Shale gas saturation determination method, device and equipment based on deep learning

Abstract

The invention provides a shale gas saturation determination method, device and equipment based on deep learning, and the method comprises the steps of obtaining the fracture permeability and target moment of a target stratum; converting the fracture permeability into equivalent matrix permeability to obtain equivalent permeability data of the target stratum; determining a target equivalent permeability field diagram of the target stratum according to the equivalent permeability data; and according to the target equivalent permeability field diagram and the target moment, determining a saturation field diagram of the target stratum at the target moment by utilizing a target deep convolution decoding network. In the embodiment of the invention, a solving problem of an uncertainty equation can be converted into a graph-graph regression problem by utilizing a target deep convolution solution coding network, and a relationship among a permeability field graph, a target moment and a saturation field graph is established. And the resolution of the image can be reduced through the target deep convolution decoding network, so that the calculation efficiency can be effectively improved, andthe technical effect of efficiently and accurately predicting saturation distribution is achieved.

Description

technical field [0001] The present application relates to the technical field of oil and gas exploration, in particular to a method, device and equipment for determining shale gas saturation based on deep learning. Background technique [0002] Reservoir description is an important content in geological research of oil and gas development, and it is the geological basis for formulating oil and gas reservoir development plans. Saturation distribution is a key parameter in reservoir description, and a reasonable, quantitative and precise characterization of saturation distribution is an urgent requirement for efficient development of oil and gas reservoirs. Shale gas is one of the important unconventional energy resources. Accurately predicting the saturation distribution of shale gas reservoirs is crucial for formulating a reasonable gas reservoir development strategy under uncertain conditions. [0003] In the prior art, the statistical distribution of saturation is usually...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a deep learning-based shale gas saturation determination method, device, and equipment to solve the problem of inability to efficiently and accurately determine the saturation distribution of each point in the formation to be studied at the target production time in the prior art. problem of prediction

Images