Seismic facies recognition model training method and device and seismic facies prediction method and device
A technology for seismic facies identification and model training, applied in the field of oil and gas exploration, can solve the problems of single distribution of seismic data, small amount of data, and automatic identification of weak dependence of seismic facies labels, so as to improve the prediction accuracy, reduce the degree of dependence, and solve the problem of artificial The effect of heavy workload
Pending Publication Date: 2022-03-25
CHINA UNIV OF PETROLEUM (BEIJING)
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
It solves the problem of weak automatic identification of seismic facies labels when the amount of seismic sample data used for training is small and the distribution of seismic data is relatively single, reduces the dependence on seismic facies labels, and greatly improves the efficiency of seismic facies while improving interpretation efficiency. Automatic identification accuracy to improve prediction accuracy across the entire seismic dataset
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
[0058] In order to better understand the technical solution in the present specification, the drawings in the examples will be described in conjunction with the drawings in the examples in the present specification, and the embodiments described herein will be described in conjunction with the embodiments described herein. Example is only a part of this embodiment, not all of the embodiments. Based on the embodiments herein, one of ordinary skill in the art does not have all other embodiments obtained under the pre-creative labor premise, it belongs to the scope of this paper.
[0059] It should be noted that the specification and claims in the present invention and the terms "first", "second", "second" or the like are used to distinguish a similar object without having to describe a particular order or ahead order. It should be understood that the data such as use can be interchanged in appropriate, so as to be described herein, in addition to those illustrated or described herei...
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 relates to the field of oil-gas exploration, in particular to a seismic facies recognition model training method and device and a seismic facies prediction method and device, and the training method comprises the steps: 1, obtaining seismic data; 2, determining a similar data set of each seismic data in the first seismic data set according to the correlation between the seismic data in the first seismic data set and the seismic data in the second seismic data set; step 3, assigning the seismic facies label of each seismic data in the first seismic data set to a related similar data set; 4, training a seismic facies recognition model; 5, judging whether the second seismic data set is null or not, and if yes, ending training; if not, executing the step 6; step 6, identifying boundary seismic data in the similar data set by using the seismic facies identification model obtained by training; step 7, updating the first seismic data set according to the boundary seismic data; according to the method, the degree of dependence on the seismic facies label can be reduced, and the seismic facies prediction precision can be improved.
Description
Technical field [0001] This paper relates to the field of oil and gas exploration, especially a seismic phase recognition model training method and device, seismic phase prediction method and apparatus. Background technique [0002] With the continuous in-depth, accurate division of oil and gas exploration, the identification of the seismic phase category is an important role in exploring the underground geological environment and geological structure, high resolution treatment, earthquake inversion, reservoir prediction, constructical interpretation. [0003] Traditional earthquake association needs to explain the person's naked eye observation seismic profile information, combined with its own expertise and experience give reasonable seismic phase division results. This process has a large randomness, easy to lose details, and it is difficult to construct a complex nonlinear inner relationship between seismic phase categories and seismic data. In the prior art, there is also a ...
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): G06K9/00G06K9/62
CPCG06F2218/22G06F2218/12G06F18/22G06F18/241
Inventor 袁三一贺粟梅陈胜宋朝辉王尚旭
Owner CHINA UNIV OF PETROLEUM (BEIJING)