Recently, the team of Zhang Kai has made new progress in the field of interwell connectivity characterization, and the related research has been published in Water. The paper is titled " Waterflooding Interwell Connectivity Characterization and Productivity Forecast with Physical Knowledge Fusion and Model Structure Transfer ".

Innovation: A novel neural network named physical knowledge fusion neural network (PKFNN) is developed, cooperating with the material balance equation to control the approximation of the waterflooding process, thereby revealing the physical principle of the data and guaranteeing the rationality of estimation. A physical evaluation function is built to ensure the physical boundaries of inter-well connectivity and avoids the complex computation resulting from constraint optimization. The physical knowledge transfer and model structure transfer are employed in PKFNN to cope with the continuity and homogeneity of geological properties, in-creasing the interactions between models.

Abstract: Waterflooding reservoir interwell connectivity characterization is the fundamental work in oil development, aiming to inverse the vital connecting channels between injectors and producers. In this paper, we endow an artificial neural network (ANN) with strong interpretability through the ordinary differential equation (ODE) of the material balance equation, proposing a physical knowledge fusion neural network (PKFNN). In addition, the proposed model could inherit the knowledge learned from different injector–producer pairs, fully improving the training efficiency. In this way, PKFNN combines the merits of both physical and machine learning approaches. Firstly, based on the physical control law and the ODE of the material balance equation, we endow the model with highly transparent modular architectures in the framework of feedforward neural network. In this way, our work has both high interpretability and excellent approximation ability, combining the merits of the physical and machine learning approaches. The proposed model shows great performance on productivity forecast and interwell connectivity reflection in several reservoir experiments. PKFNN provides a novel way to enhance the interpretability and robustness of the data-driven-based interwell connectivity-analyzing models by integrating the physical knowledge of waterflooding reservoirs.

Water covers all aspects of water, including water science, technology, management and governance. Topics include: water resources management; water governance; hydrology and hydraulics; water scarcity; flood risk; water quality; water and wastewater treatment; urban water management; water footprint assessment; water-food; water-energy; water-human development; water-ecosystems, etc. The latest impact factor of the journal is 3.530, and the average impact factor IF in the past 5 years is 3.628. This journal currently appears in the JCR Q2 or the Chinese Academy of Sciences ranking 3.

Paper link:

https://doi.org/10.3390/w15020218

Citation:

Jiang Y, Zhang H, Zhang K, et al. Waterflooding Interwell Connectivity Characterization and Productivity Forecast with Physical Knowledge Fusion and Model Structure Transfer [J]. Water, 2023, 15(2): 218.