The advancement in big data and artificial intelligence has enabled a novel exploration mode for the study of petroleum engineering. Unlike theory-based solution methods,the data-driven intelligent approaches demonstrate superior flexibility,computational efficiency and accuracy for dealing with complex multi-scale,and multi-physics problems. However,these intelligent models often disregard physical laws in pursuit of error minimization,which leads to certain uncertainties. Therefore,physics-informed machine learning approaches have been developed based on data,guided by physics,and supported by machine learning models. This study summarizes four embedding mechanisms for introducing physical information into machine learning models,including input data-based embedding,model architecture-based embedding,loss function-based embedding,and model optimization-based embedding mechanism. These “data + physics” dual-driven intelligent models not only exhibit higher prediction accuracy while adhering to physic laws,but also accelerate the convergence to improve computational efficiency. This paradigm will facilitate the guide developments in solving petroleum engineering problems toward a more comprehensive and efficient direction.

This report summarizes our recent experimental findings [Xie et al., Phys. Rev. Lett., 2022] and pore-scale simulation results [Xie et al., Phys. Rev. Fluids., 2020] on viscoelastic oscillation, which is a new observation of viscoelastic instability in the multiphase flow state. The viscoelastic oscillation causes trapping of droplets in contraction-expansion micro-channels regardless of the injection rate. Based on the force balance analysis of the viscous, capillary and elastic forces, the oscillation amplitude is found to linearly increase with viscoelasticity, and the trapped droplet size is determined by the elasto-capillary number. The oscillation also helps to extract droplets from their originally trapped positions such as dead-ends once a critical Deborah number is reached. These results successfully explain the phenomenon that the alternative injection of viscoelastic and inelastic fluids continually produces additional oil, indicating that the viscoelastic oscillation is a new important mechanism of viscoelastic fluid for enhanced oil recovery.