Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Seismic data resolution improving method based on deep learning

A technology of seismic data and deep learning, which is applied in the fields of seismology, seismology, and seismic signal processing for logging records. problem, to achieve the effect of increasing the resolution

Pending Publication Date: 2021-03-05
CHINA PETROLEUM & CHEM CORP +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Seismic data are limited by acquisition, processing and interpretation techniques, and the resolution of processed seismic data is low
The high-resolution stratigraphic data corresponding to well logging data is limited by the number of logging wells and cannot describe the global seismic data
[0003] Most of the traditional methods for improving the resolution of seismic data assume that the seismic data is steady-state and the noise level does not change with space, but the actual situation does not meet this assumption, resulting in the effect of improving the resolution cannot meet the expected requirements

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 data resolution improving method based on deep learning
  • Seismic data resolution improving method based on deep learning
  • Seismic data resolution improving method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described below in conjunction with accompanying drawing.

[0044] figure 1 shows a method for improving the resolution of seismic data based on deep learning according to the present application, figure 2 The design idea of ​​the method is shown. exist figure 2 It can be seen from the design idea of ​​the deep network that to perform deep network training first, you need to obtain training data and training labels first, obtain a deep network training model, and then perform deep network training on low-resolution seismic data. After training, you can get the Reflection coefficients for low-resolution seismic data, and finally high-resolution seismic data.

[0045] Specifically, according to figure 1 The method includes the following steps:

[0046] Step 1: Collect seismic and logging data.

[0047] In this step, the acquired seismic and logging data should maintain the isotropic properties of the seismic data as much as po...

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 seismic data resolution improving method based on deep learning. The seismic data resolution improving method comprises the steps that: S10, seismic and logging data are acquired; S20, a deep network training model for seismic data resolution enhancement is established; and S30, deep learning training is carried out on the seismic and logging data by using the deep networktraining model to obtain high-resolution seismic and logging data. According to the method of the invention, the deep learning method and well-to-seismic combination are utilized to realize automaticenhancement of the ground seismic data and train the seismic and logging data, and therefore, the resolution of the seismic and logging data is improved, and a basis is provided for seismic and logging data analysis, and data support is provided for development of seismic exploration technology.

Description

technical field [0001] The invention relates to the technical field of seismic data processing, and more specifically, designs a method for improving the resolution of seismic data based on deep learning. Background technique [0002] Seismic data is limited by acquisition, processing and interpretation techniques, and the resolution of processed seismic data is low. The high-resolution stratigraphic data corresponding to well logging data is limited by the number of well logging and cannot describe the global seismic data. [0003] Most of the traditional methods for improving the resolution of seismic data assume that the seismic data is steady-state and the noise level does not change with space, but the actual situation does not meet this assumption, resulting in the effect of resolution-enhancing processing not meeting the expected requirements. [0004] The application of deep learning in the field of image and audio is becoming more and more mature, and the effect is...

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
IPC IPC(8): G01V1/28G01V1/40G01V1/30
CPCG01V1/282G01V1/40G01V1/307
Inventor 王小品
Owner CHINA PETROLEUM & CHEM CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products