerical simulation was conducted to study multi-component competitive adsorption, desorption, and seepage flow under high temperature and high pressure in a deep coal seam’s horizontal well. Finally, the optimization of the total injection amount (0.7 PV) and injection pressure (approximately 15.0 MPa) was carried out for the plan of CO2 displacement of methane in a single well in the later stage.
The advancement of Industry 5.0 hinges on the deep integration of artificial intelligence (AI) with domain expertise to foster sustainable industrial development. This study proposes a deep learning-based surrogate modeling framework that integrates reservoir production requirements with AI technologies, providing intelligent decision support for production optimization and enhanced efficiency. To evaluate AI’s effectiveness in complex industrial scenarios, we conduct an integrated analysis encompassing model construction, dynamic prediction, and production optimization using a real-world oilfield case. This oilfield features a dynamically increasing number of wells and requires dynamic adjustments to injection–production relationships. To address this challenge, we enhance the Embed-to-Control model by improving the nonlinear representation capability within its decoder structure. Subsequently, we construct a high-fidelity dataset containing 300 samples for model training and testing. The experimental results demonstrate that the proposed improved model achieves a high accuracy in predicting key state variables (pressure and saturation) and oil production. Regarding computational efficiency, a single model run requires only approximately 17.3 s, achieving an over 200× speedup relative to traditional numerical simulators. Finally, we coupled the trained surrogate model with the particle swarm optimization algorithm to optimize the injection well control strategy. The optimized scheme increases daily oil production by 13.84%, boosting economic benefits. This study demonstrates a practical technological pathway to accelerate the oil and gas industry’s transition toward Industry 5.0.