Supercharge Your Innovation With Domain-Expert AI Agents!

Seismic facies analysis method based on support vector machine algorithm

A technology that supports vector machines and analysis methods, applied in the field of oil and gas and coalbed methane seismic exploration and development, and can solve problems such as low interpretation and identification accuracy

Pending Publication Date: 2021-03-05
CHINA PETROLEUM & CHEM CORP +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is generally used in the interpretation and analysis of local seismic data, and the accuracy of interpretation and identification is relatively low

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Seismic facies analysis method based on support vector machine algorithm
  • Seismic facies analysis method based on support vector machine algorithm
  • Seismic facies analysis method based on support vector machine algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Such as figure 1 Shown, the present invention proposes a kind of seismic facies analysis method based on support vector machine algorithm, mainly comprises the following steps:

[0050] S100, selecting N channels of seismic data to be classified from the post-stack seismic data volume of the target layer;

[0051] S200, acquire known K categories of sample data that can represent the lateral variation of seismic signals in a region of the target layer; where K≤N

[0052] S300, using known sample data to train a support vector machine to determine K classification functions for dividing the sample data into K categories;

[0053] S400, using the trained K classification functions to classify the N channels of seismic data to be classified, so as to divide the N channels of seismic data into K partitions;

[0054] S500, forming seismic facies based on the classification results, and analyzing the spatial variation of petrophysical parameters and sedimentary facies corresp...

Embodiment 2

[0056] The working process of the above-mentioned seismic facies analysis method based on the support vector machine algorithm will be described in detail below in conjunction with the embodiments.

[0057] Here, the purpose of the present invention is to divide the seismic data into K (K≤N) partitions under the condition of given N-channel seismic data set D and the number K of seismic facies to be distinguished, wherein, S k Represents the data set of each partition after partitioning, a partition is called a cluster, and each cluster represents a seismic facies.

[0058] First, for the post-stack seismic data volume of the target layer (time domain or depth domain), select the N-channel seismic data set D to be used for classification. Specifically, there are two ways to select: the first way is to give the center point and the size of the time window, and select the data block with the center point as the center of the time window and the size of the time window as the len...

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

No PUM Login to View More

Abstract

The invention provides a method for classifying seismic waveforms by using a support vector machine algorithm. The method comprises the following steps: firstly, selecting N seismic data to be classified from a post-stack seismic data volume of a target layer; acquiring known K types of sample data capable of representing transverse changes of seismic signals in a section of region of the target layer, wherein K < = N; training a support vector machine by utilizing known sample data so as to determine K classification functions for dividing the sample data into K categories; and then classifying the to-be-classified N seismic data by utilizing the K trained classification functions, and forming a selected rock physical parameter or sedimentary facies plane distribution rule graph accordingto a classification result.

Description

technical field [0001] The invention belongs to the seismic exploration and development of oil and gas and coal bed gas, in particular to a seismic facies analysis method based on a support vector machine algorithm. Background technique [0002] In the exploration and development of underground sedimentary minerals such as petroleum and coal, the study of sedimentary facies is of great significance. However, because the target layer is deeply buried underground, the research means and methods adopted are quite different from those of the sedimentary facies in the outcrop area. [0003] In subsurface facies analysis, the target sedimentary facies signs can only be observed through rock data, and drilling and coring are generally not carried out continuously, and the whole well coring rate of an exploratory well is often only a few percent to more than ten percent , which makes the study of sedimentary facies very difficult. Although the logging facies analysis using electri...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01V1/30
CPCG01V1/307G01V1/301
Inventor 郑四连刘百红朱海伟杨子兴
Owner CHINA PETROLEUM & CHEM CORP
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com