Oil and gas reservoir characterization method based on convolutional neural network
A convolutional neural network and a technology for oil and gas reservoirs, which are applied in the fields of devices, oil and gas reservoir characterization methods, equipment and readable storage media, can solve the problems of low oil and gas reservoir development efficiency, time-consuming and labor-intensive, and heavy workload, etc. Achieve the effect of improving development efficiency, enhancing generalization ability, improving speed and accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0053] The following is an introduction to Embodiment 1 of a convolutional neural network-based oil and gas reservoir characterization method provided by this application, see figure 1 , embodiment one includes:
[0054] S101. Obtain seismic trace data;
[0055] S102. Intercepting the seismic trace data corresponding to the preset order of sedimentary cycles;
[0056] Specifically, the interception operation on the seismic trace data can be realized through the interception unit, which is located outside the convolutional neural network and is used to limit the input data to ensure that the input data is the seismic trace data corresponding to the depositional cycle of the preset order.
[0057] Among them, the sedimentary cycle refers to the regular and periodic repetition of several rocks with similar lithology and lithofacies on the vertical bottom section. According to the different scales, the sedimentary cycle is divided into levels, such as figure 2 As shown, the sc...
Embodiment 2
[0066] see Figure 4 , embodiment two specifically includes:
[0067] S401. Obtain seismic trace data;
[0068] S402. Intercepting the seismic trace data corresponding to the lowest order sedimentary cycle identifiable by seismic;
[0069] S403. Input the intercepted seismic trace data into the pre-trained convolutional neural network to obtain high-frequency synthetic records;
[0070] S404. According to the high-frequency synthetic records, determine the development position, geometric shape, scale and superposition relationship of small-scale geological bodies, so as to realize reservoir characterization.
[0071] This embodiment provides a convolutional neural network-based reservoir characterization method for oil and gas reservoirs, using convolutional neural networks to learn the relationship between relatively low-frequency seismic trace data and high-resolution synthetic records, corresponding to specific levels of depositional cycles The seismic trace data is the ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


