Unsupervised seismic data generation method based on Nash equilibrium principle
A seismic data and Nash equilibrium technology, applied in data processing applications, neural learning methods, biological neural network models, etc., can solve problems such as insufficient seismic data samples and unsupervised generation of seismic data
Pending Publication Date: 2022-05-03
CHINA PETROLEUM & CHEM CORP +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide a method for unsupervised generation of seismic data based on the principle of Nash equilibrium for the problem of insufficient seismic data samples with clear classification characteristics in the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] Below in conjunction with accompanying drawing, the present invention is described in detail.
[0031] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0032] Based on the Nash equilibrium principle, the unsupervised method directly uses the existing seismic data for unsupervised learning, such as figure 2 shown, including:
[0033] Step 101: input all the seismic data within the specified block range, interpret the horizon of the earthquake according to the interpretation process, preprocess and extract the seismic data of each layer according to the interpretation horizon, and use it as a training sample for the seismic data model identificat...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an unsupervised seismic data generation method based on a Nash equilibrium principle, and the method comprises the steps: enabling a generation network to generate seismic data with classification features, namely, enabling the generated seismic data to comprise reservoir features and gas-bearing features, to be a training sample set which can be greatly expanded, and enabling the seismic data to be directly used as a training sample; the identification network can be used for judging the consistency of the propagation law of the seismic data and directly checking the processing quality of the seismic data; the generated data is from real seismic data and implies a physical propagation rule of a target layer, so that the learning process of deep learning can be indirectly constrained and cannot be separated from a physical propagation model.
Description
technical field [0001] The invention relates to the technical field of seismic data processing and fluid prediction, in particular to a method for unsupervised generation of seismic data based on the Nash equilibrium principle. Background technique [0002] In the field of oil and gas exploration, some progress has been made in reservoir prediction and gas-bearing prediction based on deep learning methods. Artificial intelligence methods are used to carry out related research on reservoir prediction and gas-bearing prediction. Due to the application characteristics of exploration and development, although seismic data in the work area The amount of data is very large, but usually only the seismic data of the target interval is selected for research and application. Since the number of sample wells in the target layer is usually small, in the process of actually applying the deep learning method, it is necessary to match the seismic data of the target interval. The sample siz...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08G06Q10/04G06Q50/26
CPCG06N3/08G06Q10/04G06Q50/26G06N3/045G06F18/214G06F18/24
Inventor 喻勤许多詹国卫丁蔚楠王浩马昭军沈杰王金龙张剑飞张聪玲全永旺
Owner CHINA PETROLEUM & CHEM CORP