Key points are not available for this paper at this time.
The effective channeling of fluid flow by fractures is a liability for enhanced oil recovery (EOR) methods like CO 2 flooding or CO 2 storage. Developing a distributed fracture model to understand the heterogeneity of the fracture network is essential in characterizing tight and low-permeability reservoirs. In the Ordos Basin, the Chang 8-1-2 layer of the Yanchang Formation is a typical tight and low permeability reservoir in the JH17 wellblock. The strong heterogeneity of distributed fractures, differing fracture scales and fracture types make it difficult to effectively characterize the fracture distribution within the Chang 8-1-2 layer. In this paper, multi-source and multi-attribute methods are used to integrate data into a neural network at different scales, and fuzzy logic control is used to judge the correlation of various attributes. The results suggest that attribute correlation between coherence and fracture indication is the best, followed by correlations with fault distance, north–south slope, and north–south curvature. Advantageous attributes from the target area are used to train the neural network, and the fracture density model and discrete fracture network (DFN) model are built at different scales. This method can be used to effectively predict the distribution characteristics of fractures in the study area. And any learning done by the neural network from this case study can be applied to fracture network modeling for reservoirs of the same type.
Yinbang Zhou (Thu,) studied this question.