Selecting the most suitable enhanced oil recovery (EOR) technique remains challenging due to severe class imbalance in historical datasets and the limitations of traditional screening criteria. To address data imbalance while preserving domain knowledge, this study proposes a novel machine learning framework that incorporates domain-informed synthetic data generation strictly constrained by established EOR screening criteria. An initial dataset of 583 documented EOR projects was compiled from field reports and public databases. After rigorous cleaning, 575 valid samples were retained and subsequently augmented to 760 balanced instances (class sizes ranging from 60–110 samples per class). T... More >

The depleted gas reservoirs can serve not only as sites for CO$_2$ sequestration but also as potential spaces for hydrogen storage. However, this process remains insufficiently investigated and thus cannot offer reliable technical support for the injection operations. In this study, a mathematical model for simulating hydrogen storage in depleted gas reservoirs was developed and numerically solved. Meanwhile, the applicability was then verified through comparison with results from previous studies. Based on this model, a detailed analysis was performed to investigate the evolution of key parameters under specific injection conditions. Finally, the effects of various factors on parameters suc... More >