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

A High-Resolution Seismic Inversion Method Based on Joint Dictionary Learning and High-Frequency Prediction

A dictionary learning and high-resolution technology, which is applied in the fields of seismology, seismology, machine learning, etc. for well logging, can solve the problems of not generating more effective and reliable information, and achieve the improvement of spatial horizontal continuity, The effect of suppressing noise and rationally judging the basis

Active Publication Date: 2021-09-28
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In fact, these methods do not produce more effective and reliable information in essence. The so-called "high resolution" is more reflected in the pursuit of "high contrast" (that is, sharp boundaries) between formations.

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
  • A High-Resolution Seismic Inversion Method Based on Joint Dictionary Learning and High-Frequency Prediction
  • A High-Resolution Seismic Inversion Method Based on Joint Dictionary Learning and High-Frequency Prediction
  • A High-Resolution Seismic Inversion Method Based on Joint Dictionary Learning and High-Frequency Prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to facilitate the understanding of the technical content of the present invention, the following prior art is first introduced:

[0044] 1. Earthquake inversion model

[0045] Using the ZoEppritx equation approximation and based on convolutionary model, the positive performance of seismic observation data can be approximated as the following linear equation:

[0046] D = GX + E (1)

[0047] Where D represents the data vectors, the first matrix G in the right side of the equation is a normal matrix, X is the model parameters (such as inversion of the upper three-parameter inversion of the stack, X is constructed by the transformation of the vertical and horizontal wave impedance and density), E is an error between observing data and synthetic data. As known in the formula (1), the observed matrix G, the seismic inversion problem is estimated to estimate as possible model parameters X, so that the GX is more matched more agglomerated with the observed data D. By assu...

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 discloses a high-resolution seismic inversion method based on joint dictionary learning and high-frequency prediction, which is applied to seismic inversion, in order to solve the problem that the resolution of the inversion result of the traditional method in the prior art cannot reach the fine description of complex oil and gas reservoirs To solve the problem required, the present invention first improves the seismic inversion method based on dictionary learning and sparse representation by introducing a multi-channel inversion mechanism to generate reliable middle and low frequency inversion components, and secondly combines the middle and low frequency components provided by the logging position Correlation learning with high-frequency components, the final result predicts high-frequency components of model parameters at any position in space, realizes high-resolution seismic inversion effects, and lays a solid foundation for refined description of complex oil and gas reservoirs.

Description

Technical field [0001] The present invention belongs to the field of earth science, and in particular, the present invention relates to an seismic inversion technique. Background technique [0002] Earthquake inversion technology is a method of estimating the elastic physical parameters of underground media using seismic data and logging data collected in the field. This technology can be widely used in oil and gas resources exploration, engineering geological survey, ground abnormal physical examination, volcanic, earthquake, etc. In the field of oil and gas resource seismic exploration, earthquake inversion technology is the most important and most effective. However, with an effective exploration in the past a hundred years, the world's simplest oil and gas reservoir has almost developed. Complex noodles (including very oily temperament) is the focus of oil and gas exploration for a longer period of time in the future; at the same time, due to the decline in oil prices, low-co...

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 Patents(China)
IPC IPC(8): G01V1/30G01V1/40G06N20/00
CPCG01V1/306G01V1/40G01V2210/6161G01V2210/6169G01V2210/6242G06N20/00
Inventor 王峣钧厍斌胡光岷
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com