Reservoir discontinuous boundary identification method based on expansion convolutional neural network

Abstract

The invention discloses a reservoir discontinuous boundary identification method based on an expansion convolutional neural network. The method comprises the following steps: obtaining an attribute graph from seismic data; mapping attribute data to a low-dimensional vector space by adopting a multi-layer fusion technology; the method comprises the following steps: analyzing geological data, logging data and seismic data to obtain a discontinuous boundary type, and obtaining a label according to the divided discontinuous boundary type; learning a deep feature r1 from an input attribute by adopting a CNN; learning a non-continuity feature r2 from an input attribute by using DCNN; carrying out splicing by adopting a splicing technology and characteristics; sending the splicing result to a pooling layer, and sending the splicing result to a full connection layer after average pooling; and outputting a result by using a Softmax function to obtain an identification type. The method has the advantages that features can be automatically learned, identification errors are reduced, and discontinuous boundary types are accurately distinguished; feature differences between boundary lines can be highlighted; and interference of false boundaries in seismic data can be reduced.

Description

technical field

[0001] The invention relates to the technical field of oil and gas field exploration and development, in particular to a method for identifying discontinuous boundaries inside reservoirs based on an expanded convolutional neural network. Background technique

[0002] The research on discontinuity (also called heterogeneity) inside the underground reservoir runs through the entire exploration and development process of oil and gas fields. As we all know, there are many different types of discontinuity boundaries in reservoirs, such as faults, fractures, and rock Their existence will directly affect the flow of underground fluids, which in turn will affect the distribution of remaining oil and the relationship between injection and production, and finally affect the effect of oil and gas development. With the development of computers and artificial intelligence, reducing the cost of exploration and development and improving the recognition accuracy of reservoir...

Images